diff --git a/.claude/skills_lib/team-lifecycle-v2/SKILL.md b/.claude/skills_lib/team-lifecycle-v2/SKILL.md deleted file mode 100644 index c23b4ebb..00000000 --- a/.claude/skills_lib/team-lifecycle-v2/SKILL.md +++ /dev/null @@ -1,574 +0,0 @@ ---- -name: team-lifecycle-v2 -description: Unified team skill for full lifecycle - spec/impl/test. All roles invoke this skill with --role arg for role-specific execution. Triggers on "team lifecycle". -allowed-tools: TeamCreate(*), TeamDelete(*), SendMessage(*), TaskCreate(*), TaskUpdate(*), TaskList(*), TaskGet(*), Task(*), AskUserQuestion(*), TodoWrite(*), Read(*), Write(*), Edit(*), Bash(*), Glob(*), Grep(*) ---- - -# Team Lifecycle - -Unified team skill covering specification, implementation, testing, and review. All team members invoke this skill with `--role=xxx` to route to role-specific execution. - -## Architecture Overview - -``` -┌───────────────────────────────────────────────────┐ -│ Skill(skill="team-lifecycle-v2") │ -│ args="任务描述" 或 args="--role=xxx" │ -└───────────────────┬───────────────────────────────┘ - │ Role Router - │ - ┌──── --role present? ────┐ - │ NO │ YES - ↓ ↓ - Orchestration Mode Role Dispatch - (auto → coordinator) (route to role.md) - │ - ┌────┴────┬───────┬───────┬───────┬───────┬───────┬───────┐ - ↓ ↓ ↓ ↓ ↓ ↓ ↓ ↓ -┌──────────┐┌───────┐┌──────┐┌──────────┐┌───────┐┌────────┐┌──────┐┌────────┐ -│coordinator││analyst││writer││discussant││planner││executor││tester││reviewer│ -│ roles/ ││roles/ ││roles/││ roles/ ││roles/ ││ roles/ ││roles/││ roles/ │ -└──────────┘└───────┘└──────┘└──────────┘└───────┘└────────┘└──────┘└────────┘ - ↑ ↑ - on-demand by coordinator - ┌──────────┐ ┌─────────┐ - │ explorer │ │architect│ - │ (service)│ │(consult)│ - └──────────┘ └─────────┘ -``` - -## Command Architecture - -Each role is organized as a folder with a `role.md` orchestrator and optional `commands/` for delegation: - -``` -roles/ -├── coordinator/ -│ ├── role.md # Orchestrator (Phase 1/5 inline, Phase 2-4 delegate) -│ └── commands/ -│ ├── dispatch.md # Task chain creation (3 modes) -│ └── monitor.md # Coordination loop + message routing -├── analyst/ -│ ├── role.md -│ └── commands/ -├── writer/ -│ ├── role.md -│ └── commands/ -│ └── generate-doc.md # Multi-CLI document generation (4 doc types) -├── discussant/ -│ ├── role.md -│ └── commands/ -│ └── critique.md # Multi-perspective CLI critique -├── planner/ -│ ├── role.md -│ └── commands/ -│ └── explore.md # Multi-angle codebase exploration -├── executor/ -│ ├── role.md -│ └── commands/ -│ └── implement.md # Multi-backend code implementation -├── tester/ -│ ├── role.md -│ └── commands/ -│ └── validate.md # Test-fix cycle -├── reviewer/ -│ ├── role.md -│ └── commands/ -│ ├── code-review.md # 4-dimension code review -│ └── spec-quality.md # 5-dimension spec quality check -├── explorer/ # Service role (on-demand) -│ └── role.md # Multi-strategy code search & pattern discovery -└── architect/ # Consulting role (on-demand) - ├── role.md # Multi-mode architecture assessment - └── commands/ - └── assess.md # Mode-specific assessment strategies -├── fe-developer/ # Frontend pipeline role -│ └── role.md # Frontend component/page implementation -└── fe-qa/ # Frontend pipeline role - ├── role.md - └── commands/ - └── pre-delivery-checklist.md - └── role.md # 5-dimension frontend QA + GC loop -``` - -**Design principle**: role.md keeps Phase 1 (Task Discovery) and Phase 5 (Report) inline. Phases 2-4 either stay inline (simple logic) or delegate to `commands/*.md` via `Read("commands/xxx.md")` when they involve subagent delegation, CLI fan-out, or complex strategies. - -**Command files** are self-contained: each includes Strategy, Execution Steps, and Error Handling. Any subagent can `Read()` a command file and execute it independently. - -## Role Router - -### Input Parsing - -Parse `$ARGUMENTS` to extract `--role`: - -```javascript -const args = "$ARGUMENTS" -const roleMatch = args.match(/--role[=\s]+(\w+)/) -const teamName = args.match(/--team[=\s]+([\w-]+)/)?.[1] || "lifecycle" - -if (!roleMatch) { - // No --role: Orchestration Mode → auto route to coordinator - // See "Orchestration Mode" section below -} - -const role = roleMatch ? roleMatch[1] : "coordinator" -``` - -### Role Dispatch - -```javascript -const VALID_ROLES = { - "coordinator": { file: "roles/coordinator/role.md", prefix: null }, - "analyst": { file: "roles/analyst/role.md", prefix: "RESEARCH" }, - "writer": { file: "roles/writer/role.md", prefix: "DRAFT" }, - "discussant": { file: "roles/discussant/role.md", prefix: "DISCUSS" }, - "planner": { file: "roles/planner/role.md", prefix: "PLAN" }, - "executor": { file: "roles/executor/role.md", prefix: "IMPL" }, - "tester": { file: "roles/tester/role.md", prefix: "TEST" }, - "reviewer": { file: "roles/reviewer/role.md", prefix: ["REVIEW", "QUALITY"] }, - "explorer": { file: "roles/explorer/role.md", prefix: "EXPLORE", type: "service" }, - "architect": { file: "roles/architect/role.md", prefix: "ARCH", type: "consulting" }, - "fe-developer":{ file: "roles/fe-developer/role.md",prefix: "DEV-FE", type: "frontend-pipeline" }, - "fe-qa": { file: "roles/fe-qa/role.md", prefix: "QA-FE", type: "frontend-pipeline" } -} - -if (!VALID_ROLES[role]) { - throw new Error(`Unknown role: ${role}. Available: ${Object.keys(VALID_ROLES).join(', ')}`) -} - -// Read and execute role-specific logic -Read(VALID_ROLES[role].file) -// → Execute the 5-phase process defined in that file -``` - -### Orchestration Mode（无参数触发） - -当不带 `--role` 调用时，自动进入 coordinator 编排模式。用户只需传任务描述即可触发完整流程。 - -**触发方式**: - -```javascript -// 用户调用（无 --role）— 自动路由到 coordinator -Skill(skill="team-lifecycle-v2", args="任务描述") - -// 等价于 -Skill(skill="team-lifecycle-v2", args="--role=coordinator 任务描述") -``` - -**流程**: - -```javascript -if (!roleMatch) { - // Orchestration Mode: 自动路由到 coordinator - // coordinator role.md 将执行： - // Phase 1: 需求澄清 - // Phase 2: TeamCreate + spawn 所有 worker agents - // 每个 agent prompt 中包含 Skill(args="--role=xxx") 回调 - // Phase 3: 创建任务链 - // Phase 4: 监控协调循环 - // Phase 5: 结果汇报 - - const role = "coordinator" - Read(VALID_ROLES[role].file) -} -``` - -**完整调用链**: - -``` -用户: Skill(args="任务描述") - │ - ├─ SKILL.md: 无 --role → Orchestration Mode → 读取 coordinator role.md - │ - ├─ coordinator Phase 2: TeamCreate + spawn workers - │ 每个 worker prompt 中包含 Skill(args="--role=xxx") 回调 - │ - ├─ coordinator Phase 3: dispatch 任务链 - │ - ├─ worker 收到任务 → Skill(args="--role=xxx") → SKILL.md Role Router → role.md - │ 每个 worker 自动获取: - │ ├─ 角色定义 (role.md: identity, boundaries, message types) - │ ├─ 可用命令 (commands/*.md) - │ └─ 执行逻辑 (5-phase process) - │ - └─ coordinator Phase 4-5: 监控 → 结果汇报 -``` - -### Available Roles - -| Role | Task Prefix | Responsibility | Role File | -|------|-------------|----------------|-----------| -| `coordinator` | N/A | Pipeline orchestration, requirement clarification, task dispatch | [roles/coordinator/role.md](roles/coordinator/role.md) | -| `analyst` | RESEARCH-* | Seed analysis, codebase exploration, context gathering | [roles/analyst/role.md](roles/analyst/role.md) | -| `writer` | DRAFT-* | Product Brief / PRD / Architecture / Epics generation | [roles/writer/role.md](roles/writer/role.md) | -| `discussant` | DISCUSS-* | Multi-perspective critique, consensus building | [roles/discussant/role.md](roles/discussant/role.md) | -| `planner` | PLAN-* | Multi-angle exploration, structured planning | [roles/planner/role.md](roles/planner/role.md) | -| `executor` | IMPL-* | Code implementation following plans | [roles/executor/role.md](roles/executor/role.md) | -| `tester` | TEST-* | Adaptive test-fix cycles, quality gates | [roles/tester/role.md](roles/tester/role.md) | -| `reviewer` | `REVIEW-*` + `QUALITY-*` | Code review + Spec quality validation (auto-switch by prefix) | [roles/reviewer/role.md](roles/reviewer/role.md) | -| `explorer` | EXPLORE-* | Code search, pattern discovery, dependency tracing (service role, on-demand) | [roles/explorer/role.md](roles/explorer/role.md) | -| `architect` | ARCH-* | Architecture assessment, tech feasibility, design review (consulting role, on-demand) | [roles/architect/role.md](roles/architect/role.md) | -| `fe-developer` | DEV-FE-* | Frontend component/page implementation, design token consumption (frontend pipeline) | [roles/fe-developer/role.md](roles/fe-developer/role.md) | -| `fe-qa` | QA-FE-* | 5-dimension frontend QA, accessibility, design compliance, GC loop (frontend pipeline) | [roles/fe-qa/role.md](roles/fe-qa/role.md) | - -## Shared Infrastructure - -### Role Isolation Rules - -**核心原则**: 每个角色仅能执行自己职责范围内的工作。 - -#### Output Tagging（强制） - -所有角色的输出必须带 `[role_name]` 标识前缀： - -```javascript -// SendMessage — content 和 summary 都必须带标识 -SendMessage({ - content: `## [${role}] ...`, - summary: `[${role}] ...` -}) - -// team_msg — summary 必须带标识 -mcp__ccw-tools__team_msg({ - summary: `[${role}] ...` -}) -``` - -#### Coordinator 隔离 - -| 允许 | 禁止 | -|------|------| -| 需求澄清 (AskUserQuestion) | ❌ 直接编写/修改代码 | -| 创建任务链 (TaskCreate) | ❌ 调用实现类 subagent (code-developer 等) | -| 分发任务给 worker | ❌ 直接执行分析/测试/审查 | -| 监控进度 (消息总线) | ❌ 绕过 worker 自行完成任务 | -| 汇报结果给用户 | ❌ 修改源代码或产物文件 | - -#### Worker 隔离 - -| 允许 | 禁止 | -|------|------| -| 处理自己前缀的任务 | ❌ 处理其他角色前缀的任务 | -| SendMessage 给 coordinator | ❌ 直接与其他 worker 通信 | -| 使用 Toolbox 中声明的工具 | ❌ 为其他角色创建任务 (TaskCreate) | -| 委派给 commands/ 中的命令 | ❌ 修改不属于本职责的资源 | - -### Message Bus (All Roles) - -Every SendMessage **before**, must call `mcp__ccw-tools__team_msg` to log: - -```javascript -mcp__ccw-tools__team_msg({ - operation: "log", - team: teamName, - from: role, - to: "coordinator", - type: "", - summary: `[${role}] `, - ref: "" -}) -``` - -**Message types by role**: - -| Role | Types | -|------|-------| -| coordinator | `plan_approved`, `plan_revision`, `task_unblocked`, `fix_required`, `error`, `shutdown` | -| analyst | `research_ready`, `research_progress`, `error` | -| writer | `draft_ready`, `draft_revision`, `impl_progress`, `error` | -| discussant | `discussion_ready`, `discussion_blocked`, `impl_progress`, `error` | -| planner | `plan_ready`, `plan_revision`, `impl_progress`, `error` | -| executor | `impl_complete`, `impl_progress`, `error` | -| tester | `test_result`, `impl_progress`, `fix_required`, `error` | -| reviewer | `review_result`, `quality_result`, `fix_required`, `error` | -| explorer | `explore_ready`, `explore_progress`, `task_failed` | -| architect | `arch_ready`, `arch_concern`, `arch_progress`, `error` | -| fe-developer | `dev_fe_complete`, `dev_fe_progress`, `error` | -| fe-qa | `qa_fe_passed`, `qa_fe_result`, `fix_required`, `error` | - -### CLI Fallback - -When `mcp__ccw-tools__team_msg` MCP is unavailable: - -```javascript -Bash(`ccw team log --team "${teamName}" --from "${role}" --to "coordinator" --type "" --summary "[${role}] " --json`) -Bash(`ccw team list --team "${teamName}" --last 10 --json`) -Bash(`ccw team status --team "${teamName}" --json`) -``` - -### Wisdom Accumulation (All Roles) - -跨任务知识积累机制。Coordinator 在 session 初始化时创建 `wisdom/` 目录，所有 worker 在执行过程中读取和贡献 wisdom。 - -**目录结构**: -``` -{sessionFolder}/wisdom/ -├── learnings.md # 发现的模式和洞察 -├── decisions.md # 架构和设计决策 -├── conventions.md # 代码库约定 -└── issues.md # 已知风险和问题 -``` - -**Phase 2 加载（所有 worker）**: -```javascript -// Load wisdom context at start of Phase 2 -const sessionFolder = task.description.match(/Session:\s*([^\n]+)/)?.[1]?.trim() -let wisdom = {} -if (sessionFolder) { - try { wisdom.learnings = Read(`${sessionFolder}/wisdom/learnings.md`) } catch {} - try { wisdom.decisions = Read(`${sessionFolder}/wisdom/decisions.md`) } catch {} - try { wisdom.conventions = Read(`${sessionFolder}/wisdom/conventions.md`) } catch {} - try { wisdom.issues = Read(`${sessionFolder}/wisdom/issues.md`) } catch {} -} -``` - -**Phase 4/5 贡献（任务完成时）**: -```javascript -// Contribute wisdom after task completion -if (sessionFolder) { - const timestamp = new Date().toISOString().substring(0, 10) - - // Role-specific contributions: - // analyst → learnings (exploration dimensions, codebase patterns) - // writer → conventions (document structure, naming patterns) - // planner → decisions (task decomposition rationale) - // executor → learnings (implementation patterns), issues (bugs encountered) - // tester → issues (test failures, edge cases), learnings (test patterns) - // reviewer → conventions (code quality patterns), issues (review findings) - // explorer → conventions (codebase patterns), learnings (dependency insights) - // architect → decisions (architecture choices), issues (architectural risks) - - try { - const targetFile = `${sessionFolder}/wisdom/${wisdomTarget}.md` - const existing = Read(targetFile) - const entry = `- [${timestamp}] [${role}] ${wisdomEntry}` - Write(targetFile, existing + '\n' + entry) - } catch {} // wisdom not initialized -} -``` - -**Coordinator 注入**: Coordinator 在 spawn worker 时通过 task description 传递 `Session: {sessionFolder}`，worker 据此定位 wisdom 目录。已有 wisdom 内容为后续 worker 提供上下文，实现跨任务知识传递。 - -### Task Lifecycle (All Worker Roles) - -```javascript -// Standard task lifecycle every worker role follows -// Phase 1: Discovery -const tasks = TaskList() -const prefixes = Array.isArray(VALID_ROLES[role].prefix) ? VALID_ROLES[role].prefix : [VALID_ROLES[role].prefix] -const myTasks = tasks.filter(t => - prefixes.some(p => t.subject.startsWith(`${p}-`)) && - t.owner === role && - t.status === 'pending' && - t.blockedBy.length === 0 -) -if (myTasks.length === 0) return // idle -const task = TaskGet({ taskId: myTasks[0].id }) -TaskUpdate({ taskId: task.id, status: 'in_progress' }) - -// Phase 1.5: Resume Artifact Check (防止重复产出) -// 当 session 从暂停恢复时，coordinator 已将 in_progress 任务重置为 pending。 -// Worker 在开始工作前，必须检查该任务的输出产物是否已存在。 -// 如果产物已存在且内容完整： -// → 直接跳到 Phase 5 报告完成（避免覆盖上次成果） -// 如果产物存在但不完整（如文件为空或缺少关键 section）： -// → 正常执行 Phase 2-4（基于已有产物继续，而非从头开始） -// 如果产物不存在： -// → 正常执行 Phase 2-4 -// -// 每个 role 检查自己的输出路径: -// analyst → sessionFolder/spec/discovery-context.json -// writer → sessionFolder/spec/{product-brief.md | requirements/ | architecture/ | epics/} -// discussant → sessionFolder/discussions/discuss-NNN-*.md -// planner → sessionFolder/plan/plan.json -// executor → git diff (已提交的代码变更) -// tester → test pass rate -// reviewer → sessionFolder/spec/readiness-report.md (quality) 或 review findings (code) - -// Phase 2-4: Role-specific (see roles/{role}/role.md) - -// Phase 5: Report + Loop — 所有输出必须带 [role] 标识 -mcp__ccw-tools__team_msg({ operation: "log", team: teamName, from: role, to: "coordinator", type: "...", summary: `[${role}] ...` }) -SendMessage({ type: "message", recipient: "coordinator", content: `## [${role}] ...`, summary: `[${role}] ...` }) -TaskUpdate({ taskId: task.id, status: 'completed' }) -// Check for next task → back to Phase 1 -``` - -## Three-Mode Pipeline - -``` -Spec-only: - RESEARCH-001 → DISCUSS-001 → DRAFT-001 → DISCUSS-002 - → DRAFT-002 → DISCUSS-003 → DRAFT-003 → DISCUSS-004 - → DRAFT-004 → DISCUSS-005 → QUALITY-001 → DISCUSS-006 - -Impl-only (backend): - PLAN-001 → IMPL-001 → TEST-001 + REVIEW-001 - -Full-lifecycle (backend): - [Spec pipeline] → PLAN-001(blockedBy: DISCUSS-006) → IMPL-001 → TEST-001 + REVIEW-001 -``` - -### Frontend Pipelines - -Coordinator 根据任务关键词自动检测前端任务并路由到前端子流水线： - -``` -FE-only (纯前端): - PLAN-001 → DEV-FE-001 → QA-FE-001 - (GC loop: if QA-FE verdict=NEEDS_FIX → DEV-FE-002 → QA-FE-002, max 2 rounds) - -Fullstack (前后端并行): - PLAN-001 → IMPL-001 ∥ DEV-FE-001 → TEST-001 ∥ QA-FE-001 → REVIEW-001 - -Full-lifecycle + FE: - [Spec pipeline] → PLAN-001(blockedBy: DISCUSS-006) - → IMPL-001 ∥ DEV-FE-001 → TEST-001 ∥ QA-FE-001 → REVIEW-001 -``` - -### Frontend Detection - -Coordinator 在 Phase 1 根据任务关键词 + 项目文件自动检测前端任务并选择流水线模式（fe-only / fullstack / impl-only）。检测逻辑见 [roles/coordinator/role.md](roles/coordinator/role.md)。 - -### Generator-Critic Loop (fe-developer ↔ fe-qa) - -``` -┌──────────────┐ DEV-FE artifact ┌──────────┐ -│ fe-developer │ ──────────────────→ │ fe-qa │ -│ (Generator) │ │ (Critic) │ -│ │ ←────────────────── │ │ -└──────────────┘ QA-FE feedback └──────────┘ - (max 2 rounds) - -Convergence: fe-qa.score >= 8 && fe-qa.critical_count === 0 -``` - -## Unified Session Directory - -All session artifacts are stored under a single session folder: - -``` -.workflow/.team/TLS-{slug}-{YYYY-MM-DD}/ -├── team-session.json # Session state (status, progress, completed_tasks) -├── spec/ # Spec artifacts (analyst, writer, reviewer output) -│ ├── spec-config.json -│ ├── discovery-context.json -│ ├── product-brief.md -│ ├── requirements/ # _index.md + REQ-*.md + NFR-*.md -│ ├── architecture/ # _index.md + ADR-*.md -│ ├── epics/ # _index.md + EPIC-*.md -│ ├── readiness-report.md -│ └── spec-summary.md -├── discussions/ # Discussion records (discussant output) -│ └── discuss-001..006.md -├── plan/ # Plan artifacts (planner output) -│ ├── exploration-{angle}.json -│ ├── explorations-manifest.json -│ ├── plan.json -│ └── .task/ -│ └── TASK-*.json -├── explorations/ # Explorer output (cached for cross-role reuse) -│ └── explore-*.json -├── architecture/ # Architect output (assessment reports) -│ └── arch-*.json -└── wisdom/ # Cross-task accumulated knowledge - ├── learnings.md # Patterns and insights discovered - ├── decisions.md # Architectural decisions made - ├── conventions.md # Codebase conventions found - └── issues.md # Known issues and risks -├── qa/ # QA output (fe-qa audit reports) -│ └── audit-fe-*.json -└── build/ # Frontend build output (fe-developer) - ├── token-files/ - └── component-files/ -``` - -Messages remain at `.workflow/.team-msg/{team-name}/` (unchanged). - -## Session Resume - -Coordinator supports `--resume` / `--continue` flags to resume interrupted sessions: - -1. Scans `.workflow/.team/TLS-*/team-session.json` for `status: "active"` or `"paused"` -2. Multiple matches → `AskUserQuestion` for user selection -3. **Audit TaskList** — 获取当前所有任务的真实状态 -4. **Reconcile** — 双向同步 session.completed_tasks ↔ TaskList 状态: - - session 已完成但 TaskList 未标记 → 修正 TaskList 为 completed - - TaskList 已完成但 session 未记录 → 补录到 session - - in_progress 状态（暂停中断）→ 重置为 pending -5. Determines remaining pipeline from reconciled state -6. Rebuilds team (`TeamCreate` + worker spawns for needed roles only) -7. Creates missing tasks with correct `blockedBy` dependency chain (uses `TASK_METADATA` lookup) -8. Verifies dependency chain integrity for existing tasks -9. Updates session file with reconciled state + current_phase -10. **Kick** — 向首个可执行任务的 worker 发送 `task_unblocked` 消息，打破 resume 死锁 -11. Jumps to Phase 4 coordination loop - -## Coordinator Spawn Template - -When coordinator creates teammates, use this pattern: - -```javascript -TeamCreate({ team_name: teamName }) - -// For each worker role: -Task({ - subagent_type: "general-purpose", - description: `Spawn ${roleName} worker`, // ← 必填参数 - team_name: teamName, - name: "", - prompt: `你是 team "${teamName}" 的 . - -## ⚠️ 首要指令（MUST） -你的所有工作必须通过调用 Skill 获取角色定义后执行，禁止自行发挥： -Skill(skill="team-lifecycle-v2", args="--role=") -此调用会加载你的角色定义（role.md）、可用命令（commands/*.md）和完整执行逻辑。 - -当前需求: ${taskDescription} -约束: ${constraints} -Session: ${sessionFolder} - -## 角色准则（强制） -- 你只能处理 -* 前缀的任务，不得执行其他角色的工作 -- 所有输出（SendMessage、team_msg）必须带 [] 标识前缀 -- 仅与 coordinator 通信，不得直接联系其他 worker -- 不得使用 TaskCreate 为其他角色创建任务 - -## 消息总线（必须） -每次 SendMessage 前，先调用 mcp__ccw-tools__team_msg 记录。 - -## 工作流程（严格按顺序） -1. 调用 Skill(skill="team-lifecycle-v2", args="--role=") 获取角色定义和执行逻辑 -2. 按 role.md 中的 5-Phase 流程执行（TaskList → 找到 -* 任务 → 执行 → 汇报） -3. team_msg log + SendMessage 结果给 coordinator（带 [] 标识） -4. TaskUpdate completed → 检查下一个任务 → 回到步骤 1` -}) -``` - -See [roles/coordinator/role.md](roles/coordinator/role.md) for the full spawn implementation with per-role prompts. - -## Shared Spec Resources - -Writer 和 Reviewer 角色在 spec 模式下使用本 skill 内置的标准和模板（从 spec-generator 复制，独立维护）： - -| Resource | Path | Usage | -|----------|------|-------| -| Document Standards | `specs/document-standards.md` | YAML frontmatter、命名规范、内容结构 | -| Quality Gates | `specs/quality-gates.md` | Per-phase 质量门禁、评分标尺 | -| Product Brief Template | `templates/product-brief.md` | DRAFT-001 文档生成 | -| Requirements Template | `templates/requirements-prd.md` | DRAFT-002 文档生成 | -| Architecture Template | `templates/architecture-doc.md` | DRAFT-003 文档生成 | -| Epics Template | `templates/epics-template.md` | DRAFT-004 文档生成 | - -> Writer 在执行每个 DRAFT-* 任务前 **必须先 Read** 对应的 template 文件和 document-standards.md。 -> 从 `roles/` 子目录引用时路径为 `../../specs/` 和 `../../templates/`。 - -## Error Handling - -| Scenario | Resolution | -|----------|------------| -| Unknown --role value | Error with available role list | -| Missing --role arg | Orchestration Mode → auto route to coordinator | -| Role file not found | Error with expected path (roles/{name}/role.md) | -| Command file not found | Fall back to inline execution in role.md | -| Task prefix conflict | Log warning, proceed | diff --git a/.claude/skills_lib/team-lifecycle-v2/roles/analyst/role.md b/.claude/skills_lib/team-lifecycle-v2/roles/analyst/role.md deleted file mode 100644 index ded63cf9..00000000 --- a/.claude/skills_lib/team-lifecycle-v2/roles/analyst/role.md +++ /dev/null @@ -1,271 +0,0 @@ -# Role: analyst - -Seed analysis, codebase exploration, and multi-dimensional context gathering. Maps to spec-generator Phase 1 (Discovery). - -## Role Identity - -- **Name**: `analyst` -- **Task Prefix**: `RESEARCH-*` -- **Output Tag**: `[analyst]` -- **Responsibility**: Seed Analysis → Codebase Exploration → Context Packaging → Report -- **Communication**: SendMessage to coordinator only - -## Role Boundaries - -### MUST -- Only process RESEARCH-* tasks -- Communicate only with coordinator -- Use Toolbox tools (ACE search, Gemini CLI) -- Generate discovery-context.json and spec-config.json -- Support file reference input (@ prefix or .md/.txt extension) - -### MUST NOT -- Create tasks for other roles -- Directly contact other workers -- Modify spec documents (only create discovery-context.json and spec-config.json) -- Skip seed analysis step -- Proceed without codebase detection - -## Message Types - -| Type | Direction | Trigger | Description | -|------|-----------|---------|-------------| -| `research_ready` | analyst → coordinator | Research complete | With discovery-context.json path and dimension summary | -| `research_progress` | analyst → coordinator | Long research progress | Intermediate progress update | -| `error` | analyst → coordinator | Unrecoverable error | Codebase access failure, CLI timeout, etc. | - -## Message Bus - -Before every `SendMessage`, MUST call `mcp__ccw-tools__team_msg` to log: - -```javascript -// Research complete -mcp__ccw-tools__team_msg({ - operation: "log", - team: teamName, - from: "analyst", - to: "coordinator", - type: "research_ready", - summary: "[analyst] Research done: 5 exploration dimensions", - ref: `${sessionFolder}/spec/discovery-context.json` -}) - -// Error report -mcp__ccw-tools__team_msg({ - operation: "log", - team: teamName, - from: "analyst", - to: "coordinator", - type: "error", - summary: "[analyst] Codebase access failed" -}) -``` - -### CLI Fallback - -When `mcp__ccw-tools__team_msg` MCP is unavailable: - -```bash -ccw team log --team "${teamName}" --from "analyst" --to "coordinator" --type "research_ready" --summary "[analyst] Research done" --ref "${sessionFolder}/discovery-context.json" --json -``` - -## Toolbox - -### Available Commands -- None (simple enough for inline execution) - -### Subagent Capabilities -- None - -### CLI Capabilities -- `ccw cli --tool gemini --mode analysis` for seed analysis - -## Execution (5-Phase) - -### Phase 1: Task Discovery - -```javascript -const tasks = TaskList() -const myTasks = tasks.filter(t => - t.subject.startsWith('RESEARCH-') && - t.owner === 'analyst' && - t.status === 'pending' && - t.blockedBy.length === 0 -) - -if (myTasks.length === 0) return // idle - -const task = TaskGet({ taskId: myTasks[0].id }) -TaskUpdate({ taskId: task.id, status: 'in_progress' }) -``` - -### Phase 2: Seed Analysis - -```javascript -// Extract session folder from task description -const sessionMatch = task.description.match(/Session:\s*(.+)/) -const sessionFolder = sessionMatch ? sessionMatch[1].trim() : '.workflow/.team/default' - -// Parse topic from task description -const topicLines = task.description.split('\n').filter(l => !l.startsWith('Session:') && !l.startsWith('输出:') && l.trim()) -const rawTopic = topicLines[0] || task.subject.replace('RESEARCH-001: ', '') - -// 支持文件引用输入（与 spec-generator Phase 1 一致） -const topic = (rawTopic.startsWith('@') || rawTopic.endsWith('.md') || rawTopic.endsWith('.txt')) - ? Read(rawTopic.replace(/^@/, '')) - : rawTopic - -// Use Gemini CLI for seed analysis -Bash({ - command: `ccw cli -p "PURPOSE: Analyze the following topic/idea and extract structured seed information for specification generation. -TASK: -• Extract problem statement (what problem does this solve) -• Identify target users and their pain points -• Determine domain and industry context -• List constraints and assumptions -• Identify 3-5 exploration dimensions for deeper research -• Assess complexity (simple/moderate/complex) - -TOPIC: ${topic} - -MODE: analysis -CONTEXT: @**/* -EXPECTED: JSON output with fields: problem_statement, target_users[], domain, constraints[], exploration_dimensions[], complexity_assessment -CONSTRAINTS: Output as valid JSON" --tool gemini --mode analysis --rule analysis-analyze-technical-document`, - run_in_background: true -}) -// Wait for CLI result, then parse seedAnalysis from output -``` - -### Phase 3: Codebase Exploration (conditional) - -```javascript -// Check if there's an existing codebase to explore -const hasProject = Bash(`test -f package.json || test -f Cargo.toml || test -f pyproject.toml || test -f go.mod; echo $?`) - -if (hasProject === '0') { - mcp__ccw-tools__team_msg({ - operation: "log", - team: teamName, - from: "analyst", - to: "coordinator", - type: "research_progress", - summary: "[analyst] 种子分析完成, 开始代码库探索" - }) - - // Explore codebase using ACE search - const archSearch = mcp__ace-tool__search_context({ - project_root_path: projectRoot, - query: `Architecture patterns, main modules, entry points for: ${topic}` - }) - - // Detect tech stack from package files - // Explore existing patterns and integration points - - var codebaseContext = { - tech_stack, - architecture_patterns, - existing_conventions, - integration_points, - constraints_from_codebase: [] - } -} else { - var codebaseContext = null -} -``` - -### Phase 4: Context Packaging - -```javascript -// Generate spec-config.json -const specConfig = { - session_id: `SPEC-${topicSlug}-${dateStr}`, - topic: topic, - status: "research_complete", - complexity: seedAnalysis.complexity_assessment || "moderate", - depth: task.description.match(/讨论深度:\s*(.+)/)?.[1] || "standard", - focus_areas: seedAnalysis.exploration_dimensions || [], - mode: "interactive", // team 模式始终交互 - phases_completed: ["discovery"], - created_at: new Date().toISOString(), - session_folder: sessionFolder, - discussion_depth: task.description.match(/讨论深度:\s*(.+)/)?.[1] || "standard" -} -Write(`${sessionFolder}/spec/spec-config.json`, JSON.stringify(specConfig, null, 2)) - -// Generate discovery-context.json -const discoveryContext = { - session_id: specConfig.session_id, - phase: 1, - document_type: "discovery-context", - status: "complete", - generated_at: new Date().toISOString(), - seed_analysis: { - problem_statement: seedAnalysis.problem_statement, - target_users: seedAnalysis.target_users, - domain: seedAnalysis.domain, - constraints: seedAnalysis.constraints, - exploration_dimensions: seedAnalysis.exploration_dimensions, - complexity: seedAnalysis.complexity_assessment - }, - codebase_context: codebaseContext, - recommendations: { focus_areas: [], risks: [], open_questions: [] } -} -Write(`${sessionFolder}/spec/discovery-context.json`, JSON.stringify(discoveryContext, null, 2)) -``` - -### Phase 5: Report to Coordinator - -```javascript -const dimensionCount = discoveryContext.seed_analysis.exploration_dimensions?.length || 0 -const hasCodebase = codebaseContext !== null - -mcp__ccw-tools__team_msg({ - operation: "log", team: teamName, - from: "analyst", to: "coordinator", - type: "research_ready", - summary: `[analyst] 研究完成: ${dimensionCount}个探索维度, ${hasCodebase ? '有' : '无'}代码库上下文, 复杂度=${specConfig.complexity}`, - ref: `${sessionFolder}/discovery-context.json` -}) - -SendMessage({ - type: "message", - recipient: "coordinator", - content: `[analyst] ## 研究分析结果 - -**Task**: ${task.subject} -**复杂度**: ${specConfig.complexity} -**代码库**: ${hasCodebase ? '已检测到现有项目' : '全新项目'} - -### 问题陈述 -${discoveryContext.seed_analysis.problem_statement} - -### 目标用户 -${(discoveryContext.seed_analysis.target_users || []).map(u => '- ' + u).join('\n')} - -### 探索维度 -${(discoveryContext.seed_analysis.exploration_dimensions || []).map((d, i) => (i+1) + '. ' + d).join('\n')} - -### 输出位置 -- Config: ${sessionFolder}/spec/spec-config.json -- Context: ${sessionFolder}/spec/discovery-context.json - -研究已就绪，可进入讨论轮次 DISCUSS-001。`, - summary: `[analyst] 研究就绪: ${dimensionCount}维度, ${specConfig.complexity}` -}) - -TaskUpdate({ taskId: task.id, status: 'completed' }) - -// Check for next RESEARCH task → back to Phase 1 -``` - -## Error Handling - -| Scenario | Resolution | -|----------|------------| -| No RESEARCH-* tasks available | Idle, wait for coordinator assignment | -| Gemini CLI analysis failure | Fallback to direct Claude analysis without CLI | -| Codebase detection failed | Continue as new project (no codebase context) | -| Session folder cannot be created | Notify coordinator, request alternative path | -| Topic too vague for analysis | Report to coordinator with clarification questions | -| Unexpected error | Log error via team_msg, report to coordinator | diff --git a/.claude/skills_lib/team-lifecycle-v2/roles/architect/commands/assess.md b/.claude/skills_lib/team-lifecycle-v2/roles/architect/commands/assess.md deleted file mode 100644 index 8fd76f66..00000000 --- a/.claude/skills_lib/team-lifecycle-v2/roles/architect/commands/assess.md +++ /dev/null @@ -1,271 +0,0 @@ -# Assess Command - -## Purpose -Multi-mode architecture assessment with mode-specific analysis strategies. Delegated from architect role.md Phase 3. - -## Input Context - -```javascript -// Provided by role.md Phase 2 -const { consultMode, sessionFolder, wisdom, explorations, projectTech, task } = context -``` - -## Mode Strategies - -### spec-review (ARCH-SPEC-*) - -审查架构文档的技术合理性。 - -```javascript -const dimensions = [ - { name: 'consistency', weight: 0.25 }, - { name: 'scalability', weight: 0.25 }, - { name: 'security', weight: 0.25 }, - { name: 'tech-fitness', weight: 0.25 } -] - -// Load architecture documents -const archIndex = Read(`${sessionFolder}/spec/architecture/_index.md`) -const adrFiles = Glob({ pattern: `${sessionFolder}/spec/architecture/ADR-*.md` }) -const adrs = adrFiles.map(f => ({ path: f, content: Read(f) })) - -// Check ADR consistency -const adrDecisions = adrs.map(adr => { - const status = adr.content.match(/status:\s*(\w+)/i)?.[1] - const context = adr.content.match(/## Context\n([\s\S]*?)##/)?.[1]?.trim() - const decision = adr.content.match(/## Decision\n([\s\S]*?)##/)?.[1]?.trim() - return { path: adr.path, status, context, decision } -}) - -// Cross-reference: ADR decisions vs architecture index -// Flag contradictions between ADRs -// Check if tech choices align with project-tech.json - -for (const dim of dimensions) { - const score = evaluateDimension(dim.name, archIndex, adrs, projectTech) - assessment.dimensions.push({ name: dim.name, score, weight: dim.weight }) -} -``` - -### plan-review (ARCH-PLAN-*) - -审查实现计划的架构合理性。 - -```javascript -const plan = JSON.parse(Read(`${sessionFolder}/plan/plan.json`)) -const taskFiles = Glob({ pattern: `${sessionFolder}/plan/.task/TASK-*.json` }) -const tasks = taskFiles.map(f => JSON.parse(Read(f))) - -// 1. Dependency cycle detection -function detectCycles(tasks) { - const graph = {} - tasks.forEach(t => { graph[t.id] = t.depends_on || [] }) - const visited = new Set(), inStack = new Set() - function dfs(node) { - if (inStack.has(node)) return true // cycle - if (visited.has(node)) return false - visited.add(node); inStack.add(node) - for (const dep of (graph[node] || [])) { - if (dfs(dep)) return true - } - inStack.delete(node) - return false - } - return Object.keys(graph).filter(n => dfs(n)) -} -const cycles = detectCycles(tasks) -if (cycles.length > 0) { - assessment.concerns.push({ - severity: 'high', - concern: `Circular dependency detected: ${cycles.join(' → ')}`, - suggestion: 'Break cycle by extracting shared interface or reordering tasks' - }) -} - -// 2. Task granularity check -tasks.forEach(t => { - const fileCount = (t.files || []).length - if (fileCount > 8) { - assessment.concerns.push({ - severity: 'medium', - task: t.id, - concern: `Task touches ${fileCount} files — may be too coarse`, - suggestion: 'Split into smaller tasks with clearer boundaries' - }) - } -}) - -// 3. Convention compliance (from wisdom) -if (wisdom.conventions) { - // Check if plan follows discovered conventions -} - -// 4. Architecture alignment (from wisdom.decisions) -if (wisdom.decisions) { - // Verify plan doesn't contradict previous architectural decisions -} -``` - -### code-review (ARCH-CODE-*) - -评估代码变更的架构影响。 - -```javascript -const changedFiles = Bash(`git diff --name-only HEAD~1 2>/dev/null || git diff --name-only --cached`) - .split('\n').filter(Boolean) - -// 1. Layer violation detection -function detectLayerViolation(file, content) { - // Check import depth — deeper layers should not import from shallower - const imports = (content.match(/from\s+['"]([^'"]+)['"]/g) || []) - .map(i => i.match(/['"]([^'"]+)['"]/)?.[1]).filter(Boolean) - return imports.filter(imp => isUpwardImport(file, imp)) -} - -// 2. New dependency analysis -const pkgChanges = changedFiles.filter(f => f.includes('package.json')) -if (pkgChanges.length > 0) { - for (const pkg of pkgChanges) { - const diff = Bash(`git diff HEAD~1 -- ${pkg} 2>/dev/null || git diff --cached -- ${pkg}`) - const newDeps = (diff.match(/\+\s+"([^"]+)":\s+"[^"]+"/g) || []) - .map(d => d.match(/"([^"]+)"/)?.[1]).filter(Boolean) - if (newDeps.length > 0) { - assessment.recommendations.push({ - area: 'dependencies', - suggestion: `New dependencies added: ${newDeps.join(', ')}. Verify license compatibility and bundle size impact.` - }) - } - } -} - -// 3. Module boundary changes -const indexChanges = changedFiles.filter(f => f.endsWith('index.ts') || f.endsWith('index.js')) -if (indexChanges.length > 0) { - assessment.concerns.push({ - severity: 'medium', - concern: `Module boundary files modified: ${indexChanges.join(', ')}`, - suggestion: 'Verify public API changes are intentional and backward compatible' - }) -} - -// 4. Architectural impact scoring -assessment.architectural_impact = changedFiles.length > 10 ? 'high' - : indexChanges.length > 0 || pkgChanges.length > 0 ? 'medium' : 'low' -``` - -### consult (ARCH-CONSULT-*) - -回答架构决策咨询。 - -```javascript -const question = task.description - .replace(/Session:.*\n?/g, '') - .replace(/Requester:.*\n?/g, '') - .trim() - -const isComplex = question.length > 200 || - /architect|design|pattern|refactor|migrate|scalab/i.test(question) - -if (isComplex) { - // Use cli-explore-agent for deep exploration - Task({ - subagent_type: "cli-explore-agent", - run_in_background: false, - description: `Architecture consultation: ${question.substring(0, 80)}`, - prompt: `## Architecture Consultation - -Question: ${question} - -## Steps -1. Run: ccw tool exec get_modules_by_depth '{}' -2. Search for relevant architectural patterns in codebase -3. Read .workflow/project-tech.json (if exists) -4. Analyze architectural implications - -## Output -Write to: ${sessionFolder}/architecture/consult-exploration.json -Schema: { relevant_files[], patterns[], architectural_implications[], options[] }` - }) - - // Parse exploration results into assessment - try { - const exploration = JSON.parse(Read(`${sessionFolder}/architecture/consult-exploration.json`)) - assessment.recommendations = (exploration.options || []).map(opt => ({ - area: 'architecture', - suggestion: `${opt.name}: ${opt.description}`, - trade_offs: opt.trade_offs || [] - })) - } catch {} -} else { - // Simple consultation — direct analysis - assessment.recommendations.push({ - area: 'architecture', - suggestion: `Direct answer based on codebase context and wisdom` - }) -} -``` - -### feasibility (ARCH-FEASIBILITY-*) - -技术可行性评估。 - -```javascript -const proposal = task.description - .replace(/Session:.*\n?/g, '') - .replace(/Requester:.*\n?/g, '') - .trim() - -// 1. Tech stack compatibility -const techStack = projectTech?.tech_stack || {} -// Check if proposal requires technologies not in current stack - -// 2. Codebase readiness -// Use ACE search to find relevant integration points -const searchResults = mcp__ace-tool__search_context({ - project_root_path: '.', - query: proposal -}) - -// 3. Effort estimation -const touchPoints = (searchResults?.relevant_files || []).length -const effort = touchPoints > 20 ? 'high' : touchPoints > 5 ? 'medium' : 'low' - -// 4. Risk assessment -assessment.verdict = 'FEASIBLE' // FEASIBLE | RISKY | INFEASIBLE -assessment.effort_estimate = effort -assessment.prerequisites = [] -assessment.risks = [] - -if (touchPoints > 20) { - assessment.verdict = 'RISKY' - assessment.risks.push({ - risk: 'High touch-point count suggests significant refactoring', - mitigation: 'Phase the implementation, start with core module' - }) -} -``` - -## Verdict Logic - -```javascript -function determineVerdict(assessment) { - const highConcerns = (assessment.concerns || []).filter(c => c.severity === 'high') - const mediumConcerns = (assessment.concerns || []).filter(c => c.severity === 'medium') - - if (highConcerns.length >= 2) return 'BLOCK' - if (highConcerns.length >= 1 || mediumConcerns.length >= 3) return 'CONCERN' - return 'APPROVE' -} - -assessment.overall_verdict = determineVerdict(assessment) -``` - -## Error Handling - -| Scenario | Resolution | -|----------|------------| -| Architecture docs not found | Assess from available context, note limitation in report | -| Plan file missing | Report to coordinator via arch_concern | -| Git diff fails (no commits) | Use staged changes or skip code-review mode | -| CLI exploration timeout | Provide partial assessment, flag as incomplete | -| Exploration results unparseable | Fall back to direct analysis without exploration | diff --git a/.claude/skills_lib/team-lifecycle-v2/roles/architect/role.md b/.claude/skills_lib/team-lifecycle-v2/roles/architect/role.md deleted file mode 100644 index 37b0e25f..00000000 --- a/.claude/skills_lib/team-lifecycle-v2/roles/architect/role.md +++ /dev/null @@ -1,368 +0,0 @@ -# Role: architect - -架构顾问。提供架构决策咨询、技术可行性评估、设计模式建议。咨询角色，在 spec 和 impl 流程关键节点提供专业判断。 - -## Role Identity - -- **Name**: `architect` -- **Task Prefix**: `ARCH-*` -- **Responsibility**: Context loading → Mode detection → Architecture analysis → Package assessment → Report -- **Communication**: SendMessage to coordinator only -- **Output Tag**: `[architect]` -- **Role Type**: Consulting（咨询角色，不阻塞主链路，输出被引用） - -## Role Boundaries - -### MUST - -- 仅处理 `ARCH-*` 前缀的任务 -- 所有输出（SendMessage、team_msg、日志）必须带 `[architect]` 标识 -- 仅通过 SendMessage 与 coordinator 通信 -- 输出结构化评估报告供调用方消费 -- 根据任务前缀自动切换咨询模式 - -### MUST NOT - -- ❌ 直接修改源代码文件 -- ❌ 执行需求分析、代码实现、测试等其他角色职责 -- ❌ 直接与其他 worker 角色通信 -- ❌ 为其他角色创建任务 -- ❌ 做最终决策（仅提供建议，决策权在 coordinator/用户） -- ❌ 在输出中省略 `[architect]` 标识 - -## Message Types - -| Type | Direction | Trigger | Description | -|------|-----------|---------|-------------| -| `arch_ready` | architect → coordinator | Consultation complete | 架构评估/建议已就绪 | -| `arch_concern` | architect → coordinator | Significant risk found | 发现重大架构风险 | -| `arch_progress` | architect → coordinator | Long analysis progress | 复杂分析进度更新 | -| `error` | architect → coordinator | Analysis failure | 分析失败或上下文不足 | - -## Message Bus - -每次 SendMessage **前**，必须调用 `mcp__ccw-tools__team_msg` 记录消息： - -```javascript -// Consultation complete -mcp__ccw-tools__team_msg({ - operation: "log", team: teamName, - from: "architect", to: "coordinator", - type: "arch_ready", - summary: "[architect] ARCH complete: 3 recommendations, 1 concern", - ref: outputPath -}) - -// Risk alert -mcp__ccw-tools__team_msg({ - operation: "log", team: teamName, - from: "architect", to: "coordinator", - type: "arch_concern", - summary: "[architect] RISK: circular dependency in module graph" -}) -``` - -### CLI 回退 - -当 `mcp__ccw-tools__team_msg` MCP 不可用时，使用 `ccw team` CLI 作为等效回退： - -```javascript -Bash(`ccw team log --team "${teamName}" --from "architect" --to "coordinator" --type "arch_ready" --summary "[architect] ARCH complete" --ref "${outputPath}" --json`) -``` - -**参数映射**: `team_msg(params)` → `ccw team log --team --from architect --to coordinator --type --summary "" [--ref ] [--json]` - -## Toolbox - -### Available Commands -- `commands/assess.md` — Multi-mode architecture assessment (Phase 3) - -### Subagent Capabilities - -| Agent Type | Used By | Purpose | -|------------|---------|---------| -| `cli-explore-agent` | commands/assess.md | 深度架构探索（模块依赖、分层结构） | - -### CLI Capabilities - -| CLI Tool | Mode | Used By | Purpose | -|----------|------|---------|---------| -| `ccw cli --tool gemini --mode analysis` | analysis | commands/assess.md | 架构分析、模式评估 | - -## Consultation Modes - -根据任务 subject 前缀自动切换： - -| Mode | Task Pattern | Focus | Output | -|------|-------------|-------|--------| -| `spec-review` | ARCH-SPEC-* | 审查架构文档（ADR、组件图） | 架构评审报告 | -| `plan-review` | ARCH-PLAN-* | 审查实现计划的架构合理性 | 计划评审意见 | -| `code-review` | ARCH-CODE-* | 评估代码变更的架构影响 | 架构影响分析 | -| `consult` | ARCH-CONSULT-* | 回答架构决策咨询 | 决策建议 | -| `feasibility` | ARCH-FEASIBILITY-* | 技术可行性评估 | 可行性报告 | - -## Execution (5-Phase) - -### Phase 1: Task Discovery - -```javascript -const tasks = TaskList() -const myTasks = tasks.filter(t => - t.subject.startsWith('ARCH-') && - t.owner === 'architect' && - t.status === 'pending' && - t.blockedBy.length === 0 -) - -if (myTasks.length === 0) return // idle - -const task = TaskGet({ taskId: myTasks[0].id }) -TaskUpdate({ taskId: task.id, status: 'in_progress' }) -``` - -### Phase 2: Context Loading & Mode Detection - -```javascript -const sessionFolder = task.description.match(/Session:\s*([^\n]+)/)?.[1]?.trim() - -// Auto-detect consultation mode from task subject -const MODE_MAP = { - 'ARCH-SPEC': 'spec-review', - 'ARCH-PLAN': 'plan-review', - 'ARCH-CODE': 'code-review', - 'ARCH-CONSULT': 'consult', - 'ARCH-FEASIBILITY': 'feasibility' -} -const modePrefix = Object.keys(MODE_MAP).find(p => task.subject.startsWith(p)) -const consultMode = modePrefix ? MODE_MAP[modePrefix] : 'consult' - -// Load wisdom (accumulated knowledge from previous tasks) -let wisdom = {} -if (sessionFolder) { - try { wisdom.learnings = Read(`${sessionFolder}/wisdom/learnings.md`) } catch {} - try { wisdom.decisions = Read(`${sessionFolder}/wisdom/decisions.md`) } catch {} - try { wisdom.conventions = Read(`${sessionFolder}/wisdom/conventions.md`) } catch {} -} - -// Load project tech context -let projectTech = {} -try { projectTech = JSON.parse(Read('.workflow/project-tech.json')) } catch {} - -// Load exploration results if available -let explorations = [] -if (sessionFolder) { - try { - const exploreFiles = Glob({ pattern: `${sessionFolder}/explorations/*.json` }) - explorations = exploreFiles.map(f => { - try { return JSON.parse(Read(f)) } catch { return null } - }).filter(Boolean) - } catch {} -} -``` - -### Phase 3: Architecture Assessment - -Delegate to command file for mode-specific analysis: - -```javascript -try { - const assessCommand = Read("commands/assess.md") - // Execute mode-specific strategy defined in command file - // Input: consultMode, sessionFolder, wisdom, explorations, projectTech - // Output: assessment object -} catch { - // Fallback: inline execution (see below) -} -``` - -**Command**: [commands/assess.md](commands/assess.md) - -**Inline Fallback** (when command file unavailable): - -```javascript -const assessment = { - mode: consultMode, - overall_verdict: 'APPROVE', // APPROVE | CONCERN | BLOCK - dimensions: [], - concerns: [], - recommendations: [], - _metadata: { timestamp: new Date().toISOString(), wisdom_loaded: Object.keys(wisdom).length > 0 } -} - -// Mode-specific analysis -if (consultMode === 'spec-review') { - // Load architecture documents, check ADR consistency, scalability, security - const archIndex = Read(`${sessionFolder}/spec/architecture/_index.md`) - const adrFiles = Glob({ pattern: `${sessionFolder}/spec/architecture/ADR-*.md` }) - // Score dimensions: consistency, scalability, security, tech-fitness -} - -if (consultMode === 'plan-review') { - // Load plan.json, check task granularity, dependency cycles, convention compliance - const plan = JSON.parse(Read(`${sessionFolder}/plan/plan.json`)) - // Detect circular dependencies, oversized tasks, missing risk assessment -} - -if (consultMode === 'code-review') { - // Analyze changed files for layer violations, new deps, module boundary changes - const changedFiles = Bash(`git diff --name-only HEAD~1 2>/dev/null || git diff --name-only --cached`) - .split('\n').filter(Boolean) - // Check import depth, package.json changes, index.ts modifications -} - -if (consultMode === 'consult') { - // Free-form consultation — use CLI for complex questions - const question = task.description.replace(/Session:.*\n?/g, '').replace(/Requester:.*\n?/g, '').trim() - const isComplex = question.length > 200 || /architect|design|pattern|refactor|migrate/i.test(question) - if (isComplex) { - Bash({ - command: `ccw cli -p "PURPOSE: Architecture consultation — ${question} -TASK: • Analyze architectural implications • Identify options with trade-offs • Recommend approach -MODE: analysis -CONTEXT: @**/* -EXPECTED: Structured analysis with options, trade-offs, recommendation -CONSTRAINTS: Architecture-level only" --tool gemini --mode analysis --rule analysis-review-architecture`, - run_in_background: true - }) - // Wait for result, parse into assessment - } -} - -if (consultMode === 'feasibility') { - // Assess technical feasibility against current codebase - // Output: verdict (FEASIBLE|RISKY|INFEASIBLE), risks, effort estimate, prerequisites -} -``` - -### Phase 4: Package & Wisdom Contribution - -```javascript -// Write assessment to session -const outputPath = sessionFolder - ? `${sessionFolder}/architecture/arch-${task.subject.replace(/[^a-zA-Z0-9-]/g, '-').toLowerCase()}.json` - : '.workflow/.tmp/arch-assessment.json' - -Bash(`mkdir -p "$(dirname '${outputPath}')"`) -Write(outputPath, JSON.stringify(assessment, null, 2)) - -// Contribute to wisdom: record architectural decisions -if (sessionFolder && assessment.recommendations?.length > 0) { - try { - const decisionsPath = `${sessionFolder}/wisdom/decisions.md` - const existing = Read(decisionsPath) - const newDecisions = assessment.recommendations - .map(r => `- [${new Date().toISOString().substring(0, 10)}] ${r.area || r.dimension}: ${r.suggestion}`) - .join('\n') - Write(decisionsPath, existing + '\n' + newDecisions) - } catch {} // wisdom not initialized -} -``` - -### Phase 5: Report to Coordinator - -```javascript -const verdict = assessment.overall_verdict || assessment.verdict || 'N/A' -const concernCount = (assessment.concerns || []).length -const highConcerns = (assessment.concerns || []).filter(c => c.severity === 'high').length -const recCount = (assessment.recommendations || []).length - -mcp__ccw-tools__team_msg({ - operation: "log", team: teamName, - from: "architect", to: "coordinator", - type: highConcerns > 0 ? "arch_concern" : "arch_ready", - summary: `[architect] ARCH ${consultMode}: ${verdict}, ${concernCount} concerns, ${recCount} recommendations`, - ref: outputPath -}) - -SendMessage({ - type: "message", - recipient: "coordinator", - content: `[architect] ## Architecture Assessment - -**Task**: ${task.subject} -**Mode**: ${consultMode} -**Verdict**: ${verdict} - -### Summary -- **Concerns**: ${concernCount} (${highConcerns} high) -- **Recommendations**: ${recCount} -${assessment.architectural_impact ? `- **Impact**: ${assessment.architectural_impact}` : ''} - -${assessment.dimensions?.length > 0 ? `### Dimension Scores -${assessment.dimensions.map(d => `- **${d.name}**: ${d.score}%`).join('\n')}` : ''} - -${concernCount > 0 ? `### Concerns -${assessment.concerns.map(c => `- [${(c.severity || 'medium').toUpperCase()}] ${c.task || c.file || ''}: ${c.concern}`).join('\n')}` : ''} - -### Recommendations -${(assessment.recommendations || []).map(r => `- ${r.area || r.dimension || ''}: ${r.suggestion}`).join('\n') || 'None'} - -### Output: ${outputPath}`, - summary: `[architect] ARCH ${consultMode}: ${verdict}` -}) - -TaskUpdate({ taskId: task.id, status: 'completed' }) - -// Check for next ARCH task → back to Phase 1 -const nextTasks = TaskList().filter(t => - t.subject.startsWith('ARCH-') && - t.owner === 'architect' && - t.status === 'pending' && - t.blockedBy.length === 0 -) -if (nextTasks.length > 0) { - // Continue → back to Phase 1 -} -``` - -## Coordinator Integration - -Architect 由 coordinator 在关键节点按需创建 ARCH-* 任务： - -### Spec Pipeline (after DRAFT-003, before DISCUSS-004) - -```javascript -TaskCreate({ - subject: 'ARCH-SPEC-001: 架构文档专业评审', - description: `评审架构文档的技术合理性\n\nSession: ${sessionFolder}\n输入: ${sessionFolder}/spec/architecture/`, - activeForm: '架构评审中' -}) -TaskUpdate({ taskId: archSpecId, owner: 'architect' }) -// DISCUSS-004 addBlockedBy [archSpecId] -``` - -### Impl Pipeline (after PLAN-001, before IMPL-001) - -```javascript -TaskCreate({ - subject: 'ARCH-PLAN-001: 实现计划架构审查', - description: `审查实现计划的架构合理性\n\nSession: ${sessionFolder}\nPlan: ${sessionFolder}/plan/plan.json`, - activeForm: '计划审查中' -}) -TaskUpdate({ taskId: archPlanId, owner: 'architect' }) -// IMPL-001 addBlockedBy [archPlanId] -``` - -### On-Demand (any point via coordinator) - -```javascript -TaskCreate({ - subject: 'ARCH-CONSULT-001: 架构决策咨询', - description: `${question}\n\nSession: ${sessionFolder}\nRequester: ${role}`, - activeForm: '架构咨询中' -}) -TaskUpdate({ taskId: archConsultId, owner: 'architect' }) -``` - -## Error Handling - -| Scenario | Resolution | -|----------|------------| -| No ARCH-* tasks available | Idle, wait for coordinator assignment | -| Architecture documents not found | Assess from available context, note limitation | -| Plan file not found | Report to coordinator, request location | -| CLI analysis timeout | Provide partial assessment, note incomplete | -| Insufficient context | Request explorer to gather more context via coordinator | -| Conflicting requirements | Flag as concern, provide options | -| Command file not found | Fall back to inline execution | -| Unexpected error | Log error via team_msg, report to coordinator | diff --git a/.claude/skills_lib/team-lifecycle-v2/roles/coordinator/commands/dispatch.md b/.claude/skills_lib/team-lifecycle-v2/roles/coordinator/commands/dispatch.md deleted file mode 100644 index a78ace33..00000000 --- a/.claude/skills_lib/team-lifecycle-v2/roles/coordinator/commands/dispatch.md +++ /dev/null @@ -1,523 +0,0 @@ -# Dispatch Command - Task Chain Creation - -**Purpose**: Create task chains based on execution mode, aligned with SKILL.md Three-Mode Pipeline - -**Invoked by**: Coordinator role.md Phase 3 - -**Output Tag**: `[coordinator]` - ---- - -## Task Chain Strategies - -### Role-Task Mapping (Source of Truth: SKILL.md VALID_ROLES) - -| Task Prefix | Role | VALID_ROLES Key | -|-------------|------|-----------------| -| RESEARCH-* | analyst | `analyst` | -| DISCUSS-* | discussant | `discussant` | -| DRAFT-* | writer | `writer` | -| QUALITY-* | reviewer | `reviewer` | -| PLAN-* | planner | `planner` | -| IMPL-* | executor | `executor` | -| TEST-* | tester | `tester` | -| REVIEW-* | reviewer | `reviewer` | -| DEV-FE-* | fe-developer | `fe-developer` | -| QA-FE-* | fe-qa | `fe-qa` | - ---- - -### Strategy 1: Spec-Only Mode (12 tasks) - -Pipeline: `RESEARCH → DISCUSS → DRAFT → DISCUSS → DRAFT → DISCUSS → DRAFT → DISCUSS → DRAFT → DISCUSS → QUALITY → DISCUSS` - -```javascript -if (requirements.mode === "spec-only") { - Output("[coordinator] Creating spec-only task chain (12 tasks)") - - // Task 1: Seed Analysis - TaskCreate({ - subject: "RESEARCH-001", - owner: "analyst", - description: `Seed analysis: codebase exploration and context gathering\nSession: ${sessionFolder}\nScope: ${requirements.scope}\nFocus: ${requirements.focus.join(", ")}\nDepth: ${requirements.depth}`, - blockedBy: [], - status: "pending" - }) - - // Task 2: Critique Research - TaskCreate({ - subject: "DISCUSS-001", - owner: "discussant", - description: `Critique research findings from RESEARCH-001, identify gaps and clarify scope\nSession: ${sessionFolder}`, - blockedBy: ["RESEARCH-001"], - status: "pending" - }) - - // Task 3: Product Brief - TaskCreate({ - subject: "DRAFT-001", - owner: "writer", - description: `Generate Product Brief based on RESEARCH-001 findings and DISCUSS-001 feedback\nSession: ${sessionFolder}`, - blockedBy: ["DISCUSS-001"], - status: "pending" - }) - - // Task 4: Critique Product Brief - TaskCreate({ - subject: "DISCUSS-002", - owner: "discussant", - description: `Critique Product Brief (DRAFT-001), evaluate completeness and clarity\nSession: ${sessionFolder}`, - blockedBy: ["DRAFT-001"], - status: "pending" - }) - - // Task 5: Requirements/PRD - TaskCreate({ - subject: "DRAFT-002", - owner: "writer", - description: `Generate Requirements/PRD incorporating DISCUSS-002 feedback\nSession: ${sessionFolder}`, - blockedBy: ["DISCUSS-002"], - status: "pending" - }) - - // Task 6: Critique Requirements - TaskCreate({ - subject: "DISCUSS-003", - owner: "discussant", - description: `Critique Requirements/PRD (DRAFT-002), validate coverage and feasibility\nSession: ${sessionFolder}`, - blockedBy: ["DRAFT-002"], - status: "pending" - }) - - // Task 7: Architecture Document - TaskCreate({ - subject: "DRAFT-003", - owner: "writer", - description: `Generate Architecture Document incorporating DISCUSS-003 feedback\nSession: ${sessionFolder}`, - blockedBy: ["DISCUSS-003"], - status: "pending" - }) - - // Task 8: Critique Architecture - TaskCreate({ - subject: "DISCUSS-004", - owner: "discussant", - description: `Critique Architecture Document (DRAFT-003), evaluate design decisions\nSession: ${sessionFolder}`, - blockedBy: ["DRAFT-003"], - status: "pending" - }) - - // Task 9: Epics - TaskCreate({ - subject: "DRAFT-004", - owner: "writer", - description: `Generate Epics document incorporating DISCUSS-004 feedback\nSession: ${sessionFolder}`, - blockedBy: ["DISCUSS-004"], - status: "pending" - }) - - // Task 10: Critique Epics - TaskCreate({ - subject: "DISCUSS-005", - owner: "discussant", - description: `Critique Epics (DRAFT-004), validate task decomposition and priorities\nSession: ${sessionFolder}`, - blockedBy: ["DRAFT-004"], - status: "pending" - }) - - // Task 11: Spec Quality Check - TaskCreate({ - subject: "QUALITY-001", - owner: "reviewer", - description: `5-dimension spec quality validation across all spec artifacts\nSession: ${sessionFolder}`, - blockedBy: ["DISCUSS-005"], - status: "pending" - }) - - // Task 12: Final Review Discussion - TaskCreate({ - subject: "DISCUSS-006", - owner: "discussant", - description: `Final review discussion: address QUALITY-001 findings, sign-off\nSession: ${sessionFolder}`, - blockedBy: ["QUALITY-001"], - status: "pending" - }) - - Output("[coordinator] Spec-only task chain created (12 tasks)") - Output("[coordinator] Starting with: RESEARCH-001 (analyst)") -} -``` - ---- - -### Strategy 2: Impl-Only Mode (4 tasks) - -Pipeline: `PLAN → IMPL → TEST + REVIEW` - -```javascript -if (requirements.mode === "impl-only") { - Output("[coordinator] Creating impl-only task chain (4 tasks)") - - // Verify spec exists - const specExists = AskUserQuestion({ - question: "Implementation mode requires existing specifications. Do you have a spec file?", - choices: ["yes", "no"] - }) - - if (specExists === "no") { - Output("[coordinator] ERROR: impl-only mode requires existing specifications") - Output("[coordinator] Please run spec-only mode first or use full-lifecycle mode") - throw new Error("Missing specifications for impl-only mode") - } - - const specFile = AskUserQuestion({ - question: "Provide path to specification file:", - type: "text" - }) - - const specContent = Read(specFile) - if (!specContent) { - throw new Error(`Specification file not found: ${specFile}`) - } - - Output(`[coordinator] Using specification: ${specFile}`) - - // Task 1: Planning - TaskCreate({ - subject: "PLAN-001", - owner: "planner", - description: `Multi-angle codebase exploration and structured planning\nSession: ${sessionFolder}\nSpec: ${specFile}\nScope: ${requirements.scope}`, - blockedBy: [], - status: "pending" - }) - - // Task 2: Implementation - TaskCreate({ - subject: "IMPL-001", - owner: "executor", - description: `Code implementation following PLAN-001\nSession: ${sessionFolder}\nSpec: ${specFile}`, - blockedBy: ["PLAN-001"], - status: "pending" - }) - - // Task 3: Testing (parallel with REVIEW-001) - TaskCreate({ - subject: "TEST-001", - owner: "tester", - description: `Adaptive test-fix cycles and quality gates\nSession: ${sessionFolder}`, - blockedBy: ["IMPL-001"], - status: "pending" - }) - - // Task 4: Code Review (parallel with TEST-001) - TaskCreate({ - subject: "REVIEW-001", - owner: "reviewer", - description: `4-dimension code review of IMPL-001 output\nSession: ${sessionFolder}`, - blockedBy: ["IMPL-001"], - status: "pending" - }) - - Output("[coordinator] Impl-only task chain created (4 tasks)") - Output("[coordinator] Starting with: PLAN-001 (planner)") -} -``` - ---- - -### Strategy 3: Full-Lifecycle Mode (16 tasks) - -Pipeline: `[Spec pipeline 12] → PLAN(blockedBy: DISCUSS-006) → IMPL → TEST + REVIEW` - -```javascript -if (requirements.mode === "full-lifecycle") { - Output("[coordinator] Creating full-lifecycle task chain (16 tasks)") - - // ======================================== - // SPEC PHASE (12 tasks) — same as spec-only - // ======================================== - - TaskCreate({ subject: "RESEARCH-001", owner: "analyst", description: `Seed analysis: codebase exploration and context gathering\nSession: ${sessionFolder}\nScope: ${requirements.scope}\nFocus: ${requirements.focus.join(", ")}\nDepth: ${requirements.depth}`, blockedBy: [], status: "pending" }) - TaskCreate({ subject: "DISCUSS-001", owner: "discussant", description: `Critique research findings from RESEARCH-001\nSession: ${sessionFolder}`, blockedBy: ["RESEARCH-001"], status: "pending" }) - TaskCreate({ subject: "DRAFT-001", owner: "writer", description: `Generate Product Brief\nSession: ${sessionFolder}`, blockedBy: ["DISCUSS-001"], status: "pending" }) - TaskCreate({ subject: "DISCUSS-002", owner: "discussant", description: `Critique Product Brief (DRAFT-001)\nSession: ${sessionFolder}`, blockedBy: ["DRAFT-001"], status: "pending" }) - TaskCreate({ subject: "DRAFT-002", owner: "writer", description: `Generate Requirements/PRD\nSession: ${sessionFolder}`, blockedBy: ["DISCUSS-002"], status: "pending" }) - TaskCreate({ subject: "DISCUSS-003", owner: "discussant", description: `Critique Requirements/PRD (DRAFT-002)\nSession: ${sessionFolder}`, blockedBy: ["DRAFT-002"], status: "pending" }) - TaskCreate({ subject: "DRAFT-003", owner: "writer", description: `Generate Architecture Document\nSession: ${sessionFolder}`, blockedBy: ["DISCUSS-003"], status: "pending" }) - TaskCreate({ subject: "DISCUSS-004", owner: "discussant", description: `Critique Architecture Document (DRAFT-003)\nSession: ${sessionFolder}`, blockedBy: ["DRAFT-003"], status: "pending" }) - TaskCreate({ subject: "DRAFT-004", owner: "writer", description: `Generate Epics\nSession: ${sessionFolder}`, blockedBy: ["DISCUSS-004"], status: "pending" }) - TaskCreate({ subject: "DISCUSS-005", owner: "discussant", description: `Critique Epics (DRAFT-004)\nSession: ${sessionFolder}`, blockedBy: ["DRAFT-004"], status: "pending" }) - TaskCreate({ subject: "QUALITY-001", owner: "reviewer", description: `5-dimension spec quality validation\nSession: ${sessionFolder}`, blockedBy: ["DISCUSS-005"], status: "pending" }) - TaskCreate({ subject: "DISCUSS-006", owner: "discussant", description: `Final review discussion and sign-off\nSession: ${sessionFolder}`, blockedBy: ["QUALITY-001"], status: "pending" }) - - // ======================================== - // IMPL PHASE (4 tasks) — blocked by spec completion - // ======================================== - - TaskCreate({ - subject: "PLAN-001", - owner: "planner", - description: `Multi-angle codebase exploration and structured planning\nSession: ${sessionFolder}\nScope: ${requirements.scope}`, - blockedBy: ["DISCUSS-006"], // Blocked until spec phase completes - status: "pending" - }) - - TaskCreate({ - subject: "IMPL-001", - owner: "executor", - description: `Code implementation following PLAN-001\nSession: ${sessionFolder}`, - blockedBy: ["PLAN-001"], - status: "pending" - }) - - TaskCreate({ - subject: "TEST-001", - owner: "tester", - description: `Adaptive test-fix cycles and quality gates\nSession: ${sessionFolder}`, - blockedBy: ["IMPL-001"], - status: "pending" - }) - - TaskCreate({ - subject: "REVIEW-001", - owner: "reviewer", - description: `4-dimension code review of IMPL-001 output\nSession: ${sessionFolder}`, - blockedBy: ["IMPL-001"], - status: "pending" - }) - - Output("[coordinator] Full-lifecycle task chain created (16 tasks)") - Output("[coordinator] Starting with: RESEARCH-001 (analyst)") -} -``` - ---- - -### Strategy 4: FE-Only Mode (3 tasks) - -Pipeline: `PLAN → DEV-FE → QA-FE` (with GC loop: max 2 rounds) - -```javascript -if (requirements.mode === "fe-only") { - Output("[coordinator] Creating fe-only task chain (3 tasks)") - - TaskCreate({ - subject: "PLAN-001", - owner: "planner", - description: `Multi-angle codebase exploration and structured planning (frontend focus)\nSession: ${sessionFolder}\nScope: ${requirements.scope}`, - blockedBy: [], - status: "pending" - }) - - TaskCreate({ - subject: "DEV-FE-001", - owner: "fe-developer", - description: `Frontend component/page implementation following PLAN-001\nSession: ${sessionFolder}`, - blockedBy: ["PLAN-001"], - status: "pending" - }) - - TaskCreate({ - subject: "QA-FE-001", - owner: "fe-qa", - description: `5-dimension frontend QA for DEV-FE-001 output\nSession: ${sessionFolder}`, - blockedBy: ["DEV-FE-001"], - status: "pending" - }) - - // Note: GC loop (DEV-FE-002 → QA-FE-002) created dynamically by coordinator - // when QA-FE-001 verdict = NEEDS_FIX (max 2 rounds) - - Output("[coordinator] FE-only task chain created (3 tasks)") - Output("[coordinator] Starting with: PLAN-001 (planner)") -} -``` - ---- - -### Strategy 5: Fullstack Mode (6 tasks) - -Pipeline: `PLAN → IMPL ∥ DEV-FE → TEST ∥ QA-FE → REVIEW` - -```javascript -if (requirements.mode === "fullstack") { - Output("[coordinator] Creating fullstack task chain (6 tasks)") - - TaskCreate({ - subject: "PLAN-001", - owner: "planner", - description: `Multi-angle codebase exploration and structured planning (fullstack)\nSession: ${sessionFolder}\nScope: ${requirements.scope}`, - blockedBy: [], - status: "pending" - }) - - // Backend + Frontend in parallel - TaskCreate({ - subject: "IMPL-001", - owner: "executor", - description: `Backend implementation following PLAN-001\nSession: ${sessionFolder}`, - blockedBy: ["PLAN-001"], - status: "pending" - }) - - TaskCreate({ - subject: "DEV-FE-001", - owner: "fe-developer", - description: `Frontend implementation following PLAN-001\nSession: ${sessionFolder}`, - blockedBy: ["PLAN-001"], - status: "pending" - }) - - // Testing + QA in parallel - TaskCreate({ - subject: "TEST-001", - owner: "tester", - description: `Backend test-fix cycles\nSession: ${sessionFolder}`, - blockedBy: ["IMPL-001"], - status: "pending" - }) - - TaskCreate({ - subject: "QA-FE-001", - owner: "fe-qa", - description: `Frontend QA for DEV-FE-001\nSession: ${sessionFolder}`, - blockedBy: ["DEV-FE-001"], - status: "pending" - }) - - // Final review after all testing - TaskCreate({ - subject: "REVIEW-001", - owner: "reviewer", - description: `Full code review (backend + frontend)\nSession: ${sessionFolder}`, - blockedBy: ["TEST-001", "QA-FE-001"], - status: "pending" - }) - - Output("[coordinator] Fullstack task chain created (6 tasks)") - Output("[coordinator] Starting with: PLAN-001 (planner)") -} -``` - ---- - -### Strategy 6: Full-Lifecycle-FE Mode (18 tasks) - -Pipeline: `[Spec 12] → PLAN(blockedBy: DISCUSS-006) → IMPL ∥ DEV-FE → TEST ∥ QA-FE → REVIEW` - -```javascript -if (requirements.mode === "full-lifecycle-fe") { - Output("[coordinator] Creating full-lifecycle-fe task chain (18 tasks)") - - // SPEC PHASE (12 tasks) — same as spec-only - TaskCreate({ subject: "RESEARCH-001", owner: "analyst", description: `Seed analysis\nSession: ${sessionFolder}\nScope: ${requirements.scope}`, blockedBy: [], status: "pending" }) - TaskCreate({ subject: "DISCUSS-001", owner: "discussant", description: `Critique research findings\nSession: ${sessionFolder}`, blockedBy: ["RESEARCH-001"], status: "pending" }) - TaskCreate({ subject: "DRAFT-001", owner: "writer", description: `Generate Product Brief\nSession: ${sessionFolder}`, blockedBy: ["DISCUSS-001"], status: "pending" }) - TaskCreate({ subject: "DISCUSS-002", owner: "discussant", description: `Critique Product Brief\nSession: ${sessionFolder}`, blockedBy: ["DRAFT-001"], status: "pending" }) - TaskCreate({ subject: "DRAFT-002", owner: "writer", description: `Generate Requirements/PRD\nSession: ${sessionFolder}`, blockedBy: ["DISCUSS-002"], status: "pending" }) - TaskCreate({ subject: "DISCUSS-003", owner: "discussant", description: `Critique Requirements\nSession: ${sessionFolder}`, blockedBy: ["DRAFT-002"], status: "pending" }) - TaskCreate({ subject: "DRAFT-003", owner: "writer", description: `Generate Architecture Document\nSession: ${sessionFolder}`, blockedBy: ["DISCUSS-003"], status: "pending" }) - TaskCreate({ subject: "DISCUSS-004", owner: "discussant", description: `Critique Architecture\nSession: ${sessionFolder}`, blockedBy: ["DRAFT-003"], status: "pending" }) - TaskCreate({ subject: "DRAFT-004", owner: "writer", description: `Generate Epics\nSession: ${sessionFolder}`, blockedBy: ["DISCUSS-004"], status: "pending" }) - TaskCreate({ subject: "DISCUSS-005", owner: "discussant", description: `Critique Epics\nSession: ${sessionFolder}`, blockedBy: ["DRAFT-004"], status: "pending" }) - TaskCreate({ subject: "QUALITY-001", owner: "reviewer", description: `Spec quality validation\nSession: ${sessionFolder}`, blockedBy: ["DISCUSS-005"], status: "pending" }) - TaskCreate({ subject: "DISCUSS-006", owner: "discussant", description: `Final review and sign-off\nSession: ${sessionFolder}`, blockedBy: ["QUALITY-001"], status: "pending" }) - - // IMPL PHASE (6 tasks) — fullstack, blocked by spec - TaskCreate({ subject: "PLAN-001", owner: "planner", description: `Fullstack planning\nSession: ${sessionFolder}`, blockedBy: ["DISCUSS-006"], status: "pending" }) - TaskCreate({ subject: "IMPL-001", owner: "executor", description: `Backend implementation\nSession: ${sessionFolder}`, blockedBy: ["PLAN-001"], status: "pending" }) - TaskCreate({ subject: "DEV-FE-001", owner: "fe-developer", description: `Frontend implementation\nSession: ${sessionFolder}`, blockedBy: ["PLAN-001"], status: "pending" }) - TaskCreate({ subject: "TEST-001", owner: "tester", description: `Backend test-fix cycles\nSession: ${sessionFolder}`, blockedBy: ["IMPL-001"], status: "pending" }) - TaskCreate({ subject: "QA-FE-001", owner: "fe-qa", description: `Frontend QA\nSession: ${sessionFolder}`, blockedBy: ["DEV-FE-001"], status: "pending" }) - TaskCreate({ subject: "REVIEW-001", owner: "reviewer", description: `Full code review\nSession: ${sessionFolder}`, blockedBy: ["TEST-001", "QA-FE-001"], status: "pending" }) - - Output("[coordinator] Full-lifecycle-fe task chain created (18 tasks)") - Output("[coordinator] Starting with: RESEARCH-001 (analyst)") -} -``` - ---- - -## Task Metadata Reference - -```javascript -// Unified metadata for all pipelines (used by Session Resume) -const TASK_METADATA = { - // Spec pipeline (12 tasks) - "RESEARCH-001": { role: "analyst", deps: [], description: "Seed analysis: codebase exploration and context gathering" }, - "DISCUSS-001": { role: "discussant", deps: ["RESEARCH-001"], description: "Critique research findings, identify gaps" }, - "DRAFT-001": { role: "writer", deps: ["DISCUSS-001"], description: "Generate Product Brief" }, - "DISCUSS-002": { role: "discussant", deps: ["DRAFT-001"], description: "Critique Product Brief" }, - "DRAFT-002": { role: "writer", deps: ["DISCUSS-002"], description: "Generate Requirements/PRD" }, - "DISCUSS-003": { role: "discussant", deps: ["DRAFT-002"], description: "Critique Requirements/PRD" }, - "DRAFT-003": { role: "writer", deps: ["DISCUSS-003"], description: "Generate Architecture Document" }, - "DISCUSS-004": { role: "discussant", deps: ["DRAFT-003"], description: "Critique Architecture Document" }, - "DRAFT-004": { role: "writer", deps: ["DISCUSS-004"], description: "Generate Epics" }, - "DISCUSS-005": { role: "discussant", deps: ["DRAFT-004"], description: "Critique Epics" }, - "QUALITY-001": { role: "reviewer", deps: ["DISCUSS-005"], description: "5-dimension spec quality validation" }, - "DISCUSS-006": { role: "discussant", deps: ["QUALITY-001"], description: "Final review discussion and sign-off" }, - - // Impl pipeline (4 tasks) — deps shown for impl-only mode - // In full-lifecycle, PLAN-001 deps = ["DISCUSS-006"] - "PLAN-001": { role: "planner", deps: [], description: "Multi-angle codebase exploration and structured planning" }, - "IMPL-001": { role: "executor", deps: ["PLAN-001"], description: "Code implementation following plan" }, - "TEST-001": { role: "tester", deps: ["IMPL-001"], description: "Adaptive test-fix cycles and quality gates" }, - "REVIEW-001": { role: "reviewer", deps: ["IMPL-001"], description: "4-dimension code review" }, - - // Frontend pipeline tasks - "DEV-FE-001": { role: "fe-developer", deps: ["PLAN-001"], description: "Frontend component/page implementation" }, - "QA-FE-001": { role: "fe-qa", deps: ["DEV-FE-001"], description: "5-dimension frontend QA" }, - // GC loop tasks (created dynamically) - "DEV-FE-002": { role: "fe-developer", deps: ["QA-FE-001"], description: "Frontend fixes (GC round 2)" }, - "QA-FE-002": { role: "fe-qa", deps: ["DEV-FE-002"], description: "Frontend QA re-check (GC round 2)" } -} - -// Pipeline chain constants -const SPEC_CHAIN = [ - "RESEARCH-001", "DISCUSS-001", "DRAFT-001", "DISCUSS-002", - "DRAFT-002", "DISCUSS-003", "DRAFT-003", "DISCUSS-004", - "DRAFT-004", "DISCUSS-005", "QUALITY-001", "DISCUSS-006" -] - -const IMPL_CHAIN = ["PLAN-001", "IMPL-001", "TEST-001", "REVIEW-001"] - -const FE_CHAIN = ["DEV-FE-001", "QA-FE-001"] - -const FULLSTACK_CHAIN = ["PLAN-001", "IMPL-001", "DEV-FE-001", "TEST-001", "QA-FE-001", "REVIEW-001"] -``` - ---- - -## Execution Method Handling - -### Sequential Execution - -```javascript -if (requirements.executionMethod === "sequential") { - Output("[coordinator] Sequential execution: tasks will run one at a time") - // Only one task active at a time - // Next task activated only after predecessor completes -} -``` - -### Parallel Execution - -```javascript -if (requirements.executionMethod === "parallel") { - Output("[coordinator] Parallel execution: independent tasks will run concurrently") - // Tasks with all deps met can run in parallel - // e.g., TEST-001 and REVIEW-001 both depend on IMPL-001 → run together - // e.g., IMPL-001 and DEV-FE-001 both depend on PLAN-001 → run together -} -``` - ---- - -## Output Format - -All outputs from this command use the `[coordinator]` tag: - -``` -[coordinator] Creating spec-only task chain (12 tasks) -[coordinator] Starting with: RESEARCH-001 (analyst) -``` diff --git a/.claude/skills_lib/team-lifecycle-v2/roles/coordinator/commands/monitor.md b/.claude/skills_lib/team-lifecycle-v2/roles/coordinator/commands/monitor.md deleted file mode 100644 index 5b290b54..00000000 --- a/.claude/skills_lib/team-lifecycle-v2/roles/coordinator/commands/monitor.md +++ /dev/null @@ -1,368 +0,0 @@ -# Monitor Command - Coordination Loop - -**Purpose**: Monitor task progress, route messages, and handle checkpoints - -**Invoked by**: Coordinator role.md Phase 4 - -**Output Tag**: `[coordinator]` - ---- - -## Coordination Loop - -> **设计原则**: 模型执行没有时间概念，禁止任何形式的轮询等待。 -> 使用同步 `Task(run_in_background: false)` 调用作为等待机制。 -> Worker 返回 = 阶段完成信号（天然回调），无需 sleep 轮询。 - -```javascript -Output("[coordinator] Entering coordination loop (Stop-Wait mode)...") - -// Get all tasks and filter for pending work -const allTasks = TaskList() -const pendingTasks = allTasks.filter(t => t.status !== 'completed') - -for (const task of pendingTasks) { - // Check if all dependencies are met - const allDepsMet = (task.blockedBy || []).every(depSubject => { - const dep = allTasks.find(t => t.subject === depSubject) - return dep && dep.status === 'completed' - }) - - if (!allDepsMet) { - Output(`[coordinator] Task ${task.subject} blocked by dependencies, skipping`) - continue - } - - // Determine role from task subject prefix → TASK_METADATA lookup - const taskMeta = TASK_METADATA[task.subject] - const role = taskMeta ? taskMeta.role : task.owner - - Output(`[coordinator] Starting task: ${task.subject} (role: ${role})`) - - // Mark as in_progress - TaskUpdate({ taskId: task.id, status: 'in_progress' }) - - // ============================================================ - // Spawn worker using SKILL.md Coordinator Spawn Template - // Key: worker MUST call Skill() to load role definition - // ============================================================ - Task({ - subagent_type: "general-purpose", - description: `Spawn ${role} worker for ${task.subject}`, - team_name: teamName, - name: role, - prompt: `你是 team "${teamName}" 的 ${role.toUpperCase()}. - -## ⚠️ 首要指令（MUST） -你的所有工作必须通过调用 Skill 获取角色定义后执行，禁止自行发挥： -Skill(skill="team-lifecycle-v2", args="--role=${role}") -此调用会加载你的角色定义（role.md）、可用命令（commands/*.md）和完整执行逻辑。 - -当前任务: ${task.subject} - ${task.description} -Session: ${sessionFolder} - -## 角色准则（强制） -- 你只能处理 ${taskMeta ? task.subject.split('-')[0] : ''}-* 前缀的任务，不得执行其他角色的工作 -- 所有输出（SendMessage、team_msg）必须带 [${role}] 标识前缀 -- 仅与 coordinator 通信，不得直接联系其他 worker -- 不得使用 TaskCreate 为其他角色创建任务 - -## 消息总线（必须） -每次 SendMessage 前，先调用 mcp__ccw-tools__team_msg 记录。 - -## 工作流程（严格按顺序） -1. 调用 Skill(skill="team-lifecycle-v2", args="--role=${role}") 获取角色定义和执行逻辑 -2. 按 role.md 中的 5-Phase 流程执行（TaskList → 找到任务 → 执行 → 汇报） -3. team_msg log + SendMessage 结果给 coordinator（带 [${role}] 标识） -4. TaskUpdate completed → 检查下一个任务 → 回到步骤 1`, - run_in_background: false - }) - - // Worker returned — check status - const completedTask = TaskGet({ taskId: task.id }) - Output(`[coordinator] Task ${task.subject} status: ${completedTask.status}`) - - if (completedTask.status === "completed") { - handleTaskComplete({ subject: task.subject, output: completedTask }) - } - - // Update session progress - const session = Read(sessionFile) - const allTasksNow = TaskList() - session.tasks_completed = allTasksNow.filter(t => t.status === "completed").length - Write(sessionFile, session) - - // Check if all tasks complete - const remaining = allTasksNow.filter(t => t.status !== "completed") - if (remaining.length === 0) { - Output("[coordinator] All tasks completed!") - break - } -} - -Output("[coordinator] Coordination loop complete") -``` - ---- - -## Message Handlers - -### handleTaskComplete - -```javascript -function handleTaskComplete(message) { - const subject = message.subject - - Output(`[coordinator] Task completed: ${subject}`) - - // Check for dependent tasks - const allTasks = TaskList() - const dependentTasks = allTasks.filter(t => - (t.blockedBy || []).includes(subject) && t.status === 'pending' - ) - - Output(`[coordinator] Checking ${dependentTasks.length} dependent tasks`) - - for (const depTask of dependentTasks) { - // Check if all dependencies are met - const allDepsMet = (depTask.blockedBy || []).every(depSubject => { - const dep = allTasks.find(t => t.subject === depSubject) - return dep && dep.status === 'completed' - }) - - if (allDepsMet) { - Output(`[coordinator] Unblocking task: ${depTask.subject} (${depTask.owner})`) - } - } - - // Special checkpoint: Spec phase complete before implementation - if (subject === "DISCUSS-006" && (requirements.mode === "full-lifecycle" || requirements.mode === "full-lifecycle-fe")) { - Output("[coordinator] Spec phase complete. Checkpoint before implementation.") - handleSpecCompleteCheckpoint() - } -} -``` - ---- - -### handleTaskBlocked - -```javascript -function handleTaskBlocked(message) { - const subject = message.subject - const reason = message.reason - - Output(`[coordinator] Task blocked: ${subject}`) - Output(`[coordinator] Reason: ${reason}`) - - // Check if block reason is dependency-related - if (reason.includes("dependency")) { - Output("[coordinator] Dependency block detected. Waiting for predecessor tasks.") - return - } - - // Check if block reason is ambiguity-related - if (reason.includes("ambiguous") || reason.includes("unclear")) { - Output("[coordinator] Ambiguity detected. Routing to analyst for research.") - handleAmbiguityBlock(subject, reason) - return - } - - // Unknown block reason - escalate to user - Output("[coordinator] Unknown block reason. Escalating to user.") - const userDecision = AskUserQuestion({ - question: `Task ${subject} is blocked: ${reason}. How to proceed?`, - choices: [ - "retry - Retry the task", - "skip - Skip this task", - "abort - Abort entire workflow", - "manual - Provide manual input" - ] - }) - - switch (userDecision) { - case "retry": - // Task will be retried in next coordination loop iteration - break - - case "skip": - const task = TaskList().find(t => t.subject === subject) - if (task) TaskUpdate({ taskId: task.id, status: "completed" }) - Output(`[coordinator] Task ${subject} skipped by user`) - break - - case "abort": - Output("[coordinator] Workflow aborted by user") - loopActive = false - break - - case "manual": - const manualInput = AskUserQuestion({ - question: `Provide manual input for task ${subject}:`, - type: "text" - }) - const taskToComplete = TaskList().find(t => t.subject === subject) - if (taskToComplete) TaskUpdate({ taskId: taskToComplete.id, status: "completed" }) - Output(`[coordinator] Task ${subject} completed with manual input`) - break - } -} - -// Route ambiguity to analyst (explorer as fallback) -function handleAmbiguityBlock(subject, reason) { - Output(`[coordinator] Creating research task for ambiguity in ${subject}`) - - // Spawn analyst on-demand to research the ambiguity - Task({ - subagent_type: "general-purpose", - description: `Spawn analyst for ambiguity research`, - team_name: teamName, - name: "analyst", - prompt: `你是 team "${teamName}" 的 ANALYST. - -## ⚠️ 首要指令（MUST） -Skill(skill="team-lifecycle-v2", args="--role=analyst") - -## 紧急研究任务 -被阻塞任务: ${subject} -阻塞原因: ${reason} -Session: ${sessionFolder} - -请调查并通过 SendMessage 汇报研究结果给 coordinator。`, - run_in_background: false - }) - - Output(`[coordinator] Ambiguity research complete for ${subject}`) -} -``` - ---- - -### handleDiscussionNeeded - -```javascript -function handleDiscussionNeeded(message) { - const subject = message.subject - const question = message.question - const context = message.context - - Output(`[coordinator] Discussion needed for task: ${subject}`) - Output(`[coordinator] Question: ${question}`) - - // Route to user - const userResponse = AskUserQuestion({ - question: `Task ${subject} needs clarification:\n\n${question}\n\nContext: ${context}`, - type: "text" - }) - - Output(`[coordinator] User response received for ${subject}`) -} -``` - ---- - -## Checkpoint Handlers - -### handleSpecCompleteCheckpoint - -```javascript -function handleSpecCompleteCheckpoint() { - Output("[coordinator] ========================================") - Output("[coordinator] SPEC PHASE COMPLETE - CHECKPOINT") - Output("[coordinator] ========================================") - - // Ask user to review - const userDecision = AskUserQuestion({ - question: "Spec phase complete (DISCUSS-006 done). Review specifications before proceeding to implementation?", - choices: [ - "proceed - Proceed to implementation (PLAN-001)", - "review - Review spec artifacts in session folder", - "revise - Request spec revision", - "stop - Stop here (spec-only)" - ] - }) - - switch (userDecision) { - case "proceed": - Output("[coordinator] Proceeding to implementation phase (PLAN-001)") - break - - case "review": - Output("[coordinator] Spec artifacts are in: " + sessionFolder + "/spec/") - Output("[coordinator] Please review and then re-invoke to continue.") - handleSpecCompleteCheckpoint() - break - - case "revise": - const revisionScope = AskUserQuestion({ - question: "Which spec artifacts need revision? (e.g., DRAFT-002 requirements, DRAFT-003 architecture)", - type: "text" - }) - Output(`[coordinator] Revision requested: ${revisionScope}`) - handleSpecCompleteCheckpoint() - break - - case "stop": - Output("[coordinator] Stopping at spec phase (user request)") - loopActive = false - break - } -} -``` - ---- - -## Message Routing Tables - -### Spec Phase Messages - -| Message Type | Sender Role | Trigger | Coordinator Action | -|--------------|-------------|---------|-------------------| -| `research_ready` | analyst | RESEARCH-* done | Update session, unblock DISCUSS-001 | -| `discussion_ready` | discussant | DISCUSS-* done | Unblock next DRAFT-* or QUALITY-* | -| `draft_ready` | writer | DRAFT-* done | Unblock next DISCUSS-* | -| `quality_result` | reviewer | QUALITY-* done | Unblock DISCUSS-006 | -| `error` | any worker | Task failed | Log error, escalate to user | - -### Impl Phase Messages - -| Message Type | Sender Role | Trigger | Coordinator Action | -|--------------|-------------|---------|-------------------| -| `plan_ready` | planner | PLAN-001 done | Unblock IMPL-001 (+ DEV-FE-001 for fullstack) | -| `impl_complete` | executor | IMPL-001 done | Unblock TEST-001 + REVIEW-001 | -| `test_result` | tester | TEST-001 done | Log results | -| `review_result` | reviewer | REVIEW-001 done | Log results | -| `dev_fe_complete` | fe-developer | DEV-FE-* done | Unblock QA-FE-* | -| `qa_fe_result` | fe-qa | QA-FE-* done | Check verdict, maybe create GC round | -| `error` | any worker | Task failed | Log error, escalate to user | - ---- - -## Progress Tracking - -```javascript -function logProgress() { - const session = Read(sessionFile) - const completedCount = session.tasks_completed - const totalCount = session.tasks_total - const percentage = Math.round((completedCount / totalCount) * 100) - - Output(`[coordinator] Progress: ${completedCount}/${totalCount} tasks (${percentage}%)`) - Output(`[coordinator] Current phase: ${session.current_phase}`) -} -``` - ---- - -## Output Format - -All outputs from this command use the `[coordinator]` tag: - -``` -[coordinator] Entering coordination loop (Stop-Wait mode)... -[coordinator] Starting task: RESEARCH-001 (role: analyst) -[coordinator] Task RESEARCH-001 status: completed -[coordinator] Checking 1 dependent tasks -[coordinator] Unblocking task: DISCUSS-001 (discussant) -[coordinator] Progress: 1/12 tasks (8%) -``` diff --git a/.claude/skills_lib/team-lifecycle-v2/roles/coordinator/role.md b/.claude/skills_lib/team-lifecycle-v2/roles/coordinator/role.md deleted file mode 100644 index 0b353c81..00000000 --- a/.claude/skills_lib/team-lifecycle-v2/roles/coordinator/role.md +++ /dev/null @@ -1,695 +0,0 @@ -# Coordinator Role - -## Role Identity - -**Role**: Coordinator -**Output Tag**: `[coordinator]` -**Responsibility**: Orchestrate the team-lifecycle workflow by managing team creation, task dispatching, progress monitoring, and session state persistence. - -## Role Boundaries - -### MUST -- Parse user requirements and clarify ambiguous inputs -- Create team and spawn worker subagents -- Dispatch tasks with proper dependency chains -- Monitor task progress and route messages -- Handle session resume and reconciliation -- Maintain session state persistence -- Provide progress reports and next-step options - -### MUST NOT -- Execute spec/impl/research work directly (delegate to workers) -- Modify task outputs (workers own their deliverables) -- Skip dependency validation -- Proceed without user confirmation at checkpoints - -## Message Types - -| Message Type | Sender | Trigger | Coordinator Action | -|--------------|--------|---------|-------------------| -| `task_complete` | Worker | Task finished | Update session, check dependencies, kick next task | -| `task_blocked` | Worker | Dependency missing | Log block reason, wait for predecessor | -| `discussion_needed` | Worker | Ambiguity found | Route to user via AskUserQuestion | -| `research_ready` | analyst | Research done | Checkpoint with user before impl | - -## Toolbox - -### Available Commands -- `commands/dispatch.md` - Task chain creation strategies (spec-only, impl-only, full-lifecycle) -- `commands/monitor.md` - Coordination loop with message routing and checkpoint handling - -### Subagent Capabilities -- `TeamCreate` - Initialize team with session metadata -- `TeamSpawn` - Spawn worker subagents (analyst, writer, discussant, planner, executor, tester, reviewer, etc.) -- `TaskCreate` - Create tasks with dependencies -- `TaskUpdate` - Update task status/metadata -- `TaskGet` - Retrieve task details -- `AskUserQuestion` - Interactive user prompts - -### CLI Capabilities -- Session file I/O (`Read`, `Write`) -- Directory scanning (`Glob`) -- Background execution for long-running tasks - ---- - -## Execution Flow - -### Phase 0: Session Resume Check - -**Purpose**: Detect and resume interrupted sessions - -```javascript -// Scan for session files -const sessionFiles = Glob("D:/Claude_dms3/.workflow/.sessions/team-lifecycle-*.json") - -if (sessionFiles.length === 0) { - // No existing session, proceed to Phase 1 - goto Phase1 -} - -if (sessionFiles.length === 1) { - // Single session found - const session = Read(sessionFiles[0]) - if (session.status === "active" || session.status === "paused") { - Output("[coordinator] Resuming session: " + session.session_id) - goto SessionReconciliation - } -} - -if (sessionFiles.length > 1) { - // Multiple sessions - ask user - const choices = sessionFiles.map(f => { - const s = Read(f) - return `${s.session_id} (${s.status}) - ${s.mode} - ${s.tasks_completed}/${s.tasks_total}` - }) - - const answer = AskUserQuestion({ - question: "Multiple sessions found. Which to resume?", - choices: ["Create new session", ...choices] - }) - - if (answer === "Create new session") { - goto Phase1 - } else { - const selectedSession = Read(sessionFiles[answer.index - 1]) - goto SessionReconciliation - } -} - -// Session Reconciliation Process -SessionReconciliation: { - Output("[coordinator] Reconciling session state...") - - // Pipeline constants (aligned with SKILL.md Three-Mode Pipeline) - const SPEC_CHAIN = [ - "RESEARCH-001", "DISCUSS-001", "DRAFT-001", "DISCUSS-002", - "DRAFT-002", "DISCUSS-003", "DRAFT-003", "DISCUSS-004", - "DRAFT-004", "DISCUSS-005", "QUALITY-001", "DISCUSS-006" - ] - - const IMPL_CHAIN = ["PLAN-001", "IMPL-001", "TEST-001", "REVIEW-001"] - - const FE_CHAIN = ["DEV-FE-001", "QA-FE-001"] - - const FULLSTACK_CHAIN = ["PLAN-001", "IMPL-001", "DEV-FE-001", "TEST-001", "QA-FE-001", "REVIEW-001"] - - // Task metadata — role must match VALID_ROLES in SKILL.md - const TASK_METADATA = { - // Spec pipeline (12 tasks) - "RESEARCH-001": { role: "analyst", phase: "spec", deps: [], description: "Seed analysis: codebase exploration and context gathering" }, - "DISCUSS-001": { role: "discussant", phase: "spec", deps: ["RESEARCH-001"], description: "Critique research findings" }, - "DRAFT-001": { role: "writer", phase: "spec", deps: ["DISCUSS-001"], description: "Generate Product Brief" }, - "DISCUSS-002": { role: "discussant", phase: "spec", deps: ["DRAFT-001"], description: "Critique Product Brief" }, - "DRAFT-002": { role: "writer", phase: "spec", deps: ["DISCUSS-002"], description: "Generate Requirements/PRD" }, - "DISCUSS-003": { role: "discussant", phase: "spec", deps: ["DRAFT-002"], description: "Critique Requirements/PRD" }, - "DRAFT-003": { role: "writer", phase: "spec", deps: ["DISCUSS-003"], description: "Generate Architecture Document" }, - "DISCUSS-004": { role: "discussant", phase: "spec", deps: ["DRAFT-003"], description: "Critique Architecture Document" }, - "DRAFT-004": { role: "writer", phase: "spec", deps: ["DISCUSS-004"], description: "Generate Epics" }, - "DISCUSS-005": { role: "discussant", phase: "spec", deps: ["DRAFT-004"], description: "Critique Epics" }, - "QUALITY-001": { role: "reviewer", phase: "spec", deps: ["DISCUSS-005"], description: "5-dimension spec quality validation" }, - "DISCUSS-006": { role: "discussant", phase: "spec", deps: ["QUALITY-001"], description: "Final review discussion and sign-off" }, - - // Impl pipeline (deps shown for impl-only; full-lifecycle adds PLAN-001 → ["DISCUSS-006"]) - "PLAN-001": { role: "planner", phase: "impl", deps: [], description: "Multi-angle codebase exploration and structured planning" }, - "IMPL-001": { role: "executor", phase: "impl", deps: ["PLAN-001"], description: "Code implementation following plan" }, - "TEST-001": { role: "tester", phase: "impl", deps: ["IMPL-001"], description: "Adaptive test-fix cycles and quality gates" }, - "REVIEW-001": { role: "reviewer", phase: "impl", deps: ["IMPL-001"], description: "4-dimension code review" }, - - // Frontend pipeline tasks - "DEV-FE-001": { role: "fe-developer", phase: "impl", deps: ["PLAN-001"], description: "Frontend component/page implementation" }, - "QA-FE-001": { role: "fe-qa", phase: "impl", deps: ["DEV-FE-001"], description: "5-dimension frontend QA" } - } - - // Helper: Get predecessor task - function getPredecessor(taskId, chain) { - const index = chain.indexOf(taskId) - return index > 0 ? chain[index - 1] : null - } - - // Step 1: Audit current state - const session = Read(sessionFile) - const teamState = TeamGet(session.team_id) - const allTasks = teamState.tasks - - Output("[coordinator] Session audit:") - Output(` Mode: ${session.mode}`) - Output(` Tasks completed: ${session.tasks_completed}/${session.tasks_total}`) - Output(` Status: ${session.status}`) - - // Step 2: Reconcile task states - const completedTasks = allTasks.filter(t => t.status === "completed") - const activeTasks = allTasks.filter(t => t.status === "active") - const blockedTasks = allTasks.filter(t => t.status === "blocked") - const pendingTasks = allTasks.filter(t => t.status === "pending") - - Output("[coordinator] Task breakdown:") - Output(` Completed: ${completedTasks.length}`) - Output(` Active: ${activeTasks.length}`) - Output(` Blocked: ${blockedTasks.length}`) - Output(` Pending: ${pendingTasks.length}`) - - // Step 3: Determine remaining work - const expectedChain = - session.mode === "spec-only" ? SPEC_CHAIN : - session.mode === "impl-only" ? IMPL_CHAIN : - session.mode === "fe-only" ? ["PLAN-001", ...FE_CHAIN] : - session.mode === "fullstack" ? FULLSTACK_CHAIN : - session.mode === "full-lifecycle-fe" ? [...SPEC_CHAIN, ...FULLSTACK_CHAIN] : - [...SPEC_CHAIN, ...IMPL_CHAIN] // full-lifecycle default - - const remainingTaskIds = expectedChain.filter(id => - !completedTasks.some(t => t.subject === id) - ) - - Output(`[coordinator] Remaining tasks: ${remainingTaskIds.join(", ")}`) - - // Step 4: Rebuild team if needed - if (!teamState || teamState.status === "disbanded") { - Output("[coordinator] Team disbanded, recreating...") - TeamCreate({ - team_id: session.team_id, - session_id: session.session_id, - mode: session.mode - }) - } - - // Step 5: Create missing tasks - for (const taskId of remainingTaskIds) { - const existingTask = allTasks.find(t => t.subject === taskId) - if (!existingTask) { - const metadata = TASK_METADATA[taskId] - TaskCreate({ - subject: taskId, - owner: metadata.role, - description: `${metadata.description}\nSession: ${sessionFolder}`, - blockedBy: metadata.deps, - status: "pending" - }) - Output(`[coordinator] Created missing task: ${taskId} (${metadata.role})`) - } - } - - // Step 6: Verify dependencies - for (const taskId of remainingTaskIds) { - const task = allTasks.find(t => t.subject === taskId) - if (!task) continue - const metadata = TASK_METADATA[taskId] - const allDepsMet = metadata.deps.every(depId => - completedTasks.some(t => t.subject === depId) - ) - - if (allDepsMet && task.status !== "completed") { - Output(`[coordinator] Unblocked task: ${taskId} (${metadata.role})`) - } - } - - // Step 7: Update session state - session.status = "active" - session.resumed_at = new Date().toISOString() - session.tasks_completed = completedTasks.length - Write(sessionFile, session) - - // Step 8: Report reconciliation - Output("[coordinator] Session reconciliation complete") - Output(`[coordinator] Ready to resume from: ${remainingTaskIds[0] || "all tasks complete"}`) - - // Step 9: Kick next task - if (remainingTaskIds.length > 0) { - const nextTaskId = remainingTaskIds[0] - const nextTask = TaskGet(nextTaskId) - const metadata = TASK_METADATA[nextTaskId] - - if (metadata.deps.every(depId => completedTasks.some(t => t.subject === depId))) { - TaskUpdate(nextTaskId, { status: "active" }) - Output(`[coordinator] Kicking task: ${nextTaskId}`) - goto Phase4_CoordinationLoop - } else { - Output(`[coordinator] Next task ${nextTaskId} blocked on: ${metadata.deps.join(", ")}`) - goto Phase4_CoordinationLoop - } - } else { - Output("[coordinator] All tasks complete!") - goto Phase5_Report - } -} -``` - ---- - -### Phase 1: Requirement Clarification - -**Purpose**: Parse user input and clarify execution parameters - -```javascript -Output("[coordinator] Phase 1: Requirement Clarification") - -// Parse $ARGUMENTS -const userInput = $ARGUMENTS - -// Extract mode if specified -let mode = null -if (userInput.includes("spec-only")) mode = "spec-only" -if (userInput.includes("impl-only")) mode = "impl-only" -if (userInput.includes("full-lifecycle")) mode = "full-lifecycle" - -// Extract scope if specified -let scope = null -if (userInput.includes("scope:")) { - scope = userInput.match(/scope:\s*([^\n]+)/)[1] -} - -// Extract focus areas -let focus = [] -if (userInput.includes("focus:")) { - focus = userInput.match(/focus:\s*([^\n]+)/)[1].split(",").map(s => s.trim()) -} - -// Extract depth preference -let depth = "standard" -if (userInput.includes("depth:shallow")) depth = "shallow" -if (userInput.includes("depth:deep")) depth = "deep" - -// Ask for missing parameters -if (!mode) { - mode = AskUserQuestion({ - question: "Select execution mode:", - choices: [ - "spec-only - Generate specifications only", - "impl-only - Implementation only (requires existing spec)", - "full-lifecycle - Complete spec + implementation", - "fe-only - Frontend-only pipeline (plan → dev → QA)", - "fullstack - Backend + frontend parallel pipeline", - "full-lifecycle-fe - Full lifecycle with frontend (spec → fullstack)" - ] - }) -} - -if (!scope) { - scope = AskUserQuestion({ - question: "Describe the project scope:", - type: "text" - }) -} - -if (focus.length === 0) { - const focusAnswer = AskUserQuestion({ - question: "Any specific focus areas? (optional)", - type: "text", - optional: true - }) - if (focusAnswer) { - focus = focusAnswer.split(",").map(s => s.trim()) - } -} - -// Determine execution method -const executionMethod = AskUserQuestion({ - question: "Execution method:", - choices: [ - "sequential - One task at a time (safer, slower)", - "parallel - Multiple tasks in parallel (faster, more complex)" - ] -}) - -// Store clarified requirements -const requirements = { - mode, - scope, - focus, - depth, - executionMethod, - originalInput: userInput -} - -// --- Frontend Detection --- -// Auto-detect frontend tasks and adjust pipeline mode -const FE_KEYWORDS = /component|page|UI|前端|frontend|CSS|HTML|React|Vue|Tailwind|组件|页面|样式|layout|responsive|Svelte|Next\.js|Nuxt|shadcn|设计系统|design.system/i -const BE_KEYWORDS = /API|database|server|后端|backend|middleware|auth|REST|GraphQL|migration|schema|model|controller|service/i - -function detectImplMode(taskDescription) { - const hasFE = FE_KEYWORDS.test(taskDescription) - const hasBE = BE_KEYWORDS.test(taskDescription) - - // Also check project files for frontend frameworks - const hasFEFiles = Bash(`test -f package.json && (grep -q react package.json || grep -q vue package.json || grep -q svelte package.json || grep -q next package.json); echo $?`) === '0' - - if (hasFE && hasBE) return 'fullstack' - if (hasFE || hasFEFiles) return 'fe-only' - return 'impl-only' // default backend -} - -// Apply frontend detection for implementation modes -if (mode === 'impl-only' || mode === 'full-lifecycle') { - const detectedMode = detectImplMode(scope + ' ' + userInput) - if (detectedMode !== 'impl-only') { - // Frontend detected — upgrade pipeline mode - if (mode === 'impl-only') { - mode = detectedMode // fe-only or fullstack - } else if (mode === 'full-lifecycle') { - mode = 'full-lifecycle-fe' // spec + fullstack - } - requirements.mode = mode - Output(`[coordinator] Frontend detected → pipeline upgraded to: ${mode}`) - } -} - -Output("[coordinator] Requirements clarified:") -Output(` Mode: ${mode}`) -Output(` Scope: ${scope}`) -Output(` Focus: ${focus.join(", ") || "none"}`) -Output(` Depth: ${depth}`) -Output(` Execution: ${executionMethod}`) - -goto Phase2 -``` - ---- - -### Phase 2: Create Team + Initialize Session - -**Purpose**: Initialize team and session state - -```javascript -Output("[coordinator] Phase 2: Team Creation") - -// Generate session ID -const sessionId = `team-lifecycle-${Date.now()}` -const teamId = sessionId - -// Create team -TeamCreate({ - team_id: teamId, - session_id: sessionId, - mode: requirements.mode, - scope: requirements.scope, - focus: requirements.focus, - depth: requirements.depth, - executionMethod: requirements.executionMethod -}) - -Output(`[coordinator] Team created: ${teamId}`) - -// Initialize wisdom directory -const wisdomDir = `${sessionFolder}/wisdom` -Bash(`mkdir -p "${wisdomDir}"`) -Write(`${wisdomDir}/learnings.md`, `# Learnings\n\n\n`) -Write(`${wisdomDir}/decisions.md`, `# Decisions\n\n\n`) -Write(`${wisdomDir}/conventions.md`, `# Conventions\n\n\n\n`) -Write(`${wisdomDir}/issues.md`, `# Known Issues\n\n\n`) - -// Initialize session file -const sessionFile = `D:/Claude_dms3/.workflow/.sessions/${sessionId}.json` -const sessionData = { - session_id: sessionId, - team_id: teamId, - mode: requirements.mode, - scope: requirements.scope, - focus: requirements.focus, - depth: requirements.depth, - executionMethod: requirements.executionMethod, - status: "active", - created_at: new Date().toISOString(), - tasks_total: requirements.mode === "spec-only" ? 12 : - requirements.mode === "impl-only" ? 4 : - requirements.mode === "fe-only" ? 3 : - requirements.mode === "fullstack" ? 6 : - requirements.mode === "full-lifecycle-fe" ? 18 : 16, - tasks_completed: 0, - current_phase: requirements.mode === "impl-only" ? "impl" : "spec" -} - -Write(sessionFile, sessionData) -Output(`[coordinator] Session file created: ${sessionFile}`) - -// ⚠️ Workers are NOT pre-spawned here. -// Workers are spawned per-stage in Phase 4 via Stop-Wait Task(run_in_background: false). -// See SKILL.md Coordinator Spawn Template for worker prompt templates. -// -// Worker roles by mode (spawned on-demand, must match VALID_ROLES in SKILL.md): -// spec-only: analyst, discussant, writer, reviewer -// impl-only: planner, executor, tester, reviewer -// fe-only: planner, fe-developer, fe-qa -// fullstack: planner, executor, fe-developer, tester, fe-qa, reviewer -// full-lifecycle: analyst, discussant, writer, reviewer, planner, executor, tester -// full-lifecycle-fe: all of the above + fe-developer, fe-qa -// On-demand (ambiguity): analyst or explorer - -goto Phase3 -``` - ---- - -### Phase 3: Create Task Chain - -**Purpose**: Dispatch tasks based on execution mode - -```javascript -Output("[coordinator] Phase 3: Task Dispatching") - -// Delegate to command file -const dispatchStrategy = Read("commands/dispatch.md") - -// Execute strategy defined in command file -// (dispatch.md contains the complete task chain creation logic) - -goto Phase4 -``` - ---- - -### Phase 4: Coordination Loop - -**Purpose**: Monitor task progress and route messages - -> **设计原则（Stop-Wait）**: 模型执行没有时间概念，禁止任何形式的轮询等待。 -> - ❌ 禁止: `while` 循环 + `sleep` + 检查状态 -> - ✅ 采用: 同步 `Task(run_in_background: false)` 调用，Worker 返回 = 阶段完成信号 -> -> 按 Phase 3 创建的任务链顺序，逐阶段 spawn worker 同步执行。 -> Worker prompt 使用 SKILL.md Coordinator Spawn Template。 - -```javascript -Output("[coordinator] Phase 4: Coordination Loop") - -// Delegate to command file -const monitorStrategy = Read("commands/monitor.md") - -// Execute strategy defined in command file -// (monitor.md contains the complete message routing and checkpoint logic) - -goto Phase5 -``` - ---- - -### Phase 5: Report + Persistent Loop - -**Purpose**: Provide completion report and offer next steps - -```javascript -Output("[coordinator] Phase 5: Completion Report") - -// Load session state -const session = Read(sessionFile) -const teamState = TeamGet(session.team_id) - -// Generate report -Output("[coordinator] ========================================") -Output("[coordinator] TEAM LIFECYCLE EXECUTION COMPLETE") -Output("[coordinator] ========================================") -Output(`[coordinator] Session ID: ${session.session_id}`) -Output(`[coordinator] Mode: ${session.mode}`) -Output(`[coordinator] Tasks Completed: ${session.tasks_completed}/${session.tasks_total}`) -Output(`[coordinator] Duration: ${calculateDuration(session.created_at, new Date())}`) - -// List deliverables -const completedTasks = teamState.tasks.filter(t => t.status === "completed") -Output("[coordinator] Deliverables:") -for (const task of completedTasks) { - Output(` ✓ ${task.subject}: ${task.description}`) - if (task.output_file) { - Output(` Output: ${task.output_file}`) - } -} - -// Update session status -session.status = "completed" -session.completed_at = new Date().toISOString() -Write(sessionFile, session) - -// Offer next steps -const nextAction = AskUserQuestion({ - question: "What would you like to do next?", - choices: [ - "exit - End session", - "review - Review specific deliverables", - "extend - Add more tasks to this session", - "handoff-lite-plan - Create lite-plan from spec", - "handoff-full-plan - Create full-plan from spec", - "handoff-req-plan - Create req-plan from requirements", - "handoff-create-issues - Generate GitHub issues" - ] -}) - -switch (nextAction) { - case "exit": - Output("[coordinator] Session ended. Goodbye!") - break - - case "review": - const taskToReview = AskUserQuestion({ - question: "Which task output to review?", - choices: completedTasks.map(t => t.subject) - }) - const reviewTask = completedTasks.find(t => t.subject === taskToReview) - if (reviewTask.output_file) { - const content = Read(reviewTask.output_file) - Output(`[coordinator] Task: ${reviewTask.subject}`) - Output(content) - } - goto Phase5 // Loop back for more actions - - case "extend": - const extensionScope = AskUserQuestion({ - question: "Describe additional work:", - type: "text" - }) - Output("[coordinator] Creating extension tasks...") - // Create custom tasks based on extension scope - // (Implementation depends on extension requirements) - goto Phase4 // Return to coordination loop - - case "handoff-lite-plan": - Output("[coordinator] Generating lite-plan from specifications...") - // Read spec completion output (DISCUSS-006 = final sign-off) - const specOutput = Read(getTaskOutput("DISCUSS-006")) - // Create lite-plan format - const litePlan = generateLitePlan(specOutput) - const litePlanFile = `D:/Claude_dms3/.workflow/.sessions/${session.session_id}-lite-plan.md` - Write(litePlanFile, litePlan) - Output(`[coordinator] Lite-plan created: ${litePlanFile}`) - goto Phase5 - - case "handoff-full-plan": - Output("[coordinator] Generating full-plan from specifications...") - const fullSpecOutput = Read(getTaskOutput("DISCUSS-006")) - const fullPlan = generateFullPlan(fullSpecOutput) - const fullPlanFile = `D:/Claude_dms3/.workflow/.sessions/${session.session_id}-full-plan.md` - Write(fullPlanFile, fullPlan) - Output(`[coordinator] Full-plan created: ${fullPlanFile}`) - goto Phase5 - - case "handoff-req-plan": - Output("[coordinator] Generating req-plan from requirements...") - const reqAnalysis = Read(getTaskOutput("RESEARCH-001")) - const reqPlan = generateReqPlan(reqAnalysis) - const reqPlanFile = `D:/Claude_dms3/.workflow/.sessions/${session.session_id}-req-plan.md` - Write(reqPlanFile, reqPlan) - Output(`[coordinator] Req-plan created: ${reqPlanFile}`) - goto Phase5 - - case "handoff-create-issues": - Output("[coordinator] Generating GitHub issues...") - const issuesSpec = Read(getTaskOutput("DISCUSS-006")) - const issues = generateGitHubIssues(issuesSpec) - const issuesFile = `D:/Claude_dms3/.workflow/.sessions/${session.session_id}-issues.json` - Write(issuesFile, issues) - Output(`[coordinator] Issues created: ${issuesFile}`) - Output("[coordinator] Use GitHub CLI to import: gh issue create --title ... --body ...") - goto Phase5 -} - -// Helper functions -function calculateDuration(start, end) { - const diff = new Date(end) - new Date(start) - const minutes = Math.floor(diff / 60000) - const seconds = Math.floor((diff % 60000) / 1000) - return `${minutes}m ${seconds}s` -} - -function getTaskOutput(taskId) { - const task = TaskGet(taskId) - return task.output_file -} - -function generateLitePlan(specOutput) { - // Parse spec output and create lite-plan format - return `# Lite Plan\n\n${specOutput}\n\n## Implementation Steps\n- Step 1\n- Step 2\n...` -} - -function generateFullPlan(specOutput) { - // Parse spec output and create full-plan format with detailed breakdown - return `# Full Plan\n\n${specOutput}\n\n## Detailed Implementation\n### Phase 1\n### Phase 2\n...` -} - -function generateReqPlan(reqAnalysis) { - // Parse requirements and create req-plan format - return `# Requirements Plan\n\n${reqAnalysis}\n\n## Acceptance Criteria\n- Criterion 1\n- Criterion 2\n...` -} - -function generateGitHubIssues(specOutput) { - // Parse spec and generate GitHub issue JSON - return { - issues: [ - { title: "Issue 1", body: "Description", labels: ["feature"] }, - { title: "Issue 2", body: "Description", labels: ["bug"] } - ] - } -} -``` - ---- - -## Session File Structure - -```json -{ - "session_id": "team-lifecycle-1234567890", - "team_id": "team-lifecycle-1234567890", - "mode": "full-lifecycle", - "scope": "Build authentication system", - "focus": ["security", "scalability"], - "depth": "standard", - "executionMethod": "sequential", - "status": "active", - "created_at": "2026-02-18T10:00:00Z", - "completed_at": null, - "resumed_at": null, - "tasks_total": 16, - "tasks_completed": 5, - "current_phase": "spec" -} -``` - ---- - -## Error Handling - -| Error Type | Coordinator Action | -|------------|-------------------| -| Task timeout | Log timeout, mark task as failed, ask user to retry or skip | -| Worker crash | Respawn worker, reassign task | -| Dependency cycle | Detect cycle, report to user, halt execution | -| Invalid mode | Reject with error message, ask user to clarify | -| Session corruption | Attempt recovery, fallback to manual reconciliation | diff --git a/.claude/skills_lib/team-lifecycle-v2/roles/discussant/commands/critique.md b/.claude/skills_lib/team-lifecycle-v2/roles/discussant/commands/critique.md deleted file mode 100644 index bc429a4c..00000000 --- a/.claude/skills_lib/team-lifecycle-v2/roles/discussant/commands/critique.md +++ /dev/null @@ -1,396 +0,0 @@ -# Command: Multi-Perspective Critique - -Phase 3 of discussant execution - launch parallel CLI analyses for each required perspective. - -## Overview - -This command executes multi-perspective critique by routing to specialized CLI tools based on perspective type. Each perspective produces structured critique with strengths, weaknesses, suggestions, and ratings. - -## Perspective Definitions - -### 1. Product Perspective (gemini) - -**Focus**: Market fit, user value, business viability, competitive differentiation - -**CLI Tool**: gemini - -**Output Structure**: -```json -{ - "perspective": "product", - "strengths": ["string"], - "weaknesses": ["string"], - "suggestions": ["string"], - "rating": 1-5 -} -``` - -**Prompt Template**: -``` -Analyze from Product Manager perspective: -- Market fit and user value proposition -- Business viability and ROI potential -- Competitive differentiation -- User experience and adoption barriers - -Artifact: {artifactContent} - -Output JSON with: strengths[], weaknesses[], suggestions[], rating (1-5) -``` - -### 2. Technical Perspective (codex) - -**Focus**: Feasibility, tech debt, performance, security, maintainability - -**CLI Tool**: codex - -**Output Structure**: -```json -{ - "perspective": "technical", - "strengths": ["string"], - "weaknesses": ["string"], - "suggestions": ["string"], - "rating": 1-5 -} -``` - -**Prompt Template**: -``` -Analyze from Tech Lead perspective: -- Technical feasibility and implementation complexity -- Architecture decisions and tech debt implications -- Performance and scalability considerations -- Security vulnerabilities and risks -- Code maintainability and extensibility - -Artifact: {artifactContent} - -Output JSON with: strengths[], weaknesses[], suggestions[], rating (1-5) -``` - -### 3. Quality Perspective (claude) - -**Focus**: Completeness, testability, consistency, standards compliance - -**CLI Tool**: claude - -**Output Structure**: -```json -{ - "perspective": "quality", - "strengths": ["string"], - "weaknesses": ["string"], - "suggestions": ["string"], - "rating": 1-5 -} -``` - -**Prompt Template**: -``` -Analyze from QA Lead perspective: -- Specification completeness and clarity -- Testability and test coverage potential -- Consistency across requirements/design -- Standards compliance (coding, documentation, accessibility) -- Ambiguity detection and edge case coverage - -Artifact: {artifactContent} - -Output JSON with: strengths[], weaknesses[], suggestions[], rating (1-5) -``` - -### 4. Risk Perspective (gemini) - -**Focus**: Risk identification, dependency analysis, assumption validation, failure modes - -**CLI Tool**: gemini - -**Output Structure**: -```json -{ - "perspective": "risk", - "strengths": ["string"], - "weaknesses": ["string"], - "suggestions": ["string"], - "rating": 1-5, - "risk_level": "low|medium|high|critical" -} -``` - -**Prompt Template**: -``` -Analyze from Risk Analyst perspective: -- Risk identification (technical, business, operational) -- Dependency analysis and external risks -- Assumption validation and hidden dependencies -- Failure modes and mitigation strategies -- Timeline and resource risks - -Artifact: {artifactContent} - -Output JSON with: strengths[], weaknesses[], suggestions[], rating (1-5), risk_level -``` - -### 5. Coverage Perspective (gemini) - -**Focus**: Requirement completeness vs original intent, scope drift, gap detection - -**CLI Tool**: gemini - -**Output Structure**: -```json -{ - "perspective": "coverage", - "strengths": ["string"], - "weaknesses": ["string"], - "suggestions": ["string"], - "rating": 1-5, - "covered_requirements": ["REQ-ID"], - "partial_requirements": ["REQ-ID"], - "missing_requirements": ["REQ-ID"], - "scope_creep": ["description"] -} -``` - -**Prompt Template**: -``` -Analyze from Requirements Analyst perspective: -- Compare current artifact against original requirements in discovery-context.json -- Identify covered requirements (fully addressed) -- Identify partial requirements (partially addressed) -- Identify missing requirements (not addressed) -- Detect scope creep (new items not in original requirements) - -Original Requirements: {discoveryContext} -Current Artifact: {artifactContent} - -Output JSON with: -- strengths[], weaknesses[], suggestions[], rating (1-5) -- covered_requirements[] (REQ-IDs fully addressed) -- partial_requirements[] (REQ-IDs partially addressed) -- missing_requirements[] (REQ-IDs not addressed) ← CRITICAL if non-empty -- scope_creep[] (new items not in original requirements) -``` - -## Execution Pattern - -### Parallel CLI Execution - -```javascript -// Load artifact content -const artifactPath = `${sessionFolder}/${config.artifact}` -const artifactContent = config.type === 'json' - ? JSON.parse(Read(artifactPath)) - : Read(artifactPath) - -// Load discovery context for coverage perspective -let discoveryContext = null -try { - discoveryContext = JSON.parse(Read(`${sessionFolder}/spec/discovery-context.json`)) -} catch { /* may not exist in early rounds */ } - -// Launch parallel CLI analyses -const perspectiveResults = [] - -for (const perspective of config.perspectives) { - let cliTool, prompt - - switch(perspective) { - case 'product': - cliTool = 'gemini' - prompt = `Analyze from Product Manager perspective: -- Market fit and user value proposition -- Business viability and ROI potential -- Competitive differentiation -- User experience and adoption barriers - -Artifact: -${JSON.stringify(artifactContent, null, 2)} - -Output JSON with: strengths[], weaknesses[], suggestions[], rating (1-5)` - break - - case 'technical': - cliTool = 'codex' - prompt = `Analyze from Tech Lead perspective: -- Technical feasibility and implementation complexity -- Architecture decisions and tech debt implications -- Performance and scalability considerations -- Security vulnerabilities and risks -- Code maintainability and extensibility - -Artifact: -${JSON.stringify(artifactContent, null, 2)} - -Output JSON with: strengths[], weaknesses[], suggestions[], rating (1-5)` - break - - case 'quality': - cliTool = 'claude' - prompt = `Analyze from QA Lead perspective: -- Specification completeness and clarity -- Testability and test coverage potential -- Consistency across requirements/design -- Standards compliance (coding, documentation, accessibility) -- Ambiguity detection and edge case coverage - -Artifact: -${JSON.stringify(artifactContent, null, 2)} - -Output JSON with: strengths[], weaknesses[], suggestions[], rating (1-5)` - break - - case 'risk': - cliTool = 'gemini' - prompt = `Analyze from Risk Analyst perspective: -- Risk identification (technical, business, operational) -- Dependency analysis and external risks -- Assumption validation and hidden dependencies -- Failure modes and mitigation strategies -- Timeline and resource risks - -Artifact: -${JSON.stringify(artifactContent, null, 2)} - -Output JSON with: strengths[], weaknesses[], suggestions[], rating (1-5), risk_level` - break - - case 'coverage': - cliTool = 'gemini' - prompt = `Analyze from Requirements Analyst perspective: -- Compare current artifact against original requirements in discovery-context.json -- Identify covered requirements (fully addressed) -- Identify partial requirements (partially addressed) -- Identify missing requirements (not addressed) -- Detect scope creep (new items not in original requirements) - -Original Requirements: -${discoveryContext ? JSON.stringify(discoveryContext, null, 2) : 'Not available'} - -Current Artifact: -${JSON.stringify(artifactContent, null, 2)} - -Output JSON with: -- strengths[], weaknesses[], suggestions[], rating (1-5) -- covered_requirements[] (REQ-IDs fully addressed) -- partial_requirements[] (REQ-IDs partially addressed) -- missing_requirements[] (REQ-IDs not addressed) ← CRITICAL if non-empty -- scope_creep[] (new items not in original requirements)` - break - } - - // Execute CLI analysis (run_in_background: true per CLAUDE.md) - Bash({ - command: `ccw cli -p "${prompt.replace(/"/g, '\\"')}" --tool ${cliTool} --mode analysis`, - run_in_background: true, - description: `[discussant] ${perspective} perspective analysis` - }) -} - -// Wait for all CLI results via hook callbacks -// Results will be collected in perspectiveResults array -``` - -## Critical Divergence Detection - -### Coverage Gap Detection - -```javascript -const coverageResult = perspectiveResults.find(p => p.perspective === 'coverage') -if (coverageResult?.missing_requirements?.length > 0) { - // Flag as critical divergence - synthesis.divergent_views.push({ - topic: 'requirement_coverage_gap', - description: `${coverageResult.missing_requirements.length} requirements from discovery-context not covered: ${coverageResult.missing_requirements.join(', ')}`, - severity: 'high', - source: 'coverage' - }) -} -``` - -### Risk Level Detection - -```javascript -const riskResult = perspectiveResults.find(p => p.perspective === 'risk') -if (riskResult?.risk_level === 'high' || riskResult?.risk_level === 'critical') { - synthesis.risk_flags.push({ - level: riskResult.risk_level, - description: riskResult.weaknesses.join('; ') - }) -} -``` - -## Fallback Strategy - -### CLI Failure Fallback - -```javascript -// If CLI analysis fails for a perspective, fallback to direct Claude analysis -try { - // CLI execution - Bash({ command: `ccw cli -p "..." --tool ${cliTool} --mode analysis`, run_in_background: true }) -} catch (error) { - // Fallback: Direct Claude analysis - const fallbackResult = { - perspective: perspective, - strengths: ["Direct analysis: ..."], - weaknesses: ["Direct analysis: ..."], - suggestions: ["Direct analysis: ..."], - rating: 3, - _fallback: true - } - perspectiveResults.push(fallbackResult) -} -``` - -### All CLI Failures - -```javascript -if (perspectiveResults.every(r => r._fallback)) { - // Generate basic discussion from direct reading - const basicDiscussion = { - convergent_themes: ["Basic analysis from direct reading"], - divergent_views: [], - action_items: ["Review artifact manually"], - open_questions: [], - decisions: [], - risk_flags: [], - overall_sentiment: 'neutral', - consensus_reached: true, - _basic_mode: true - } -} -``` - -## Output Format - -Each perspective produces: - -```json -{ - "perspective": "product|technical|quality|risk|coverage", - "strengths": ["string"], - "weaknesses": ["string"], - "suggestions": ["string"], - "rating": 1-5, - - // Risk perspective only - "risk_level": "low|medium|high|critical", - - // Coverage perspective only - "covered_requirements": ["REQ-ID"], - "partial_requirements": ["REQ-ID"], - "missing_requirements": ["REQ-ID"], - "scope_creep": ["description"] -} -``` - -## Integration with Phase 4 - -Phase 4 (Consensus Synthesis) consumes `perspectiveResults` array to: -1. Extract convergent themes (2+ perspectives agree) -2. Extract divergent views (perspectives conflict) -3. Detect coverage gaps (missing_requirements non-empty) -4. Assess risk flags (high/critical risk_level) -5. Determine consensus_reached (true if no critical divergences) diff --git a/.claude/skills_lib/team-lifecycle-v2/roles/discussant/role.md b/.claude/skills_lib/team-lifecycle-v2/roles/discussant/role.md deleted file mode 100644 index 855a7ef3..00000000 --- a/.claude/skills_lib/team-lifecycle-v2/roles/discussant/role.md +++ /dev/null @@ -1,265 +0,0 @@ -# Role: discussant - -Multi-perspective critique, consensus building, and conflict escalation. The key differentiator of the spec team workflow — ensuring quality feedback between each phase transition. - -## Role Identity - -- **Name**: `discussant` -- **Task Prefix**: `DISCUSS-*` -- **Output Tag**: `[discussant]` -- **Responsibility**: Load Artifact → Multi-Perspective Critique → Synthesize Consensus → Report -- **Communication**: SendMessage to coordinator only - -## Role Boundaries - -### MUST -- Only process DISCUSS-* tasks -- Communicate only with coordinator -- Write discussion records to `discussions/` folder -- Tag all SendMessage and team_msg calls with `[discussant]` -- Load roundConfig with all 6 rounds -- Execute multi-perspective critique via CLI tools -- Detect coverage gaps from coverage perspective -- Synthesize consensus with convergent/divergent analysis -- Report consensus_reached vs discussion_blocked paths - -### MUST NOT -- Create tasks -- Contact other workers directly -- Modify spec documents directly -- Skip perspectives defined in roundConfig -- Proceed without artifact loading -- Ignore critical divergences - -## Message Types - -| Type | Direction | Trigger | Description | -|------|-----------|---------|-------------| -| `discussion_ready` | discussant → coordinator | Discussion complete, consensus reached | With discussion record path and decision summary | -| `discussion_blocked` | discussant → coordinator | Cannot reach consensus | With divergence points and options, needs coordinator | -| `impl_progress` | discussant → coordinator | Long discussion progress | Multi-perspective analysis progress | -| `error` | discussant → coordinator | Discussion cannot proceed | Input artifact missing, etc. | - -## Message Bus - -Before every `SendMessage`, MUST call `mcp__ccw-tools__team_msg` to log: - -```javascript -// Discussion complete -mcp__ccw-tools__team_msg({ operation: "log", team: teamName, from: "discussant", to: "coordinator", type: "discussion_ready", summary: "[discussant] Scope discussion consensus reached: 3 decisions", ref: `${sessionFolder}/discussions/discuss-001-scope.md` }) - -// Discussion blocked -mcp__ccw-tools__team_msg({ operation: "log", team: teamName, from: "discussant", to: "coordinator", type: "discussion_blocked", summary: "[discussant] Cannot reach consensus on tech stack", data: { reason: "...", options: [...] } }) - -// Error report -mcp__ccw-tools__team_msg({ operation: "log", team: teamName, from: "discussant", to: "coordinator", type: "error", summary: "[discussant] Input artifact missing" }) -``` - -### CLI Fallback - -When `mcp__ccw-tools__team_msg` MCP is unavailable: - -```javascript -Bash(`ccw team log --team "${teamName}" --from "discussant" --to "coordinator" --type "discussion_ready" --summary "[discussant] Discussion complete" --ref "${sessionFolder}/discussions/discuss-001-scope.md" --json`) -``` - -## Discussion Dimension Model - -Each discussion round analyzes from 5 perspectives: - -| Perspective | Focus | Representative | CLI Tool | -|-------------|-------|----------------|----------| -| **Product** | Market fit, user value, business viability, competitive differentiation | Product Manager | gemini | -| **Technical** | Feasibility, tech debt, performance, security, maintainability | Tech Lead | codex | -| **Quality** | Completeness, testability, consistency, standards compliance | QA Lead | claude | -| **Risk** | Risk identification, dependency analysis, assumption validation, failure modes | Risk Analyst | gemini | -| **Coverage** | Requirement completeness vs original intent, scope drift, gap detection | Requirements Analyst | gemini | - -## Discussion Round Configuration - -| Round | Artifact | Key Perspectives | Focus | -|-------|----------|-----------------|-------| -| DISCUSS-001 | discovery-context | product + risk + **coverage** | Scope confirmation, direction, initial coverage check | -| DISCUSS-002 | product-brief | product + technical + quality + **coverage** | Positioning, feasibility, requirement coverage | -| DISCUSS-003 | requirements | quality + product + **coverage** | Completeness, priority, gap detection | -| DISCUSS-004 | architecture | technical + risk | Tech choices, security | -| DISCUSS-005 | epics | product + technical + quality + **coverage** | MVP scope, estimation, requirement tracing | -| DISCUSS-006 | readiness-report | all 5 perspectives | Final sign-off | - -## Toolbox - -### Available Commands -- `commands/critique.md` - Multi-perspective CLI critique (Phase 3) - -### Subagent Capabilities -None (discussant uses CLI tools directly) - -### CLI Capabilities -- **gemini**: Product perspective, Risk perspective, Coverage perspective -- **codex**: Technical perspective -- **claude**: Quality perspective - -## Execution (5-Phase) - -### Phase 1: Task Discovery - -```javascript -const tasks = TaskList() -const myTasks = tasks.filter(t => - t.subject.startsWith('DISCUSS-') && - t.owner === 'discussant' && - t.status === 'pending' && - t.blockedBy.length === 0 -) - -if (myTasks.length === 0) return // idle - -const task = TaskGet({ taskId: myTasks[0].id }) -TaskUpdate({ taskId: task.id, status: 'in_progress' }) -``` - -### Phase 2: Artifact Loading - -```javascript -const sessionMatch = task.description.match(/Session:\s*(.+)/) -const sessionFolder = sessionMatch ? sessionMatch[1].trim() : '' -const roundMatch = task.subject.match(/DISCUSS-(\d+)/) -const roundNumber = roundMatch ? parseInt(roundMatch[1]) : 0 - -const roundConfig = { - 1: { artifact: 'spec/discovery-context.json', type: 'json', outputFile: 'discuss-001-scope.md', perspectives: ['product', 'risk', 'coverage'], label: '范围讨论' }, - 2: { artifact: 'spec/product-brief.md', type: 'md', outputFile: 'discuss-002-brief.md', perspectives: ['product', 'technical', 'quality', 'coverage'], label: 'Brief评审' }, - 3: { artifact: 'spec/requirements/_index.md', type: 'md', outputFile: 'discuss-003-requirements.md', perspectives: ['quality', 'product', 'coverage'], label: '需求讨论' }, - 4: { artifact: 'spec/architecture/_index.md', type: 'md', outputFile: 'discuss-004-architecture.md', perspectives: ['technical', 'risk'], label: '架构讨论' }, - 5: { artifact: 'spec/epics/_index.md', type: 'md', outputFile: 'discuss-005-epics.md', perspectives: ['product', 'technical', 'quality', 'coverage'], label: 'Epics讨论' }, - 6: { artifact: 'spec/readiness-report.md', type: 'md', outputFile: 'discuss-006-final.md', perspectives: ['product', 'technical', 'quality', 'risk', 'coverage'], label: '最终签收' } -} - -const config = roundConfig[roundNumber] -// Load target artifact and prior discussion records for continuity -Bash(`mkdir -p ${sessionFolder}/discussions`) -``` - -### Phase 3: Multi-Perspective Critique - -**Delegate to**: `Read("commands/critique.md")` - -Launch parallel CLI analyses for each required perspective. See `commands/critique.md` for full implementation. - -### Phase 4: Consensus Synthesis - -```javascript -const synthesis = { - convergent_themes: [], - divergent_views: [], - action_items: [], - open_questions: [], - decisions: [], - risk_flags: [], - overall_sentiment: '', // positive/neutral/concerns/critical - consensus_reached: true // false if major unresolvable conflicts -} - -// Extract convergent themes (items mentioned positively by 2+ perspectives) -// Extract divergent views (items where perspectives conflict) -// Check coverage gaps from coverage perspective (if present) -const coverageResult = perspectiveResults.find(p => p.perspective === 'coverage') -if (coverageResult?.missing_requirements?.length > 0) { - synthesis.coverage_gaps = coverageResult.missing_requirements - synthesis.divergent_views.push({ - topic: 'requirement_coverage_gap', - description: `${coverageResult.missing_requirements.length} requirements from discovery-context not covered: ${coverageResult.missing_requirements.join(', ')}`, - severity: 'high', - source: 'coverage' - }) -} -// Check for unresolvable conflicts -const criticalDivergences = synthesis.divergent_views.filter(d => d.severity === 'high') -if (criticalDivergences.length > 0) synthesis.consensus_reached = false - -// Determine overall sentiment from average rating -// Generate discussion record markdown with all perspectives, convergence, divergence, action items - -Write(`${sessionFolder}/discussions/${config.outputFile}`, discussionRecord) -``` - -### Phase 5: Report to Coordinator - -```javascript -if (synthesis.consensus_reached) { - mcp__ccw-tools__team_msg({ - operation: "log", team: teamName, - from: "discussant", to: "coordinator", - type: "discussion_ready", - summary: `[discussant] ${config.label}讨论完成: ${synthesis.action_items.length}个行动项, ${synthesis.open_questions.length}个开放问题, 总体${synthesis.overall_sentiment}`, - ref: `${sessionFolder}/discussions/${config.outputFile}` - }) - - SendMessage({ - type: "message", - recipient: "coordinator", - content: `[discussant] ## 讨论结果: ${config.label} - -**Task**: ${task.subject} -**共识**: 已达成 -**总体评价**: ${synthesis.overall_sentiment} - -### 行动项 (${synthesis.action_items.length}) -${synthesis.action_items.map((item, i) => (i+1) + '. ' + item).join('\n') || '无'} - -### 开放问题 (${synthesis.open_questions.length}) -${synthesis.open_questions.map((q, i) => (i+1) + '. ' + q).join('\n') || '无'} - -### 讨论记录 -${sessionFolder}/discussions/${config.outputFile} - -共识已达成，可推进至下一阶段。`, - summary: `[discussant] ${config.label}共识达成: ${synthesis.action_items.length}行动项` - }) - - TaskUpdate({ taskId: task.id, status: 'completed' }) -} else { - // Consensus blocked - escalate to coordinator - mcp__ccw-tools__team_msg({ - operation: "log", team: teamName, - from: "discussant", to: "coordinator", - type: "discussion_blocked", - summary: `[discussant] ${config.label}讨论阻塞: ${criticalDivergences.length}个关键分歧需决策`, - data: { - reason: criticalDivergences.map(d => d.description).join('; '), - options: criticalDivergences.map(d => ({ label: d.topic, description: d.options?.join(' vs ') || d.description })) - } - }) - - SendMessage({ - type: "message", - recipient: "coordinator", - content: `[discussant] ## 讨论阻塞: ${config.label} - -**Task**: ${task.subject} -**状态**: 无法达成共识，需要 coordinator 介入 - -### 关键分歧 -${criticalDivergences.map((d, i) => (i+1) + '. **' + d.topic + '**: ' + d.description).join('\n\n')} - -请通过 AskUserQuestion 收集用户对分歧点的决策。`, - summary: `[discussant] ${config.label}阻塞: ${criticalDivergences.length}分歧` - }) - // Keep task in_progress, wait for coordinator resolution -} - -// Check for next DISCUSS task → back to Phase 1 -``` - -## Error Handling - -| Scenario | Resolution | -|----------|------------| -| No DISCUSS-* tasks available | Idle, wait for coordinator assignment | -| Target artifact not found | Notify coordinator with `[discussant]` tag, request prerequisite completion | -| CLI perspective analysis failure | Fallback to direct Claude analysis for that perspective | -| All CLI analyses fail | Generate basic discussion from direct reading | -| Consensus timeout (all perspectives diverge) | Escalate as discussion_blocked with `[discussant]` tag | -| Prior discussion records missing | Continue without continuity context | -| Session folder not found | Notify coordinator with `[discussant]` tag, request session path | -| Unexpected error | Log error via team_msg with `[discussant]` tag, report to coordinator | diff --git a/.claude/skills_lib/team-lifecycle-v2/roles/executor/commands/implement.md b/.claude/skills_lib/team-lifecycle-v2/roles/executor/commands/implement.md deleted file mode 100644 index 8078f6d9..00000000 --- a/.claude/skills_lib/team-lifecycle-v2/roles/executor/commands/implement.md +++ /dev/null @@ -1,356 +0,0 @@ -# Implement Command - -## Purpose -Multi-backend code implementation with progress tracking and batch execution support. - -## Execution Paths - -### Path 1: Simple Task + Agent Backend (Direct Edit) - -**Criteria**: -```javascript -function isSimpleTask(task) { - return task.description.length < 200 && - !task.description.includes("refactor") && - !task.description.includes("architecture") && - !task.description.includes("multiple files") -} -``` - -**Execution**: -```javascript -if (isSimpleTask(task) && executor === "agent") { - // Direct file edit without subagent overhead - const targetFile = task.metadata?.target_file - if (targetFile) { - const content = Read(targetFile) - const prompt = buildExecutionPrompt(task, plan, [task]) - - // Apply edit directly - Edit(targetFile, oldContent, newContent) - - return { - success: true, - files_modified: [targetFile], - method: "direct_edit" - } - } -} -``` - -### Path 2: Agent Backend (code-developer subagent) - -**Execution**: -```javascript -if (executor === "agent") { - const prompt = buildExecutionPrompt(task, plan, [task]) - - const result = Subagent({ - type: "code-developer", - prompt: prompt, - run_in_background: false // Synchronous execution - }) - - return { - success: result.success, - files_modified: result.files_modified || [], - method: "subagent" - } -} -``` - -### Path 3: Codex Backend (CLI) - -**Execution**: -```javascript -if (executor === "codex") { - const prompt = buildExecutionPrompt(task, plan, [task]) - - team_msg({ - to: "coordinator", - type: "progress_update", - task_id: task.task_id, - status: "executing_codex", - message: "Starting Codex implementation..." - }, "[executor]") - - const result = Bash( - `ccw cli -p "${escapePrompt(prompt)}" --tool codex --mode write --cd ${task.metadata?.working_dir || "."}`, - { run_in_background: true, timeout: 300000 } - ) - - // Wait for CLI completion via hook callback - return { - success: true, - files_modified: [], // Will be detected by git diff - method: "codex_cli" - } -} -``` - -### Path 4: Gemini Backend (CLI) - -**Execution**: -```javascript -if (executor === "gemini") { - const prompt = buildExecutionPrompt(task, plan, [task]) - - team_msg({ - to: "coordinator", - type: "progress_update", - task_id: task.task_id, - status: "executing_gemini", - message: "Starting Gemini implementation..." - }, "[executor]") - - const result = Bash( - `ccw cli -p "${escapePrompt(prompt)}" --tool gemini --mode write --cd ${task.metadata?.working_dir || "."}`, - { run_in_background: true, timeout: 300000 } - ) - - // Wait for CLI completion via hook callback - return { - success: true, - files_modified: [], // Will be detected by git diff - method: "gemini_cli" - } -} -``` - -## Prompt Building - -### Single Task Prompt - -```javascript -function buildExecutionPrompt(task, plan, tasks) { - const context = extractContextFromPlan(plan, task) - - return ` -# Implementation Task: ${task.task_id} - -## Task Description -${task.description} - -## Acceptance Criteria -${task.acceptance_criteria?.map((c, i) => `${i + 1}. ${c}`).join("\n") || "None specified"} - -## Context from Plan -${context} - -## Files to Modify -${task.metadata?.target_files?.join("\n") || "Auto-detect based on task"} - -## Constraints -- Follow existing code style and patterns -- Preserve backward compatibility -- Add appropriate error handling -- Include inline comments for complex logic -- Update related tests if applicable - -## Expected Output -- Modified files with implementation -- Brief summary of changes made -- Any assumptions or decisions made during implementation -`.trim() -} -``` - -### Batch Task Prompt - -```javascript -function buildBatchPrompt(tasks, plan) { - const taskDescriptions = tasks.map((task, i) => ` -### Task ${i + 1}: ${task.task_id} -**Description**: ${task.description} -**Acceptance Criteria**: -${task.acceptance_criteria?.map((c, j) => ` ${j + 1}. ${c}`).join("\n") || " None specified"} -**Target Files**: ${task.metadata?.target_files?.join(", ") || "Auto-detect"} - `).join("\n") - - return ` -# Batch Implementation: ${tasks.length} Tasks - -## Tasks to Implement -${taskDescriptions} - -## Context from Plan -${extractContextFromPlan(plan, tasks[0])} - -## Batch Execution Guidelines -- Implement tasks in the order listed -- Ensure each task's acceptance criteria are met -- Maintain consistency across all implementations -- Report any conflicts or dependencies discovered -- Follow existing code patterns and style - -## Expected Output -- All tasks implemented successfully -- Summary of changes per task -- Any cross-task considerations or conflicts -`.trim() -} -``` - -### Context Extraction - -```javascript -function extractContextFromPlan(plan, task) { - // Extract relevant sections from plan - const sections = [] - - // Architecture context - const archMatch = plan.match(/## Architecture[\s\S]*?(?=##|$)/) - if (archMatch) { - sections.push("### Architecture\n" + archMatch[0]) - } - - // Technical stack - const techMatch = plan.match(/## Technical Stack[\s\S]*?(?=##|$)/) - if (techMatch) { - sections.push("### Technical Stack\n" + techMatch[0]) - } - - // Related tasks context - const taskSection = plan.match(new RegExp(`${task.task_id}[\\s\\S]*?(?=IMPL-\\d+|$)`)) - if (taskSection) { - sections.push("### Task Context\n" + taskSection[0]) - } - - return sections.join("\n\n") || "No additional context available" -} -``` - -## Progress Tracking - -### Batch Progress Updates - -```javascript -function reportBatchProgress(batchIndex, totalBatches, currentTask) { - if (totalBatches > 1) { - team_msg({ - to: "coordinator", - type: "progress_update", - batch_index: batchIndex + 1, - total_batches: totalBatches, - current_task: currentTask.task_id, - message: `Processing batch ${batchIndex + 1}/${totalBatches}: ${currentTask.task_id}` - }, "[executor]") - } -} -``` - -### Long-Running Task Updates - -```javascript -function reportLongRunningTask(task, elapsedSeconds) { - if (elapsedSeconds > 60 && elapsedSeconds % 30 === 0) { - team_msg({ - to: "coordinator", - type: "progress_update", - task_id: task.task_id, - elapsed_seconds: elapsedSeconds, - message: `Still processing ${task.task_id} (${elapsedSeconds}s elapsed)...` - }, "[executor]") - } -} -``` - -## Utility Functions - -### Prompt Escaping - -```javascript -function escapePrompt(prompt) { - return prompt - .replace(/\\/g, "\\\\") - .replace(/"/g, '\\"') - .replace(/\n/g, "\\n") - .replace(/\$/g, "\\$") -} -``` - -### File Change Detection - -```javascript -function detectModifiedFiles() { - const gitDiff = Bash("git diff --name-only HEAD") - return gitDiff.stdout.split("\n").filter(f => f.trim()) -} -``` - -### Simple Task Detection - -```javascript -function isSimpleTask(task) { - const simpleIndicators = [ - task.description.length < 200, - !task.description.toLowerCase().includes("refactor"), - !task.description.toLowerCase().includes("architecture"), - !task.description.toLowerCase().includes("multiple files"), - !task.description.toLowerCase().includes("complex"), - task.metadata?.target_files?.length === 1 - ] - - return simpleIndicators.filter(Boolean).length >= 4 -} -``` - -## Error Recovery - -### Retry Logic - -```javascript -function executeWithRetry(task, executor, maxRetries = 3) { - let attempt = 0 - let lastError = null - - while (attempt < maxRetries) { - try { - const result = executeTask(task, executor) - if (result.success) { - return result - } - lastError = result.error - } catch (error) { - lastError = error.message - } - - attempt++ - if (attempt < maxRetries) { - team_msg({ - to: "coordinator", - type: "progress_update", - task_id: task.task_id, - message: `Retry attempt ${attempt}/${maxRetries} after error: ${lastError}` - }, "[executor]") - } - } - - return { - success: false, - error: lastError, - retry_count: maxRetries - } -} -``` - -### Backend Fallback - -```javascript -function executeWithFallback(task, primaryExecutor) { - const result = executeTask(task, primaryExecutor) - - if (!result.success && primaryExecutor !== "agent") { - team_msg({ - to: "coordinator", - type: "progress_update", - task_id: task.task_id, - message: `${primaryExecutor} failed, falling back to agent backend...` - }, "[executor]") - - return executeTask(task, "agent") - } - - return result -} -``` diff --git a/.claude/skills_lib/team-lifecycle-v2/roles/executor/role.md b/.claude/skills_lib/team-lifecycle-v2/roles/executor/role.md deleted file mode 100644 index a6f16a9d..00000000 --- a/.claude/skills_lib/team-lifecycle-v2/roles/executor/role.md +++ /dev/null @@ -1,324 +0,0 @@ -# Executor Role - -## 1. Role Identity - -- **Name**: executor -- **Task Prefix**: IMPL-* -- **Output Tag**: `[executor]` -- **Responsibility**: Load plan → Route to backend → Implement code → Self-validate → Report - -## 2. Role Boundaries - -### MUST -- Only process IMPL-* tasks -- Follow approved plan exactly -- Use declared execution backends (agent/codex/gemini) -- Self-validate all implementations (syntax + acceptance criteria) -- Tag all outputs with `[executor]` - -### MUST NOT -- Create tasks -- Contact other workers directly -- Modify plan files -- Skip self-validation -- Proceed without plan approval - -## 3. Message Types - -| Type | Direction | Purpose | Format | -|------|-----------|---------|--------| -| `task_request` | FROM coordinator | Receive IMPL-* task assignment | `{ type: "task_request", task_id, description }` | -| `task_complete` | TO coordinator | Report implementation success | `{ type: "task_complete", task_id, status: "success", files_modified, validation_results }` | -| `task_failed` | TO coordinator | Report implementation failure | `{ type: "task_failed", task_id, error, retry_count }` | -| `progress_update` | TO coordinator | Report batch progress | `{ type: "progress_update", task_id, batch_index, total_batches }` | - -## 4. Message Bus - -**Primary**: Use `team_msg` for all coordinator communication with `[executor]` tag: -```javascript -team_msg({ - to: "coordinator", - type: "task_complete", - task_id: "IMPL-001", - status: "success", - files_modified: ["src/auth.ts"], - validation_results: { syntax: "pass", acceptance: "pass" } -}, "[executor]") -``` - -**CLI Fallback**: When message bus unavailable, write to `.workflow/.team/messages/executor-{timestamp}.json` - -## 5. Toolbox - -### Available Commands -- `commands/implement.md` - Multi-backend code implementation with progress tracking - -### Subagent Capabilities -- `code-developer` - Synchronous agent execution for simple tasks and agent backend - -### CLI Capabilities -- `ccw cli --tool codex --mode write` - Codex backend implementation -- `ccw cli --tool gemini --mode write` - Gemini backend implementation - -## 6. Execution (5-Phase) - -### Phase 1: Task & Plan Loading - -**Task Discovery**: -```javascript -const tasks = Glob(".workflow/.team/tasks/IMPL-*.json") - .filter(task => task.status === "pending" && task.assigned_to === "executor") -``` - -**Plan Path Extraction**: -```javascript -const planPath = task.metadata?.plan_path || ".workflow/plan.md" -const plan = Read(planPath) -``` - -**Execution Backend Resolution**: -```javascript -function resolveExecutor(task, plan) { - // Priority 1: Task-level override - if (task.metadata?.executor) { - return task.metadata.executor // "agent" | "codex" | "gemini" - } - - // Priority 2: Plan-level default - const planMatch = plan.match(/Execution Backend:\s*(agent|codex|gemini)/i) - if (planMatch) { - return planMatch[1].toLowerCase() - } - - // Priority 3: Auto-select based on task complexity - const isSimple = task.description.length < 200 && - !task.description.includes("refactor") && - !task.description.includes("architecture") - - return isSimple ? "agent" : "codex" // Default: codex for complex, agent for simple -} -``` - -**Code Review Resolution**: -```javascript -function resolveCodeReview(task, plan) { - // Priority 1: Task-level override - if (task.metadata?.code_review !== undefined) { - return task.metadata.code_review // boolean - } - - // Priority 2: Plan-level default - const reviewMatch = plan.match(/Code Review:\s*(enabled|disabled)/i) - if (reviewMatch) { - return reviewMatch[1].toLowerCase() === "enabled" - } - - // Priority 3: Default based on task type - const criticalKeywords = ["auth", "security", "payment", "api", "database"] - const isCritical = criticalKeywords.some(kw => - task.description.toLowerCase().includes(kw) - ) - - return isCritical // Enable review for critical paths -} -``` - -### Phase 2: Task Grouping - -**Dependency-Based Batching**: -```javascript -function createBatches(tasks, plan) { - // Extract dependencies from plan - const dependencies = new Map() - const depRegex = /IMPL-(\d+).*depends on.*IMPL-(\d+)/gi - let match - while ((match = depRegex.exec(plan)) !== null) { - const [_, taskId, depId] = match - if (!dependencies.has(`IMPL-${taskId}`)) { - dependencies.set(`IMPL-${taskId}`, []) - } - dependencies.get(`IMPL-${taskId}`).push(`IMPL-${depId}`) - } - - // Topological sort for execution order - const batches = [] - const completed = new Set() - const remaining = new Set(tasks.map(t => t.task_id)) - - while (remaining.size > 0) { - const batch = [] - - for (const taskId of remaining) { - const deps = dependencies.get(taskId) || [] - const depsCompleted = deps.every(dep => completed.has(dep)) - - if (depsCompleted) { - batch.push(tasks.find(t => t.task_id === taskId)) - } - } - - if (batch.length === 0) { - // Circular dependency detected - throw new Error(`Circular dependency detected in remaining tasks: ${[...remaining].join(", ")}`) - } - - batches.push(batch) - batch.forEach(task => { - completed.add(task.task_id) - remaining.delete(task.task_id) - }) - } - - return batches -} -``` - -### Phase 3: Code Implementation - -**Delegate to Command**: -```javascript -const implementCommand = Read("commands/implement.md") -// Command handles: -// - buildExecutionPrompt (context + acceptance criteria) -// - buildBatchPrompt (multi-task batching) -// - 4 execution paths: simple+agent, agent, codex, gemini -// - Progress updates via team_msg -``` - -### Phase 4: Self-Validation - -**Syntax Check**: -```javascript -const syntaxCheck = Bash("tsc --noEmit", { timeout: 30000 }) -const syntaxPass = syntaxCheck.exitCode === 0 -``` - -**Acceptance Criteria Verification**: -```javascript -function verifyAcceptance(task, implementation) { - const criteria = task.acceptance_criteria || [] - const results = criteria.map(criterion => { - // Simple keyword matching for automated verification - const keywords = criterion.toLowerCase().match(/\b\w+\b/g) || [] - const matched = keywords.some(kw => - implementation.toLowerCase().includes(kw) - ) - return { criterion, matched, status: matched ? "pass" : "manual_review" } - }) - - const allPassed = results.every(r => r.status === "pass") - return { allPassed, results } -} -``` - -**Test File Detection**: -```javascript -function findAffectedTests(modifiedFiles) { - const testFiles = [] - - for (const file of modifiedFiles) { - const baseName = file.replace(/\.(ts|js|tsx|jsx)$/, "") - const testVariants = [ - `${baseName}.test.ts`, - `${baseName}.test.js`, - `${baseName}.spec.ts`, - `${baseName}.spec.js`, - `${file.replace(/^src\//, "tests/")}.test.ts`, - `${file.replace(/^src\//, "__tests__/")}.test.ts` - ] - - for (const variant of testVariants) { - if (Bash(`test -f ${variant}`).exitCode === 0) { - testFiles.push(variant) - } - } - } - - return testFiles -} -``` - -**Optional Code Review**: -```javascript -const codeReviewEnabled = resolveCodeReview(task, plan) - -if (codeReviewEnabled) { - const executor = resolveExecutor(task, plan) - - if (executor === "gemini") { - // Gemini Review: Use Gemini CLI for review - const reviewResult = Bash( - `ccw cli -p "Review implementation for: ${task.description}. Check: code quality, security, architecture compliance." --tool gemini --mode analysis`, - { run_in_background: true } - ) - } else if (executor === "codex") { - // Codex Review: Use Codex CLI review mode - const reviewResult = Bash( - `ccw cli --tool codex --mode review --uncommitted`, - { run_in_background: true } - ) - } - - // Wait for review results and append to validation -} -``` - -### Phase 5: Report to Coordinator - -**Success Report**: -```javascript -team_msg({ - to: "coordinator", - type: "task_complete", - task_id: task.task_id, - status: "success", - files_modified: modifiedFiles, - validation_results: { - syntax: syntaxPass ? "pass" : "fail", - acceptance: acceptanceResults.allPassed ? "pass" : "manual_review", - tests_found: affectedTests.length, - code_review: codeReviewEnabled ? "completed" : "skipped" - }, - execution_backend: executor, - timestamp: new Date().toISOString() -}, "[executor]") -``` - -**Failure Report**: -```javascript -team_msg({ - to: "coordinator", - type: "task_failed", - task_id: task.task_id, - error: errorMessage, - retry_count: task.retry_count || 0, - validation_results: { - syntax: syntaxPass ? "pass" : "fail", - acceptance: "not_verified" - }, - timestamp: new Date().toISOString() -}, "[executor]") -``` - -## 7. Error Handling - -| Error Type | Recovery Strategy | Escalation | -|------------|-------------------|------------| -| Syntax errors | Retry with error context (max 3 attempts) | Report to coordinator after 3 failures | -| Missing dependencies | Request dependency resolution from coordinator | Immediate escalation | -| Backend unavailable | Fallback to agent backend | Report backend switch | -| Validation failure | Include validation details in report | Manual review required | -| Circular dependencies | Abort batch, report dependency graph | Immediate escalation | - -## 8. Execution Backends - -| Backend | Tool | Invocation | Mode | Use Case | -|---------|------|------------|------|----------| -| **agent** | code-developer | Subagent call (synchronous) | N/A | Simple tasks, direct edits | -| **codex** | ccw cli | `ccw cli --tool codex --mode write` | write | Complex tasks, architecture changes | -| **gemini** | ccw cli | `ccw cli --tool gemini --mode write` | write | Alternative backend, analysis-heavy tasks | - -**Backend Selection Logic**: -1. Task metadata override → Use specified backend -2. Plan default → Use plan-level backend -3. Auto-select → Simple tasks use agent, complex use codex diff --git a/.claude/skills_lib/team-lifecycle-v2/roles/explorer/role.md b/.claude/skills_lib/team-lifecycle-v2/roles/explorer/role.md deleted file mode 100644 index 90e369f8..00000000 --- a/.claude/skills_lib/team-lifecycle-v2/roles/explorer/role.md +++ /dev/null @@ -1,301 +0,0 @@ -# Explorer Role - -专职代码搜索与模式发现。服务角色，被 analyst/planner/executor/discussant 按需调用。 - -## 1. Role Identity - -- **Name**: explorer -- **Task Prefix**: EXPLORE-* -- **Output Tag**: `[explorer]` -- **Role Type**: Service（按需调用，不占主链路位置） -- **Responsibility**: Parse request → Multi-strategy search → Dependency trace → Package results → Report - -## 2. Role Boundaries - -### MUST -- Only process EXPLORE-* tasks -- Output structured JSON for downstream consumption -- Use priority-ordered search strategies (ACE → Grep → cli-explore-agent) -- Tag all outputs with `[explorer]` -- Cache results in `{session}/explorations/` for cross-role reuse - -### MUST NOT -- Create tasks -- Contact other workers directly -- Modify any source code files -- Execute analysis, planning, or implementation -- Make architectural decisions (only discover patterns) - -## 3. Message Types - -| Type | Direction | Purpose | Format | -|------|-----------|---------|--------| -| `explore_ready` | TO coordinator | Search complete | `{ type: "explore_ready", task_id, file_count, pattern_count, output_path }` | -| `explore_progress` | TO coordinator | Multi-angle progress | `{ type: "explore_progress", task_id, angle, status }` | -| `task_failed` | TO coordinator | Search failure | `{ type: "task_failed", task_id, error, fallback_used }` | - -## 4. Message Bus - -**Primary**: Use `team_msg` for all coordinator communication with `[explorer]` tag: -```javascript -team_msg({ - to: "coordinator", - type: "explore_ready", - task_id: "EXPLORE-001", - file_count: 15, - pattern_count: 3, - output_path: `${sessionFolder}/explorations/explore-001.json` -}, "[explorer]") -``` - -**CLI Fallback**: When message bus unavailable: -```bash -ccw team log --team "${teamName}" --from "explorer" --to "coordinator" --type "explore_ready" --summary "[explorer] 15 files, 3 patterns" --json -``` - -## 5. Toolbox - -### Available Commands -- None (inline execution, search logic is straightforward) - -### Search Tools (priority order) - -| Tool | Priority | Use Case | -|------|----------|----------| -| `mcp__ace-tool__search_context` | P0 | Semantic code search | -| `Grep` / `Glob` | P1 | Pattern matching, file discovery | -| `Read` | P1 | File content reading | -| `Bash` (rg, find) | P2 | Structured search fallback | -| `WebSearch` | P3 | External docs/best practices | - -### Subagent Capabilities -- `cli-explore-agent` — Deep multi-angle codebase exploration - -## 6. Execution (5-Phase) - -### Phase 1: Task Discovery & Request Parsing - -```javascript -const tasks = TaskList() -const myTasks = tasks.filter(t => - t.subject.startsWith('EXPLORE-') && - t.owner === 'explorer' && - t.status === 'pending' && - t.blockedBy.length === 0 -) -if (myTasks.length === 0) return -const task = TaskGet({ taskId: myTasks[0].id }) -TaskUpdate({ taskId: task.id, status: 'in_progress' }) - -// Parse structured request from task description -const sessionFolder = task.description.match(/Session:\s*([^\n]+)/)?.[1]?.trim() -const exploreMode = task.description.match(/Mode:\s*([^\n]+)/)?.[1]?.trim() || 'codebase' -const angles = (task.description.match(/Angles:\s*([^\n]+)/)?.[1] || 'general').split(',').map(a => a.trim()) -const keywords = (task.description.match(/Keywords:\s*([^\n]+)/)?.[1] || '').split(',').map(k => k.trim()).filter(Boolean) -const requester = task.description.match(/Requester:\s*([^\n]+)/)?.[1]?.trim() || 'coordinator' - -const outputDir = sessionFolder ? `${sessionFolder}/explorations` : '.workflow/.tmp' -Bash(`mkdir -p "${outputDir}"`) -``` - -### Phase 2: Multi-Strategy Search - -```javascript -const findings = { - relevant_files: [], // { path, rationale, role, discovery_source, key_symbols } - patterns: [], // { name, description, files } - dependencies: [], // { file, imports[] } - external_refs: [], // { keyword, results[] } - _metadata: { angles, mode: exploreMode, requester, timestamp: new Date().toISOString() } -} - -// === Strategy 1: ACE Semantic Search (P0) === -if (exploreMode !== 'external') { - for (const kw of keywords) { - try { - const results = mcp__ace-tool__search_context({ project_root_path: '.', query: kw }) - // Deduplicate and add to findings.relevant_files with discovery_source: 'ace-search' - } catch { /* ACE unavailable, fall through */ } - } -} - -// === Strategy 2: Grep Pattern Scan (P1) === -if (exploreMode !== 'external') { - for (const kw of keywords) { - // Find imports/exports/definitions - const defResults = Grep({ - pattern: `(class|function|const|export|interface|type)\\s+.*${kw}`, - glob: '*.{ts,tsx,js,jsx,py,go,rs}', - '-n': true, output_mode: 'content' - }) - // Add to findings with discovery_source: 'grep-scan' - } -} - -// === Strategy 3: Dependency Tracing === -if (exploreMode !== 'external') { - for (const file of findings.relevant_files.slice(0, 10)) { - try { - const content = Read(file.path) - const imports = (content.match(/from\s+['"]([^'"]+)['"]/g) || []) - .map(i => i.match(/['"]([^'"]+)['"]/)?.[1]).filter(Boolean) - if (imports.length > 0) { - findings.dependencies.push({ file: file.path, imports }) - } - } catch {} - } -} - -// === Strategy 4: Deep Exploration (multi-angle, via cli-explore-agent) === -if (angles.length > 1 && exploreMode !== 'external') { - for (const angle of angles) { - Task({ - subagent_type: "cli-explore-agent", - run_in_background: false, - description: `Explore: ${angle}`, - prompt: `## Exploration: ${angle} angle -Keywords: ${keywords.join(', ')} - -## Steps -1. rg -l "${keywords[0]}" --type-add 'code:*.{ts,tsx,js,py,go,rs}' --type code -2. Read .workflow/project-tech.json (if exists) -3. Focus on ${angle} perspective - -## Output -Write to: ${outputDir}/exploration-${angle}.json -Schema: { relevant_files[], patterns[], dependencies[] }` - }) - // Merge angle results into main findings - try { - const angleData = JSON.parse(Read(`${outputDir}/exploration-${angle}.json`)) - findings.relevant_files.push(...(angleData.relevant_files || [])) - findings.patterns.push(...(angleData.patterns || [])) - } catch {} - } -} - -// === Strategy 5: External Search (P3) === -if (exploreMode === 'external' || exploreMode === 'hybrid') { - for (const kw of keywords.slice(0, 3)) { - try { - const results = WebSearch({ query: `${kw} best practices documentation` }) - findings.external_refs.push({ keyword: kw, results }) - } catch {} - } -} - -// Deduplicate relevant_files by path -const seen = new Set() -findings.relevant_files = findings.relevant_files.filter(f => { - if (seen.has(f.path)) return false - seen.add(f.path) - return true -}) -``` - -### Phase 3: Wisdom Contribution - -```javascript -// If wisdom directory exists, contribute discovered patterns -if (sessionFolder) { - try { - const conventionsPath = `${sessionFolder}/wisdom/conventions.md` - const existing = Read(conventionsPath) - if (findings.patterns.length > 0) { - const newPatterns = findings.patterns - .map(p => `- ${p.name}: ${p.description || ''}`) - .join('\n') - Edit({ - file_path: conventionsPath, - old_string: '', - new_string: `\n${newPatterns}` - }) - } - } catch {} // wisdom not initialized -} -``` - -### Phase 4: Package Results - -```javascript -const outputPath = `${outputDir}/explore-${task.subject.replace(/[^a-zA-Z0-9-]/g, '-').toLowerCase()}.json` -Write(outputPath, JSON.stringify(findings, null, 2)) -``` - -### Phase 5: Report to Coordinator - -```javascript -const summary = `${findings.relevant_files.length} files, ${findings.patterns.length} patterns, ${findings.dependencies.length} deps` - -mcp__ccw-tools__team_msg({ - operation: "log", team: teamName, - from: "explorer", to: "coordinator", - type: "explore_ready", - summary: `[explorer] EXPLORE complete: ${summary}`, - ref: outputPath -}) - -SendMessage({ - type: "message", - recipient: "coordinator", - content: `[explorer] ## Exploration Results - -**Task**: ${task.subject} -**Mode**: ${exploreMode} | **Angles**: ${angles.join(', ')} | **Requester**: ${requester} - -### Files: ${findings.relevant_files.length} -${findings.relevant_files.slice(0, 8).map(f => `- \`${f.path}\` (${f.role}) — ${f.rationale}`).join('\n')} - -### Patterns: ${findings.patterns.length} -${findings.patterns.slice(0, 5).map(p => `- ${p.name}: ${p.description || ''}`).join('\n') || 'None'} - -### Output: ${outputPath}`, - summary: `[explorer] ${summary}` -}) - -TaskUpdate({ taskId: task.id, status: 'completed' }) -// Check for next EXPLORE task → back to Phase 1 -``` - -## 7. Coordinator Integration - -Explorer 是服务角色，coordinator 在以下场景按需创建 EXPLORE-* 任务： - -| Trigger | Task Example | Requester | -|---------|-------------|-----------| -| RESEARCH-001 需要代码库上下文 | `EXPLORE-001: 代码库上下文搜索` | analyst | -| PLAN-001 需要多角度探索 | `EXPLORE-002: 实现相关代码探索` | planner | -| DISCUSS-004 需要外部最佳实践 | `EXPLORE-003: 外部文档搜索` | discussant | -| IMPL-001 遇到未知代码 | `EXPLORE-004: 依赖追踪` | executor | - -**Task Description Template**: -``` -搜索描述 - -Session: {sessionFolder} -Mode: codebase|external|hybrid -Angles: architecture,patterns,dependencies -Keywords: auth,middleware,session -Requester: analyst -``` - -## 8. Result Caching - -``` -{sessionFolder}/explorations/ -├── explore-explore-001-*.json # Consolidated results -├── exploration-architecture.json # Angle-specific (from cli-explore-agent) -└── exploration-patterns.json -``` - -后续角色 Phase 2 可直接读取已有探索结果，避免重复搜索。 - -## 9. Error Handling - -| Error Type | Recovery Strategy | Escalation | -|------------|-------------------|------------| -| ACE unavailable | Fallback to Grep + rg | Continue with degraded results | -| cli-explore-agent failure | Fallback to direct search | Report partial results | -| No results found | Report empty, suggest broader keywords | Coordinator decides | -| Web search fails | Skip external refs | Continue with codebase results | -| Session folder missing | Use .workflow/.tmp | Notify coordinator | diff --git a/.claude/skills_lib/team-lifecycle-v2/roles/fe-developer/role.md b/.claude/skills_lib/team-lifecycle-v2/roles/fe-developer/role.md deleted file mode 100644 index 540ef26b..00000000 --- a/.claude/skills_lib/team-lifecycle-v2/roles/fe-developer/role.md +++ /dev/null @@ -1,410 +0,0 @@ -# Role: fe-developer - -前端开发。消费计划/架构产出，实现前端组件、页面、样式代码。 - -## Role Identity - -- **Name**: `fe-developer` -- **Task Prefix**: `DEV-FE-*` -- **Output Tag**: `[fe-developer]` -- **Role Type**: Pipeline（前端子流水线 worker） -- **Responsibility**: Context loading → Design token consumption → Component implementation → Report - -## Role Boundaries - -### MUST -- 仅处理 `DEV-FE-*` 前缀的任务 -- 所有输出带 `[fe-developer]` 标识 -- 仅通过 SendMessage 与 coordinator 通信 -- 遵循已有设计令牌和组件规范（如存在） -- 生成可访问性合规的前端代码（语义 HTML、ARIA 属性、键盘导航） -- 遵循项目已有的前端技术栈和约定 - -### MUST NOT -- ❌ 修改后端代码或 API 接口 -- ❌ 直接与其他 worker 通信 -- ❌ 为其他角色创建任务 -- ❌ 跳过设计令牌/规范检查（如存在） -- ❌ 引入未经架构审查的新前端依赖 - -## Message Types - -| Type | Direction | Trigger | Description | -|------|-----------|---------|-------------| -| `dev_fe_complete` | fe-developer → coordinator | Implementation done | 前端实现完成 | -| `dev_fe_progress` | fe-developer → coordinator | Long task progress | 进度更新 | -| `error` | fe-developer → coordinator | Implementation failure | 实现失败 | - -## Message Bus - -每次 SendMessage **前**，必须调用 `mcp__ccw-tools__team_msg` 记录： - -```javascript -mcp__ccw-tools__team_msg({ - operation: "log", team: teamName, - from: "fe-developer", to: "coordinator", - type: "dev_fe_complete", - summary: "[fe-developer] DEV-FE complete: 3 components, 1 page", - ref: outputPath -}) -``` - -### CLI 回退 - -```javascript -Bash(`ccw team log --team "${teamName}" --from "fe-developer" --to "coordinator" --type "dev_fe_complete" --summary "[fe-developer] DEV-FE complete" --ref "${outputPath}" --json`) -``` - -## Toolbox - -### Available Commands -- None (inline execution — implementation delegated to subagent) - -### Subagent Capabilities - -| Agent Type | Purpose | -|------------|---------| -| `code-developer` | 组件/页面代码实现 | - -### CLI Capabilities - -| CLI Tool | Mode | Purpose | -|----------|------|---------| -| `ccw cli --tool gemini --mode write` | write | 前端代码生成 | - -## Execution (5-Phase) - -### Phase 1: Task Discovery - -```javascript -const tasks = TaskList() -const myTasks = tasks.filter(t => - t.subject.startsWith('DEV-FE-') && - t.owner === 'fe-developer' && - t.status === 'pending' && - t.blockedBy.length === 0 -) -if (myTasks.length === 0) return -const task = TaskGet({ taskId: myTasks[0].id }) -TaskUpdate({ taskId: task.id, status: 'in_progress' }) -``` - -### Phase 2: Context Loading - -```javascript -const sessionFolder = task.description.match(/Session:\s*([^\n]+)/)?.[1]?.trim() - -// Load plan context -let plan = null -try { plan = JSON.parse(Read(`${sessionFolder}/plan/plan.json`)) } catch {} - -// Load design tokens (if architect produced them) -let designTokens = null -try { designTokens = JSON.parse(Read(`${sessionFolder}/architecture/design-tokens.json`)) } catch {} - -// Load design intelligence (from analyst via ui-ux-pro-max) -let designIntel = {} -try { designIntel = JSON.parse(Read(`${sessionFolder}/analysis/design-intelligence.json`)) } catch {} - -// Load component specs (if available) -let componentSpecs = [] -try { - const specFiles = Glob({ pattern: `${sessionFolder}/architecture/component-specs/*.md` }) - componentSpecs = specFiles.map(f => ({ path: f, content: Read(f) })) -} catch {} - -// Load shared memory (cross-role state) -let sharedMemory = {} -try { sharedMemory = JSON.parse(Read(`${sessionFolder}/shared-memory.json`)) } catch {} - -// Load wisdom -let wisdom = {} -if (sessionFolder) { - try { wisdom.conventions = Read(`${sessionFolder}/wisdom/conventions.md`) } catch {} - try { wisdom.decisions = Read(`${sessionFolder}/wisdom/decisions.md`) } catch {} -} - -// Extract design constraints from design intelligence -const antiPatterns = designIntel.recommendations?.anti_patterns || [] -const implementationChecklist = designIntel.design_system?.implementation_checklist || [] -const stackGuidelines = designIntel.stack_guidelines || {} - -// Detect frontend tech stack -let techStack = {} -try { techStack = JSON.parse(Read('.workflow/project-tech.json')) } catch {} -const feTech = detectFrontendStack(techStack) -// Override with design intelligence detection if available -if (designIntel.detected_stack) { - const diStack = designIntel.detected_stack - if (['react', 'nextjs', 'vue', 'svelte', 'nuxt'].includes(diStack)) feTech.framework = diStack -} - -function detectFrontendStack(tech) { - const deps = tech?.dependencies || {} - const stack = { framework: 'html', styling: 'css', ui_lib: null } - if (deps.react || deps['react-dom']) stack.framework = 'react' - if (deps.vue) stack.framework = 'vue' - if (deps.svelte) stack.framework = 'svelte' - if (deps.next) stack.framework = 'nextjs' - if (deps.nuxt) stack.framework = 'nuxt' - if (deps.tailwindcss) stack.styling = 'tailwind' - if (deps['@shadcn/ui'] || deps['shadcn-ui']) stack.ui_lib = 'shadcn' - if (deps['@mui/material']) stack.ui_lib = 'mui' - if (deps['antd']) stack.ui_lib = 'antd' - return stack -} -``` - -### Phase 3: Frontend Implementation - -#### Step 1: Generate Design Token CSS (if tokens available) - -```javascript -if (designTokens && task.description.includes('Scope: tokens') || task.description.includes('Scope: full')) { - // Convert design-tokens.json to CSS custom properties - let cssVars = ':root {\n' - - // Colors - if (designTokens.color) { - for (const [name, token] of Object.entries(designTokens.color)) { - const value = typeof token.$value === 'object' ? token.$value.light : token.$value - cssVars += ` --color-${name}: ${value};\n` - } - } - - // Typography - if (designTokens.typography?.['font-family']) { - for (const [name, token] of Object.entries(designTokens.typography['font-family'])) { - const value = Array.isArray(token.$value) ? token.$value.join(', ') : token.$value - cssVars += ` --font-${name}: ${value};\n` - } - } - if (designTokens.typography?.['font-size']) { - for (const [name, token] of Object.entries(designTokens.typography['font-size'])) { - cssVars += ` --text-${name}: ${token.$value};\n` - } - } - - // Spacing, border-radius, shadow, transition - for (const category of ['spacing', 'border-radius', 'shadow', 'transition']) { - const prefix = { spacing: 'space', 'border-radius': 'radius', shadow: 'shadow', transition: 'duration' }[category] - if (designTokens[category]) { - for (const [name, token] of Object.entries(designTokens[category])) { - cssVars += ` --${prefix}-${name}: ${token.$value};\n` - } - } - } - - cssVars += '}\n' - - // Dark mode overrides - if (designTokens.color) { - const darkOverrides = Object.entries(designTokens.color) - .filter(([, token]) => typeof token.$value === 'object' && token.$value.dark) - if (darkOverrides.length > 0) { - cssVars += '\n@media (prefers-color-scheme: dark) {\n :root {\n' - for (const [name, token] of darkOverrides) { - cssVars += ` --color-${name}: ${token.$value.dark};\n` - } - cssVars += ' }\n}\n' - } - } - - Bash(`mkdir -p src/styles`) - Write('src/styles/tokens.css', cssVars) -} -``` - -#### Step 2: Implement Components - -```javascript -const taskId = task.subject.match(/DEV-FE-(\d+)/)?.[0] -const taskDetail = plan?.task_ids?.includes(taskId) - ? JSON.parse(Read(`${sessionFolder}/plan/.task/${taskId}.json`)) - : { title: task.subject, description: task.description, files: [] } - -const isSimple = (taskDetail.files || []).length <= 3 && - !task.description.includes('system') && - !task.description.includes('多组件') - -if (isSimple) { - Task({ - subagent_type: "code-developer", - run_in_background: false, - description: `Frontend implementation: ${taskDetail.title}`, - prompt: `## Frontend Implementation - -Task: ${taskDetail.title} -Description: ${taskDetail.description} - -${designTokens ? `## Design Tokens\nImport from: src/styles/tokens.css\nUse CSS custom properties (var(--color-primary), var(--space-md), etc.)\n${JSON.stringify(designTokens, null, 2).substring(0, 1000)}` : ''} -${componentSpecs.length > 0 ? `## Component Specs\n${componentSpecs.map(s => s.content.substring(0, 500)).join('\n---\n')}` : ''} - -## Tech Stack -- Framework: ${feTech.framework} -- Styling: ${feTech.styling} -${feTech.ui_lib ? `- UI Library: ${feTech.ui_lib}` : ''} - -## Stack-Specific Guidelines -${JSON.stringify(stackGuidelines, null, 2).substring(0, 500)} - -## Implementation Checklist (MUST verify each item) -${implementationChecklist.map(item => `- [ ] ${item}`).join('\n') || '- [ ] Semantic HTML\n- [ ] Keyboard accessible\n- [ ] Responsive layout\n- [ ] Dark mode support'} - -## Anti-Patterns to AVOID -${antiPatterns.map(p => `- ❌ ${p}`).join('\n') || 'None specified'} - -## Coding Standards -- Use design token CSS variables, never hardcode colors/spacing -- All interactive elements must have cursor: pointer -- Transitions: 150-300ms (use var(--duration-normal)) -- Text contrast: minimum 4.5:1 ratio -- Include focus-visible styles for keyboard navigation -- Support prefers-reduced-motion -- Responsive: mobile-first with md/lg breakpoints -- No emoji as functional icons - -## Files to modify/create -${(taskDetail.files || []).map(f => `- ${f.path}: ${f.change}`).join('\n') || 'Determine from task description'} - -## Conventions -${wisdom.conventions || 'Follow project existing patterns'}` - }) -} else { - Bash({ - command: `ccw cli -p "PURPOSE: Implement frontend components for '${taskDetail.title}' -TASK: ${taskDetail.description} -MODE: write -CONTEXT: @src/**/*.{tsx,jsx,vue,svelte,css,scss,html} @public/**/* -EXPECTED: Production-ready frontend code with accessibility, responsive design, design token usage -CONSTRAINTS: Framework=${feTech.framework}, Styling=${feTech.styling}${feTech.ui_lib ? ', UI=' + feTech.ui_lib : ''} -ANTI-PATTERNS: ${antiPatterns.join(', ') || 'None'} -CHECKLIST: ${implementationChecklist.join(', ') || 'Semantic HTML, keyboard accessible, responsive, dark mode'}" --tool gemini --mode write --rule development-implement-component-ui`, - run_in_background: true - }) -} -``` - -### Phase 4: Self-Validation + Wisdom + Shared Memory - -```javascript -// === Self-Validation (pre-QA check) === -const implementedFiles = Glob({ pattern: 'src/**/*.{tsx,jsx,vue,svelte,html,css}' }) -const selfCheck = { passed: [], failed: [] } - -for (const file of implementedFiles.slice(0, 20)) { - try { - const content = Read(file) - - // Check: no hardcoded colors (hex outside tokens.css) - if (file !== 'src/styles/tokens.css' && /#[0-9a-fA-F]{3,8}/.test(content)) { - selfCheck.failed.push({ file, check: 'hardcoded-color', message: 'Hardcoded color — use var(--color-*)' }) - } - - // Check: cursor-pointer on interactive elements - if (/button| ({ path: f, status: 'implemented' })) - Write(`${sessionFolder}/shared-memory.json`, JSON.stringify(sharedMemory, null, 2)) - } catch {} -} -``` - -### Phase 5: Report to Coordinator - -```javascript -const changedFiles = Bash(`git diff --name-only HEAD 2>/dev/null || echo "unknown"`) - .split('\n').filter(Boolean) -const feFiles = changedFiles.filter(f => - /\.(tsx|jsx|vue|svelte|css|scss|html)$/.test(f) -) - -const resultStatus = selfCheck.failed.length === 0 ? 'complete' : 'complete_with_warnings' - -mcp__ccw-tools__team_msg({ - operation: "log", team: teamName, - from: "fe-developer", to: "coordinator", - type: "dev_fe_complete", - summary: `[fe-developer] DEV-FE complete: ${feFiles.length} files, self-check: ${selfCheck.failed.length} issues`, - ref: sessionFolder -}) - -SendMessage({ - type: "message", - recipient: "coordinator", - content: `[fe-developer] ## Frontend Implementation Complete - -**Task**: ${task.subject} -**Status**: ${resultStatus} -**Framework**: ${feTech.framework} | **Styling**: ${feTech.styling} -**Design Intelligence**: ${designIntel._source || 'not available'} - -### Files Modified -${feFiles.slice(0, 10).map(f => `- \`${f}\``).join('\n') || 'See git diff'} - -### Design Token Usage -${designTokens ? 'Applied design tokens from architecture → src/styles/tokens.css' : 'No design tokens available — used project defaults'} - -### Self-Validation -${selfCheck.failed.length === 0 ? '✅ All checks passed' : `⚠️ ${selfCheck.failed.length} issues:\n${selfCheck.failed.slice(0, 5).map(f => `- [${f.check}] ${f.file}: ${f.message}`).join('\n')}`} - -### Accessibility -- Semantic HTML structure -- ARIA attributes applied -- Keyboard navigation supported -- Focus-visible styles included`, - summary: `[fe-developer] DEV-FE complete: ${feFiles.length} files` -}) - -TaskUpdate({ taskId: task.id, status: 'completed' }) -// Check for next DEV-FE task → back to Phase 1 -``` - -## Error Handling - -| Scenario | Resolution | -|----------|------------| -| No DEV-FE-* tasks | Idle, wait for coordinator | -| Design tokens not found | Use project defaults, note in report | -| Component spec missing | Implement from task description only | -| Tech stack undetected | Default to HTML + CSS, ask coordinator | -| Subagent failure | Fallback to CLI write mode | -| Build/lint errors | Report to coordinator for QA-FE review | diff --git a/.claude/skills_lib/team-lifecycle-v2/roles/fe-qa/commands/pre-delivery-checklist.md b/.claude/skills_lib/team-lifecycle-v2/roles/fe-qa/commands/pre-delivery-checklist.md deleted file mode 100644 index b8c9e4b0..00000000 --- a/.claude/skills_lib/team-lifecycle-v2/roles/fe-qa/commands/pre-delivery-checklist.md +++ /dev/null @@ -1,116 +0,0 @@ -# Command: pre-delivery-checklist - -> 最终交付前的 CSS 级别精准检查清单，融合 ui-ux-pro-max Pre-Delivery Checklist 和 ux-guidelines Do/Don't 规则。 - -## When to Use - -- Phase 3 of fe-qa role, Dimension 5: Pre-Delivery -- Final review or code-review type tasks - -## Strategy - -### Delegation Mode - -**Mode**: Direct (inline pattern matching in fe-qa Phase 3) - -## Checklist Items - -### Accessibility - -| # | Check | Pattern | Severity | Do | Don't | -|---|-------|---------|----------|-----|-------| -| 1 | Images have alt text | `500ms or <100ms transitions | -| 9 | Loading states | Async ops without loading indicator | MEDIUM | Show skeleton/spinner during fetch | Leave blank screen while loading | -| 10 | Error states | Async ops without error handling | HIGH | Show user-friendly error message | Silently fail or show raw error | - -### Design Compliance - -| # | Check | Pattern | Severity | Do | Don't | -|---|-------|---------|----------|-----|-------| -| 11 | No hardcoded colors | Hex values outside tokens.css | HIGH | Use var(--color-*) tokens | Hardcode #hex values | -| 12 | No hardcoded spacing | px values for margin/padding | MEDIUM | Use var(--space-*) tokens | Hardcode pixel values | -| 13 | No emoji as icons | Unicode emoji in UI | HIGH | Use proper SVG/icon library | Use emoji for functional icons | -| 14 | Dark mode support | No prefers-color-scheme | MEDIUM | Support light/dark themes | Design for light mode only | - -### Layout - -| # | Check | Pattern | Severity | Do | Don't | -|---|-------|---------|----------|-----|-------| -| 15 | Responsive breakpoints | No md:/lg:/@media | MEDIUM | Mobile-first responsive design | Desktop-only layout | -| 16 | No horizontal scroll | Fixed widths > viewport | HIGH | Use relative/fluid widths | Set fixed pixel widths on containers | - -## Execution - -```javascript -function runPreDeliveryChecklist(fileContents) { - const results = { passed: 0, failed: 0, items: [] } - - const checks = [ - { id: 1, check: "Images have alt text", test: (c) => /]*alt=/.test(c), severity: 'CRITICAL' }, - { id: 7, check: "cursor-pointer on clickable", test: (c) => /button|onClick/.test(c) && !/cursor-pointer/.test(c), severity: 'MEDIUM' }, - { id: 11, check: "No hardcoded colors", test: (c, f) => f !== 'src/styles/tokens.css' && /#[0-9a-fA-F]{6}/.test(c), severity: 'HIGH' }, - { id: 13, check: "No emoji as icons", test: (c) => /[\u{1F300}-\u{1F9FF}]/u.test(c), severity: 'HIGH' }, - { id: 14, check: "Dark mode support", test: (c) => !/prefers-color-scheme|dark:|\.dark/.test(c), severity: 'MEDIUM', global: true }, - { id: 15, check: "Responsive breakpoints", test: (c) => !/md:|lg:|@media.*min-width/.test(c), severity: 'MEDIUM', global: true } - ] - - // Per-file checks - for (const [file, content] of Object.entries(fileContents)) { - for (const check of checks.filter(c => !c.global)) { - if (check.test(content, file)) { - results.failed++ - results.items.push({ ...check, file, status: 'FAIL' }) - } else { - results.passed++ - results.items.push({ ...check, file, status: 'PASS' }) - } - } - } - - // Global checks (across all content) - const allContent = Object.values(fileContents).join('\n') - for (const check of checks.filter(c => c.global)) { - if (check.test(allContent)) { - results.failed++ - results.items.push({ ...check, file: 'global', status: 'FAIL' }) - } else { - results.passed++ - results.items.push({ ...check, file: 'global', status: 'PASS' }) - } - } - - return results -} -``` - -## Output Format - -``` -## Pre-Delivery Checklist Results -- Passed: X / Y -- Failed: Z - -### Failed Items -- [CRITICAL] #1 Images have alt text — src/components/Hero.tsx -- [HIGH] #11 No hardcoded colors — src/styles/custom.css -``` - -## Error Handling - -| Scenario | Resolution | -|----------|------------| -| No files to check | Report empty checklist, score 10/10 | -| File read error | Skip file, note in report | -| Regex error | Skip check, note in report | diff --git a/.claude/skills_lib/team-lifecycle-v2/roles/fe-qa/role.md b/.claude/skills_lib/team-lifecycle-v2/roles/fe-qa/role.md deleted file mode 100644 index 6e57627d..00000000 --- a/.claude/skills_lib/team-lifecycle-v2/roles/fe-qa/role.md +++ /dev/null @@ -1,510 +0,0 @@ -# Role: fe-qa - -前端质量保证。5 维度代码审查 + Generator-Critic 循环确保前端代码质量。融合 ui-ux-pro-max 的 Pre-Delivery Checklist、ux-guidelines Do/Don't 规则、行业反模式库。 - -## Role Identity - -- **Name**: `fe-qa` -- **Task Prefix**: `QA-FE-*` -- **Output Tag**: `[fe-qa]` -- **Role Type**: Pipeline（前端子流水线 worker） -- **Responsibility**: Context loading → Multi-dimension review → GC feedback → Report - -## Role Boundaries - -### MUST -- 仅处理 `QA-FE-*` 前缀的任务 -- 所有输出带 `[fe-qa]` 标识 -- 仅通过 SendMessage 与 coordinator 通信 -- 执行 5 维度审查（代码质量、可访问性、设计合规、UX 最佳实践、Pre-Delivery） -- 提供可操作的修复建议（Do/Don't 格式） -- 支持 Generator-Critic 循环（最多 2 轮） -- 加载 design-intelligence.json 用于行业反模式检查 - -### MUST NOT -- ❌ 直接修改源代码（仅提供审查意见） -- ❌ 直接与其他 worker 通信 -- ❌ 为其他角色创建任务 -- ❌ 跳过可访问性检查 -- ❌ 在评分未达标时标记通过 - -## Message Types - -| Type | Direction | Trigger | Description | -|------|-----------|---------|-------------| -| `qa_fe_passed` | fe-qa → coordinator | All dimensions pass | 前端质检通过 | -| `qa_fe_result` | fe-qa → coordinator | Review complete (may have issues) | 审查结果（含问题） | -| `fix_required` | fe-qa → coordinator | Critical issues found | 需要 fe-developer 修复 | -| `error` | fe-qa → coordinator | Review failure | 审查失败 | - -## Message Bus - -```javascript -mcp__ccw-tools__team_msg({ - operation: "log", team: teamName, - from: "fe-qa", to: "coordinator", - type: "qa_fe_result", - summary: "[fe-qa] QA-FE: score=8.5, 0 critical, 2 medium", - ref: outputPath -}) -``` - -### CLI 回退 - -```javascript -Bash(`ccw team log --team "${teamName}" --from "fe-qa" --to "coordinator" --type "qa_fe_result" --summary "[fe-qa] QA-FE complete" --json`) -``` - -## Toolbox - -### Available Commands -- [commands/pre-delivery-checklist.md](commands/pre-delivery-checklist.md) — CSS 级别精准交付检查 - -### CLI Capabilities - -| CLI Tool | Mode | Purpose | -|----------|------|---------| -| `ccw cli --tool gemini --mode analysis` | analysis | 前端代码审查 | -| `ccw cli --tool codex --mode review` | review | Git-aware 代码审查 | - -## Review Dimensions - -| Dimension | Weight | Source | Focus | -|-----------|--------|--------|-------| -| Code Quality | 25% | Standard code review | TypeScript 类型安全、组件结构、状态管理、错误处理 | -| Accessibility | 25% | ux-guidelines rules | 语义 HTML、ARIA、键盘导航、色彩对比、focus-visible、prefers-reduced-motion | -| Design Compliance | 20% | design-intelligence.json | 设计令牌使用、行业反模式、emoji 检查、间距/排版一致性 | -| UX Best Practices | 15% | ux-guidelines Do/Don't | 加载状态、错误状态、空状态、cursor-pointer、响应式、动画时长 | -| Pre-Delivery | 15% | Pre-Delivery Checklist | 暗色模式、无 console.log、无硬编码、国际化就绪、must-have 检查 | - -## Execution (5-Phase) - -### Phase 1: Task Discovery - -```javascript -const tasks = TaskList() -const myTasks = tasks.filter(t => - t.subject.startsWith('QA-FE-') && - t.owner === 'fe-qa' && - t.status === 'pending' && - t.blockedBy.length === 0 -) -if (myTasks.length === 0) return -const task = TaskGet({ taskId: myTasks[0].id }) -TaskUpdate({ taskId: task.id, status: 'in_progress' }) -``` - -### Phase 2: Context Loading - -```javascript -const sessionFolder = task.description.match(/Session:\s*([^\n]+)/)?.[1]?.trim() - -// Load design tokens for compliance check -let designTokens = null -try { designTokens = JSON.parse(Read(`${sessionFolder}/architecture/design-tokens.json`)) } catch {} - -// Load design intelligence (from analyst via ui-ux-pro-max) -let designIntel = {} -try { designIntel = JSON.parse(Read(`${sessionFolder}/analysis/design-intelligence.json`)) } catch {} - -// Load shared memory for industry context + QA history -let sharedMemory = {} -try { sharedMemory = JSON.parse(Read(`${sessionFolder}/shared-memory.json`)) } catch {} - -const industryContext = sharedMemory.industry_context || {} -const antiPatterns = designIntel.recommendations?.anti_patterns || [] -const mustHave = designIntel.recommendations?.must_have || [] - -// Determine audit strictness from industry (standard / strict for medical/financial) -const strictness = industryContext.config?.strictness || 'standard' - -// Load component specs -let componentSpecs = [] -try { - const specFiles = Glob({ pattern: `${sessionFolder}/architecture/component-specs/*.md` }) - componentSpecs = specFiles.map(f => ({ path: f, content: Read(f) })) -} catch {} - -// Load previous QA results (for GC loop tracking) -let previousQA = [] -try { - const qaFiles = Glob({ pattern: `${sessionFolder}/qa/audit-fe-*.json` }) - previousQA = qaFiles.map(f => JSON.parse(Read(f))) -} catch {} - -// Determine GC round -const gcRound = previousQA.filter(q => q.task_subject === task.subject).length + 1 -const maxGCRounds = 2 - -// Get changed frontend files -const changedFiles = Bash(`git diff --name-only HEAD~1 2>/dev/null || git diff --name-only --cached 2>/dev/null || echo ""`) - .split('\n').filter(f => /\.(tsx|jsx|vue|svelte|css|scss|html|ts|js)$/.test(f)) - -// Read file contents for review -const fileContents = {} -for (const file of changedFiles.slice(0, 30)) { - try { fileContents[file] = Read(file) } catch {} -} -``` - -### Phase 3: 5-Dimension Review - -```javascript -const review = { - task_subject: task.subject, - gc_round: gcRound, - timestamp: new Date().toISOString(), - dimensions: [], - issues: [], - overall_score: 0, - verdict: 'PENDING' -} - -// === Dimension 1: Code Quality (25%) === -const codeQuality = { name: 'code-quality', weight: 0.25, score: 10, issues: [] } -for (const [file, content] of Object.entries(fileContents)) { - if (/:\s*any\b/.test(content)) { - codeQuality.issues.push({ file, severity: 'medium', issue: 'Using `any` type', fix: 'Replace with specific type', do: 'Define proper TypeScript types', dont: 'Use `any` to bypass type checking' }) - codeQuality.score -= 1.5 - } - if (/\.tsx$/.test(file) && /export/.test(content) && !/ErrorBoundary/.test(content) && /throw/.test(content)) { - codeQuality.issues.push({ file, severity: 'low', issue: 'No error boundary for component with throw', fix: 'Wrap with ErrorBoundary' }) - codeQuality.score -= 0.5 - } - if (/style=\{?\{/.test(content) && designTokens) { - codeQuality.issues.push({ file, severity: 'medium', issue: 'Inline styles detected', fix: 'Use design tokens or CSS classes', do: 'Use var(--color-*) tokens', dont: 'Hardcode style values inline' }) - codeQuality.score -= 1.5 - } - if (/catch\s*\(\s*\)\s*\{[\s]*\}/.test(content)) { - codeQuality.issues.push({ file, severity: 'high', issue: 'Empty catch block', fix: 'Add error handling logic', do: 'Log or handle the error', dont: 'Silently swallow exceptions' }) - codeQuality.score -= 2 - } - if (content.split('\n').length > 300) { - codeQuality.issues.push({ file, severity: 'medium', issue: 'File exceeds 300 lines', fix: 'Split into smaller modules' }) - codeQuality.score -= 1 - } -} -codeQuality.score = Math.max(0, codeQuality.score) -review.dimensions.push(codeQuality) - -// === Dimension 2: Accessibility (25%) === -const a11y = { name: 'accessibility', weight: 0.25, score: 10, issues: [] } -for (const [file, content] of Object.entries(fileContents)) { - if (!/\.(tsx|jsx|vue|svelte|html)$/.test(file)) continue - - if (/]*alt=/.test(content)) { - a11y.issues.push({ file, severity: 'high', issue: 'Image missing alt attribute', fix: 'Add descriptive alt text', do: 'Always provide alt text', dont: 'Leave alt empty without role="presentation"' }) - a11y.score -= 3 - } - if (/onClick/.test(content) && !/onKeyDown|onKeyPress|onKeyUp|role=.button/.test(content)) { - a11y.issues.push({ file, severity: 'medium', issue: 'Click handler without keyboard equivalent', fix: 'Add onKeyDown or role="button" tabIndex={0}' }) - a11y.score -= 1.5 - } - if (/ or aria-label', do: 'Associate every input with a label', dont: 'Use placeholder as sole label' }) - a11y.score -= 2 - } - if (/]*>\s* parseInt(h[2])) || [] - for (let i = 1; i < headings.length; i++) { - if (headings[i] - headings[i-1] > 1) { - a11y.issues.push({ file, severity: 'medium', issue: `Heading level skipped: h${headings[i-1]} → h${headings[i]}`, fix: 'Use sequential heading levels' }) - a11y.score -= 1 - } - } - // Focus-visible styles - if (/button| 0 && (ms < 100 || ms > 500)) { - uxPractices.issues.push({ file, severity: 'low', issue: `Transition ${ms}ms outside 150-300ms range`, fix: 'Use 150-300ms for micro-interactions' }) - uxPractices.score -= 0.5 - } - } - if (!/\.(tsx|jsx|vue|svelte)$/.test(file)) continue - // Loading states - if (/fetch|useQuery|useSWR|axios/.test(content) && !/loading|isLoading|skeleton|spinner/i.test(content)) { - uxPractices.issues.push({ file, severity: 'medium', issue: 'Data fetching without loading state', fix: 'Add loading indicator', do: 'Show skeleton/spinner during fetch', dont: 'Leave blank screen while loading' }) - uxPractices.score -= 1 - } - // Error states - if (/fetch|useQuery|useSWR|axios/.test(content) && !/error|isError|catch/i.test(content)) { - uxPractices.issues.push({ file, severity: 'high', issue: 'Data fetching without error handling', fix: 'Add error state UI', do: 'Show user-friendly error message', dont: 'Silently fail or show raw error' }) - uxPractices.score -= 2 - } - // Empty states - if (/\.map\(/.test(content) && !/empty|no.*data|no.*result|length\s*===?\s*0/i.test(content)) { - uxPractices.issues.push({ file, severity: 'low', issue: 'List rendering without empty state', fix: 'Add empty state message' }) - uxPractices.score -= 0.5 - } - // Responsive breakpoints - if (/className|class=/.test(content) && !/md:|lg:|@media/.test(content)) { - uxPractices.issues.push({ file, severity: 'medium', issue: 'No responsive breakpoints', fix: 'Mobile-first responsive design', do: 'Mobile-first responsive design', dont: 'Design for desktop only' }) - uxPractices.score -= 1 - } -} -uxPractices.score = Math.max(0, uxPractices.score) -review.dimensions.push(uxPractices) - -// === Dimension 5: Pre-Delivery (15%) === -// Detailed checklist: commands/pre-delivery-checklist.md -const preDelivery = { name: 'pre-delivery', weight: 0.15, score: 10, issues: [] } -const allContent = Object.values(fileContents).join('\n') - -// Per-file checks -for (const [file, content] of Object.entries(fileContents)) { - if (/console\.(log|debug|info)\(/.test(content) && !/test|spec|\.test\./.test(file)) { - preDelivery.issues.push({ file, severity: 'medium', issue: 'console.log in production code', fix: 'Remove or use proper logger' }) - preDelivery.score -= 1 - } - if (/\.(tsx|jsx)$/.test(file) && />\s*[A-Z][a-z]+\s+[a-z]+/.test(content) && !/t\(|intl|i18n|formatMessage/.test(content)) { - preDelivery.issues.push({ file, severity: 'low', issue: 'Hardcoded text — consider i18n', fix: 'Extract to translation keys' }) - preDelivery.score -= 0.5 - } - if (/TODO|FIXME|HACK|XXX/.test(content)) { - preDelivery.issues.push({ file, severity: 'low', issue: 'TODO/FIXME comment found', fix: 'Resolve or create issue' }) - preDelivery.score -= 0.5 - } -} - -// Global checklist items (from pre-delivery-checklist.md) -const checklist = [ - { check: "No emoji as functional icons", test: () => /[\u{1F300}-\u{1F9FF}]/u.test(allContent), severity: 'high' }, - { check: "cursor-pointer on clickable", test: () => /button|onClick/.test(allContent) && !/cursor-pointer/.test(allContent), severity: 'medium' }, - { check: "Focus states visible", test: () => /button|input| /animation|@keyframes/.test(allContent) && !/prefers-reduced-motion/.test(allContent), severity: 'medium' }, - { check: "Responsive breakpoints", test: () => !/md:|lg:|@media.*min-width/.test(allContent), severity: 'medium' }, - { check: "No hardcoded colors", test: () => { const nt = Object.entries(fileContents).filter(([f]) => f !== 'src/styles/tokens.css'); return nt.some(([,c]) => /#[0-9a-fA-F]{6}/.test(c)) }, severity: 'high' }, - { check: "Dark mode support", test: () => !/prefers-color-scheme|dark:|\.dark/.test(allContent), severity: 'medium' } -] -for (const item of checklist) { - try { - if (item.test()) { - preDelivery.issues.push({ check: item.check, severity: item.severity, issue: `Pre-delivery: ${item.check}` }) - preDelivery.score -= (item.severity === 'high' ? 2 : item.severity === 'medium' ? 1 : 0.5) - } - } catch {} -} - -// Must-have checks from industry config -for (const req of mustHave) { - if (req === 'wcag-aaa' && !/aria-/.test(allContent)) { - preDelivery.issues.push({ severity: 'high', issue: 'WCAG AAA required but no ARIA attributes found' }) - preDelivery.score -= 3 - } - if (req === 'high-contrast' && !/high-contrast|forced-colors/.test(allContent)) { - preDelivery.issues.push({ severity: 'medium', issue: 'High contrast mode not supported' }) - preDelivery.score -= 1 - } -} -preDelivery.score = Math.max(0, preDelivery.score) -review.dimensions.push(preDelivery) - -// === Calculate Overall Score === -review.overall_score = review.dimensions.reduce((sum, d) => sum + d.score * d.weight, 0) -review.issues = review.dimensions.flatMap(d => d.issues) -const criticalCount = review.issues.filter(i => i.severity === 'high').length - -if (review.overall_score >= 8 && criticalCount === 0) { - review.verdict = 'PASS' -} else if (gcRound >= maxGCRounds) { - review.verdict = review.overall_score >= 6 ? 'PASS_WITH_WARNINGS' : 'FAIL' -} else { - review.verdict = 'NEEDS_FIX' -} -``` - -### Phase 4: Package Results + Shared Memory - -```javascript -const outputPath = sessionFolder - ? `${sessionFolder}/qa/audit-fe-${task.subject.replace(/[^a-zA-Z0-9-]/g, '-').toLowerCase()}-r${gcRound}.json` - : '.workflow/.tmp/qa-fe-audit.json' - -Bash(`mkdir -p "$(dirname '${outputPath}')"`) -Write(outputPath, JSON.stringify(review, null, 2)) - -// Wisdom contribution -if (sessionFolder && review.issues.length > 0) { - try { - const issuesPath = `${sessionFolder}/wisdom/issues.md` - const existing = Read(issuesPath) - const timestamp = new Date().toISOString().substring(0, 10) - const highIssues = review.issues.filter(i => i.severity === 'high') - if (highIssues.length > 0) { - const entries = highIssues.map(i => `- [${timestamp}] [fe-qa] ${i.issue} in ${i.file || 'global'}`).join('\n') - Write(issuesPath, existing + '\n' + entries) - } - } catch {} -} - -// Update shared memory with QA history -if (sessionFolder) { - try { - sharedMemory.qa_history = sharedMemory.qa_history || [] - sharedMemory.qa_history.push({ - task_subject: task.subject, - gc_round: gcRound, - verdict: review.verdict, - score: review.overall_score, - critical_count: criticalCount, - total_issues: review.issues.length, - timestamp: new Date().toISOString() - }) - Write(`${sessionFolder}/shared-memory.json`, JSON.stringify(sharedMemory, null, 2)) - } catch {} -} -``` - -### Phase 5: Report to Coordinator - -```javascript -const msgType = review.verdict === 'PASS' || review.verdict === 'PASS_WITH_WARNINGS' - ? 'qa_fe_passed' - : criticalCount > 0 ? 'fix_required' : 'qa_fe_result' - -mcp__ccw-tools__team_msg({ - operation: "log", team: teamName, - from: "fe-qa", to: "coordinator", - type: msgType, - summary: `[fe-qa] QA-FE R${gcRound}: ${review.verdict}, score=${review.overall_score.toFixed(1)}, ${criticalCount} critical`, - ref: outputPath -}) - -SendMessage({ - type: "message", - recipient: "coordinator", - content: `[fe-qa] ## Frontend QA Review - -**Task**: ${task.subject} -**Round**: ${gcRound}/${maxGCRounds} -**Verdict**: ${review.verdict} -**Score**: ${review.overall_score.toFixed(1)}/10 -**Strictness**: ${strictness} -**Design Intelligence**: ${designIntel._source || 'not available'} - -### Dimension Scores -${review.dimensions.map(d => `- **${d.name}**: ${d.score.toFixed(1)}/10 (${d.issues.length} issues)`).join('\n')} - -### Critical Issues (${criticalCount}) -${review.issues.filter(i => i.severity === 'high').map(i => `- \`${i.file || i.check}\`: ${i.issue} → ${i.fix || ''}${i.do ? `\n ✅ Do: ${i.do}` : ''}${i.dont ? `\n ❌ Don't: ${i.dont}` : ''}`).join('\n') || 'None'} - -### Medium Issues -${review.issues.filter(i => i.severity === 'medium').slice(0, 5).map(i => `- \`${i.file || i.check}\`: ${i.issue} → ${i.fix || ''}`).join('\n') || 'None'} - -${review.verdict === 'NEEDS_FIX' ? `\n### Action Required\nfe-developer 需修复 ${criticalCount} 个 critical 问题后重新提交。` : ''} - -### Output: ${outputPath}`, - summary: `[fe-qa] QA-FE R${gcRound}: ${review.verdict}, ${review.overall_score.toFixed(1)}/10` -}) - -TaskUpdate({ taskId: task.id, status: 'completed' }) -// Check for next QA-FE task → back to Phase 1 -``` - -## Generator-Critic Loop - -fe-developer ↔ fe-qa 循环由 coordinator 编排： - -``` -Round 1: DEV-FE-001 → QA-FE-001 - if QA verdict = NEEDS_FIX: - coordinator creates DEV-FE-002 (fix task, blockedBy QA-FE-001) - coordinator creates QA-FE-002 (re-review, blockedBy DEV-FE-002) -Round 2: DEV-FE-002 → QA-FE-002 - if still NEEDS_FIX: verdict = PASS_WITH_WARNINGS or FAIL (max 2 rounds) -``` - -**收敛条件**: `overall_score >= 8 && critical_count === 0` - -## Error Handling - -| Scenario | Resolution | -|----------|------------| -| No QA-FE-* tasks | Idle, wait for coordinator | -| No changed frontend files | Report empty review, score = N/A | -| Design tokens not found | Skip design compliance dimension, adjust weights | -| design-intelligence.json not found | Skip industry anti-patterns, use standard strictness | -| Git diff fails | Use Glob to find recent frontend files | -| Max GC rounds exceeded | Force verdict (PASS_WITH_WARNINGS or FAIL) | -| ui-ux-pro-max not installed | Continue without design intelligence, note in report | diff --git a/.claude/skills_lib/team-lifecycle-v2/roles/planner/commands/explore.md b/.claude/skills_lib/team-lifecycle-v2/roles/planner/commands/explore.md deleted file mode 100644 index 4746d851..00000000 --- a/.claude/skills_lib/team-lifecycle-v2/roles/planner/commands/explore.md +++ /dev/null @@ -1,466 +0,0 @@ -# Command: Multi-Angle Exploration - -Phase 2 of planner execution - assess complexity, select exploration angles, and execute parallel exploration. - -## Overview - -This command performs multi-angle codebase exploration based on task complexity. Low complexity uses direct semantic search, while Medium/High complexity launches parallel cli-explore-agent subagents for comprehensive analysis. - -## Complexity Assessment - -### assessComplexity Function - -```javascript -function assessComplexity(desc) { - let score = 0 - if (/refactor|architect|restructure|模块|系统/.test(desc)) score += 2 - if (/multiple|多个|across|跨/.test(desc)) score += 2 - if (/integrate|集成|api|database/.test(desc)) score += 1 - if (/security|安全|performance|性能/.test(desc)) score += 1 - return score >= 4 ? 'High' : score >= 2 ? 'Medium' : 'Low' -} - -const complexity = assessComplexity(task.description) -``` - -### Complexity Levels - -| Level | Score | Characteristics | Angle Count | -|-------|-------|----------------|-------------| -| **Low** | 0-1 | Simple feature, single module, clear scope | 1 | -| **Medium** | 2-3 | Multiple modules, integration points, moderate scope | 3 | -| **High** | 4+ | Architecture changes, cross-cutting concerns, complex scope | 4 | - -## Angle Selection - -### ANGLE_PRESETS - -```javascript -const ANGLE_PRESETS = { - architecture: ['architecture', 'dependencies', 'modularity', 'integration-points'], - security: ['security', 'auth-patterns', 'dataflow', 'validation'], - performance: ['performance', 'bottlenecks', 'caching', 'data-access'], - bugfix: ['error-handling', 'dataflow', 'state-management', 'edge-cases'], - feature: ['patterns', 'integration-points', 'testing', 'dependencies'] -} -``` - -### selectAngles Function - -```javascript -function selectAngles(desc, count) { - const text = desc.toLowerCase() - let preset = 'feature' - if (/refactor|architect|restructure|modular/.test(text)) preset = 'architecture' - else if (/security|auth|permission|access/.test(text)) preset = 'security' - else if (/performance|slow|optimi|cache/.test(text)) preset = 'performance' - else if (/fix|bug|error|issue|broken/.test(text)) preset = 'bugfix' - return ANGLE_PRESETS[preset].slice(0, count) -} - -const angleCount = complexity === 'High' ? 4 : (complexity === 'Medium' ? 3 : 1) -const selectedAngles = selectAngles(task.description, angleCount) -``` - -### Angle Definitions - -| Angle | Focus | Use Case | -|-------|-------|----------| -| **architecture** | System structure, layer boundaries, design patterns | Refactoring, restructuring | -| **dependencies** | Module dependencies, coupling, external libraries | Integration, modularity | -| **modularity** | Component boundaries, separation of concerns | Architecture changes | -| **integration-points** | API boundaries, data flow between modules | Feature development | -| **security** | Auth/authz, input validation, data protection | Security features | -| **auth-patterns** | Authentication flows, session management | Auth implementation | -| **dataflow** | Data transformation, state propagation | Bug fixes, features | -| **validation** | Input validation, error handling | Security, quality | -| **performance** | Bottlenecks, optimization opportunities | Performance tuning | -| **bottlenecks** | Slow operations, resource contention | Performance issues | -| **caching** | Cache strategies, invalidation patterns | Performance optimization | -| **data-access** | Database queries, data fetching patterns | Performance, features | -| **error-handling** | Error propagation, recovery strategies | Bug fixes | -| **state-management** | State updates, consistency | Bug fixes, features | -| **edge-cases** | Boundary conditions, error scenarios | Bug fixes, testing | -| **patterns** | Code patterns, conventions, best practices | Feature development | -| **testing** | Test coverage, test strategies | Feature development | - -## Exploration Execution - -### Low Complexity: Direct Semantic Search - -```javascript -if (complexity === 'Low') { - // Direct exploration via semantic search - const results = mcp__ace-tool__search_context({ - project_root_path: projectRoot, - query: task.description - }) - - // Transform ACE results to exploration JSON - const exploration = { - project_structure: "Analyzed via ACE semantic search", - relevant_files: results.files.map(f => ({ - path: f.path, - rationale: f.relevance_reason || "Semantic match to task description", - role: "modify_target", - discovery_source: "ace-search", - key_symbols: f.symbols || [] - })), - patterns: results.patterns || [], - dependencies: results.dependencies || [], - integration_points: results.integration_points || [], - constraints: [], - clarification_needs: [], - _metadata: { - exploration_angle: selectedAngles[0], - complexity: 'Low', - discovery_method: 'ace-semantic-search' - } - } - - Write(`${planDir}/exploration-${selectedAngles[0]}.json`, JSON.stringify(exploration, null, 2)) -} -``` - -### Medium/High Complexity: Parallel cli-explore-agent - -```javascript -else { - // Launch parallel cli-explore-agent for each angle - selectedAngles.forEach((angle, index) => { - Task({ - subagent_type: "cli-explore-agent", - run_in_background: false, - description: `Explore: ${angle}`, - prompt: ` -## Task Objective -Execute **${angle}** exploration for task planning context. - -## Output Location -**Session Folder**: ${sessionFolder} -**Output File**: ${planDir}/exploration-${angle}.json - -## Assigned Context -- **Exploration Angle**: ${angle} -- **Task Description**: ${task.description} -- **Spec Context**: ${specContext ? 'Available — use spec/requirements, spec/architecture, spec/epics for informed exploration' : 'Not available (impl-only mode)'} -- **Exploration Index**: ${index + 1} of ${selectedAngles.length} - -## MANDATORY FIRST STEPS -1. Run: rg -l "{relevant_keyword}" --type ts (locate relevant files) -2. Execute: cat ~/.ccw/workflows/cli-templates/schemas/explore-json-schema.json (get output schema) -3. Read: .workflow/project-tech.json (if exists - technology stack) - -## Expected Output -Write JSON to: ${planDir}/exploration-${angle}.json -Follow explore-json-schema.json structure with ${angle}-focused findings. - -**MANDATORY**: Every file in relevant_files MUST have: -- **rationale** (required): Specific selection basis tied to ${angle} topic (>10 chars, not generic) -- **role** (required): modify_target|dependency|pattern_reference|test_target|type_definition|integration_point|config|context_only -- **discovery_source** (recommended): bash-scan|cli-analysis|ace-search|dependency-trace|manual -- **key_symbols** (recommended): Key functions/classes/types relevant to task - -## Exploration Focus by Angle - -${getAngleFocusGuide(angle)} - -## Output Schema Structure - -\`\`\`json -{ - "project_structure": "string - high-level architecture overview", - "relevant_files": [ - { - "path": "string - relative file path", - "rationale": "string - WHY this file matters for ${angle} (>10 chars, specific)", - "role": "modify_target|dependency|pattern_reference|test_target|type_definition|integration_point|config|context_only", - "discovery_source": "bash-scan|cli-analysis|ace-search|dependency-trace|manual", - "key_symbols": ["function/class/type names"] - } - ], - "patterns": ["string - code patterns relevant to ${angle}"], - "dependencies": ["string - module/library dependencies"], - "integration_points": ["string - API/interface boundaries"], - "constraints": ["string - technical constraints"], - "clarification_needs": ["string - questions needing user input"], - "_metadata": { - "exploration_angle": "${angle}", - "complexity": "${complexity}", - "discovery_method": "cli-explore-agent" - } -} -\`\`\` -` - }) - }) -} -``` - -### Angle Focus Guide - -```javascript -function getAngleFocusGuide(angle) { - const guides = { - architecture: ` -**Architecture Focus**: -- Identify layer boundaries (presentation, business, data) -- Map module dependencies and coupling -- Locate design patterns (factory, strategy, observer, etc.) -- Find architectural decision records (ADRs) -- Analyze component responsibilities`, - - dependencies: ` -**Dependencies Focus**: -- Map internal module dependencies (import/require statements) -- Identify external library usage (package.json, requirements.txt) -- Trace dependency chains and circular dependencies -- Locate shared utilities and common modules -- Analyze coupling strength between modules`, - - modularity: ` -**Modularity Focus**: -- Identify module boundaries and interfaces -- Analyze separation of concerns -- Locate tightly coupled code -- Find opportunities for extraction/refactoring -- Map public vs private APIs`, - - 'integration-points': ` -**Integration Points Focus**: -- Locate API endpoints and routes -- Identify data flow between modules -- Find event emitters/listeners -- Map external service integrations -- Analyze interface contracts`, - - security: ` -**Security Focus**: -- Locate authentication/authorization logic -- Identify input validation points -- Find sensitive data handling -- Analyze access control mechanisms -- Locate security-related middleware`, - - 'auth-patterns': ` -**Auth Patterns Focus**: -- Identify authentication flows (login, logout, refresh) -- Locate session management code -- Find token generation/validation -- Map user permission checks -- Analyze auth middleware`, - - dataflow: ` -**Dataflow Focus**: -- Trace data transformations -- Identify state propagation paths -- Locate data validation points -- Map data sources and sinks -- Analyze data mutation points`, - - validation: ` -**Validation Focus**: -- Locate input validation logic -- Identify schema definitions -- Find error handling for invalid data -- Map validation middleware -- Analyze sanitization functions`, - - performance: ` -**Performance Focus**: -- Identify computational bottlenecks -- Locate database queries (N+1 problems) -- Find synchronous blocking operations -- Map resource-intensive operations -- Analyze algorithm complexity`, - - bottlenecks: ` -**Bottlenecks Focus**: -- Locate slow operations (profiling data) -- Identify resource contention points -- Find inefficient algorithms -- Map hot paths in code -- Analyze concurrency issues`, - - caching: ` -**Caching Focus**: -- Locate existing cache implementations -- Identify cacheable operations -- Find cache invalidation logic -- Map cache key strategies -- Analyze cache hit/miss patterns`, - - 'data-access': ` -**Data Access Focus**: -- Locate database query patterns -- Identify ORM/query builder usage -- Find data fetching strategies -- Map data access layers -- Analyze query optimization opportunities`, - - 'error-handling': ` -**Error Handling Focus**: -- Locate try-catch blocks -- Identify error propagation paths -- Find error recovery strategies -- Map error logging points -- Analyze error types and handling`, - - 'state-management': ` -**State Management Focus**: -- Locate state containers (Redux, Vuex, etc.) -- Identify state update patterns -- Find state synchronization logic -- Map state dependencies -- Analyze state consistency mechanisms`, - - 'edge-cases': ` -**Edge Cases Focus**: -- Identify boundary conditions -- Locate null/undefined handling -- Find empty array/object handling -- Map error scenarios -- Analyze exceptional flows`, - - patterns: ` -**Patterns Focus**: -- Identify code patterns and conventions -- Locate design pattern implementations -- Find naming conventions -- Map code organization patterns -- Analyze best practices usage`, - - testing: ` -**Testing Focus**: -- Locate test files and test utilities -- Identify test coverage gaps -- Find test patterns (unit, integration, e2e) -- Map mocking/stubbing strategies -- Analyze test organization` - } - - return guides[angle] || `**${angle} Focus**: Analyze codebase from ${angle} perspective` -} -``` - -## Explorations Manifest - -```javascript -// Build explorations manifest -const explorationManifest = { - session_id: `${taskSlug}-${dateStr}`, - task_description: task.description, - complexity: complexity, - exploration_count: selectedAngles.length, - explorations: selectedAngles.map(angle => ({ - angle: angle, - file: `exploration-${angle}.json`, - path: `${planDir}/exploration-${angle}.json` - })) -} -Write(`${planDir}/explorations-manifest.json`, JSON.stringify(explorationManifest, null, 2)) -``` - -## Output Schema - -### explore-json-schema.json Structure - -```json -{ - "project_structure": "string - high-level architecture overview", - "relevant_files": [ - { - "path": "string - relative file path", - "rationale": "string - specific selection basis (>10 chars)", - "role": "modify_target|dependency|pattern_reference|test_target|type_definition|integration_point|config|context_only", - "discovery_source": "bash-scan|cli-analysis|ace-search|dependency-trace|manual", - "key_symbols": ["string - function/class/type names"] - } - ], - "patterns": ["string - code patterns relevant to angle"], - "dependencies": ["string - module/library dependencies"], - "integration_points": ["string - API/interface boundaries"], - "constraints": ["string - technical constraints"], - "clarification_needs": ["string - questions needing user input"], - "_metadata": { - "exploration_angle": "string - angle name", - "complexity": "Low|Medium|High", - "discovery_method": "ace-semantic-search|cli-explore-agent" - } -} -``` - -## Integration with Phase 3 - -Phase 3 (Plan Generation) consumes: -1. `explorations-manifest.json` - list of exploration files -2. `exploration-{angle}.json` - per-angle exploration results -3. `specContext` (if available) - requirements, architecture, epics - -These inputs are passed to cli-lite-planning-agent for plan generation. - -## Error Handling - -### Exploration Agent Failure - -```javascript -try { - Task({ - subagent_type: "cli-explore-agent", - run_in_background: false, - description: `Explore: ${angle}`, - prompt: `...` - }) -} catch (error) { - // Skip exploration, continue with available explorations - console.error(`[planner] Exploration failed for angle: ${angle}`, error) - // Remove failed angle from manifest - explorationManifest.explorations = explorationManifest.explorations.filter(e => e.angle !== angle) - explorationManifest.exploration_count = explorationManifest.explorations.length -} -``` - -### All Explorations Fail - -```javascript -if (explorationManifest.exploration_count === 0) { - // Fallback: Plan from task description only - console.warn(`[planner] All explorations failed, planning from task description only`) - // Proceed to Phase 3 with empty explorations -} -``` - -### ACE Search Failure (Low Complexity) - -```javascript -try { - const results = mcp__ace-tool__search_context({ - project_root_path: projectRoot, - query: task.description - }) -} catch (error) { - // Fallback: Use ripgrep for basic file discovery - const rgResults = Bash(`rg -l "${task.description}" --type ts`) - const exploration = { - project_structure: "Basic file discovery via ripgrep", - relevant_files: rgResults.split('\n').map(path => ({ - path: path.trim(), - rationale: "Matched task description keywords", - role: "modify_target", - discovery_source: "bash-scan", - key_symbols: [] - })), - patterns: [], - dependencies: [], - integration_points: [], - constraints: [], - clarification_needs: [], - _metadata: { - exploration_angle: selectedAngles[0], - complexity: 'Low', - discovery_method: 'ripgrep-fallback' - } - } - Write(`${planDir}/exploration-${selectedAngles[0]}.json`, JSON.stringify(exploration, null, 2)) -} -``` diff --git a/.claude/skills_lib/team-lifecycle-v2/roles/planner/role.md b/.claude/skills_lib/team-lifecycle-v2/roles/planner/role.md deleted file mode 100644 index c658ec3a..00000000 --- a/.claude/skills_lib/team-lifecycle-v2/roles/planner/role.md +++ /dev/null @@ -1,253 +0,0 @@ -# Role: planner - -Multi-angle code exploration and structured implementation planning. Submits plans to the coordinator for approval. - -## Role Identity - -- **Name**: `planner` -- **Task Prefix**: `PLAN-*` -- **Output Tag**: `[planner]` -- **Responsibility**: Code exploration → Implementation planning → Coordinator approval -- **Communication**: SendMessage to coordinator only - -## Role Boundaries - -### MUST -- Only process PLAN-* tasks -- Communicate only with coordinator -- Write plan artifacts to `plan/` folder -- Tag all SendMessage and team_msg calls with `[planner]` -- Assess complexity (Low/Medium/High) -- Execute multi-angle exploration based on complexity -- Generate plan.json + .task/TASK-*.json following schemas -- Submit plan for coordinator approval -- Load spec context in full-lifecycle mode - -### MUST NOT -- Create tasks -- Contact other workers directly -- Implement code -- Modify spec documents -- Skip complexity assessment -- Proceed without exploration (Medium/High complexity) -- Generate plan without schema validation - -## Message Types - -| Type | Direction | Trigger | Description | -|------|-----------|---------|-------------| -| `plan_ready` | planner → coordinator | Plan generation complete | With plan.json path and task count summary | -| `plan_revision` | planner → coordinator | Plan revised and resubmitted | Describes changes made | -| `impl_progress` | planner → coordinator | Exploration phase progress | Optional, for long explorations | -| `error` | planner → coordinator | Unrecoverable error | Exploration failure, schema missing, etc. | - -## Message Bus - -Before every `SendMessage`, MUST call `mcp__ccw-tools__team_msg` to log: - -```javascript -// Plan ready -mcp__ccw-tools__team_msg({ operation: "log", team: teamName, from: "planner", to: "coordinator", type: "plan_ready", summary: "[planner] Plan ready: 3 tasks, Medium complexity", ref: `${sessionFolder}/plan/plan.json` }) - -// Plan revision -mcp__ccw-tools__team_msg({ operation: "log", team: teamName, from: "planner", to: "coordinator", type: "plan_revision", summary: "[planner] Split task-2 into two subtasks per feedback" }) - -// Error report -mcp__ccw-tools__team_msg({ operation: "log", team: teamName, from: "planner", to: "coordinator", type: "error", summary: "[planner] plan-overview-base-schema.json not found, using default structure" }) -``` - -### CLI Fallback - -When `mcp__ccw-tools__team_msg` MCP is unavailable: - -```javascript -Bash(`ccw team log --team "${teamName}" --from "planner" --to "coordinator" --type "plan_ready" --summary "[planner] Plan ready: 3 tasks" --ref "${sessionFolder}/plan/plan.json" --json`) -``` - -## Toolbox - -### Available Commands -- `commands/explore.md` - Multi-angle codebase exploration (Phase 2) - -### Subagent Capabilities -- **cli-explore-agent**: Per-angle exploration (Medium/High complexity) -- **cli-lite-planning-agent**: Plan generation (Medium/High complexity) - -### CLI Capabilities -None directly (delegates to subagents) - -## Execution (5-Phase) - -### Phase 1: Task Discovery - -```javascript -const tasks = TaskList() -const myTasks = tasks.filter(t => - t.subject.startsWith('PLAN-') && - t.owner === 'planner' && - t.status === 'pending' && - t.blockedBy.length === 0 -) - -if (myTasks.length === 0) return // idle - -const task = TaskGet({ taskId: myTasks[0].id }) -TaskUpdate({ taskId: task.id, status: 'in_progress' }) -``` - -### Phase 1.5: Load Spec Context (Full-Lifecycle Mode) - -```javascript -// Extract session folder from task description (set by coordinator) -const sessionMatch = task.description.match(/Session:\s*(.+)/) -const sessionFolder = sessionMatch ? sessionMatch[1].trim() : `.workflow/.team/default` -const planDir = `${sessionFolder}/plan` -Bash(`mkdir -p ${planDir}`) - -// Check if spec directory exists (full-lifecycle mode) -const specDir = `${sessionFolder}/spec` -let specContext = null -try { - const reqIndex = Read(`${specDir}/requirements/_index.md`) - const archIndex = Read(`${specDir}/architecture/_index.md`) - const epicsIndex = Read(`${specDir}/epics/_index.md`) - const specConfig = JSON.parse(Read(`${specDir}/spec-config.json`)) - specContext = { reqIndex, archIndex, epicsIndex, specConfig } -} catch { /* impl-only mode has no spec */ } -``` - -### Phase 2: Multi-Angle Exploration - -**Delegate to**: `Read("commands/explore.md")` - -Execute complexity assessment, angle selection, and parallel exploration. See `commands/explore.md` for full implementation. - -### Phase 3: Plan Generation - -```javascript -// Read schema reference -const schema = Bash(`cat ~/.ccw/workflows/cli-templates/schemas/plan-overview-base-schema.json`) - -if (complexity === 'Low') { - // Direct Claude planning - Bash(`mkdir -p ${planDir}/.task`) - // Generate plan.json + .task/TASK-*.json following schemas - - const plan = { - session_id: `${taskSlug}-${dateStr}`, - task_description: task.description, - complexity: 'Low', - approach: "Direct implementation based on semantic search", - task_count: 1, - task_ids: ['TASK-001'], - exploration_refs: [`${planDir}/exploration-patterns.json`] - } - Write(`${planDir}/plan.json`, JSON.stringify(plan, null, 2)) - - const taskDetail = { - id: 'TASK-001', - title: task.subject, - description: task.description, - files: [], - convergence: { criteria: ["Implementation complete", "Tests pass"] }, - depends_on: [] - } - Write(`${planDir}/.task/TASK-001.json`, JSON.stringify(taskDetail, null, 2)) - -} else { - // Use cli-lite-planning-agent for Medium/High - Task({ - subagent_type: "cli-lite-planning-agent", - run_in_background: false, - description: "Generate detailed implementation plan", - prompt: `Generate implementation plan. -Output: ${planDir}/plan.json + ${planDir}/.task/TASK-*.json -Schema: cat ~/.ccw/workflows/cli-templates/schemas/plan-overview-base-schema.json -Task Description: ${task.description} -Explorations: ${explorationManifest} -Complexity: ${complexity} -${specContext ? `Spec Context: -- Requirements: ${specContext.reqIndex.substring(0, 500)} -- Architecture: ${specContext.archIndex.substring(0, 500)} -- Epics: ${specContext.epicsIndex.substring(0, 500)} -Reference REQ-* IDs, follow ADR decisions, reuse Epic/Story decomposition.` : ''} -Requirements: 2-7 tasks, each with id, title, files[].change, convergence.criteria, depends_on` - }) -} -``` - -### Phase 4: Submit for Approval - -```javascript -const plan = JSON.parse(Read(`${planDir}/plan.json`)) -const planTasks = plan.task_ids.map(id => JSON.parse(Read(`${planDir}/.task/${id}.json`))) -const taskCount = plan.task_count || plan.task_ids.length - -mcp__ccw-tools__team_msg({ - operation: "log", team: teamName, - from: "planner", to: "coordinator", - type: "plan_ready", - summary: `[planner] Plan就绪: ${taskCount}个task, ${complexity}复杂度`, - ref: `${planDir}/plan.json` -}) - -SendMessage({ - type: "message", - recipient: "coordinator", - content: `[planner] ## Plan Ready for Review - -**Task**: ${task.subject} -**Complexity**: ${complexity} -**Tasks**: ${taskCount} - -### Task Summary -${planTasks.map((t, i) => (i+1) + '. ' + t.title).join('\n')} - -### Approach -${plan.approach} - -### Plan Location -${planDir}/plan.json -Task Files: ${planDir}/.task/ - -Please review and approve or request revisions.`, - summary: `[planner] Plan ready: ${taskCount} tasks` -}) - -// Wait for coordinator response (approve → mark completed, revision → update and resubmit) -``` - -### Phase 5: After Approval - -```javascript -TaskUpdate({ taskId: task.id, status: 'completed' }) - -// Check for next PLAN task → back to Phase 1 -``` - -## Session Files - -``` -{sessionFolder}/plan/ -├── exploration-{angle}.json -├── explorations-manifest.json -├── planning-context.md -├── plan.json -└── .task/ - └── TASK-*.json -``` - -> **Note**: `sessionFolder` is extracted from task description (`Session: .workflow/.team/TLS-xxx`). Plan outputs go to `plan/` subdirectory. In full-lifecycle mode, spec products are available at `../spec/`. - -## Error Handling - -| Scenario | Resolution | -|----------|------------| -| No PLAN-* tasks available | Idle, wait for coordinator assignment | -| Exploration agent failure | Skip exploration, plan from task description only | -| Planning agent failure | Fallback to direct Claude planning | -| Plan rejected 3+ times | Notify coordinator with `[planner]` tag, suggest alternative approach | -| Schema file not found | Use basic plan structure without schema validation, log error with `[planner]` tag | -| Spec context load failure | Continue in impl-only mode (no spec context) | -| Session folder not found | Notify coordinator with `[planner]` tag, request session path | -| Unexpected error | Log error via team_msg with `[planner]` tag, report to coordinator | diff --git a/.claude/skills_lib/team-lifecycle-v2/roles/reviewer/commands/code-review.md b/.claude/skills_lib/team-lifecycle-v2/roles/reviewer/commands/code-review.md deleted file mode 100644 index 53e4a635..00000000 --- a/.claude/skills_lib/team-lifecycle-v2/roles/reviewer/commands/code-review.md +++ /dev/null @@ -1,689 +0,0 @@ -# Code Review Command - -## Purpose -4-dimension code review analyzing quality, security, architecture, and requirements compliance. - -## Review Dimensions - -### 1. Quality Review - -```javascript -function reviewQuality(files, gitDiff) { - const issues = { - critical: [], - high: [], - medium: [], - low: [] - } - - for (const file of files) { - const content = file.content - const lines = content.split("\n") - - // Check for @ts-ignore / @ts-expect-error - lines.forEach((line, idx) => { - if (line.includes("@ts-ignore") || line.includes("@ts-expect-error")) { - const nextLine = lines[idx + 1] || "" - const hasJustification = line.includes("//") && line.split("//")[1].trim().length > 10 - - if (!hasJustification) { - issues.high.push({ - file: file.path, - line: idx + 1, - type: "ts-ignore-without-justification", - message: "TypeScript error suppression without explanation", - code: line.trim() - }) - } - } - }) - - // Check for 'any' type usage - const anyMatches = Grep("\\bany\\b", { path: file.path, "-n": true }) - if (anyMatches) { - anyMatches.forEach(match => { - // Exclude comments and type definitions that are intentionally generic - if (!match.line.includes("//") && !match.line.includes("Generic")) { - issues.high.push({ - file: file.path, - line: match.lineNumber, - type: "any-type-usage", - message: "Using 'any' type reduces type safety", - code: match.line.trim() - }) - } - }) - } - - // Check for console.log in production code - const consoleMatches = Grep("console\\.(log|debug|info)", { path: file.path, "-n": true }) - if (consoleMatches && !file.path.includes("test")) { - consoleMatches.forEach(match => { - issues.high.push({ - file: file.path, - line: match.lineNumber, - type: "console-log", - message: "Console statements should be removed from production code", - code: match.line.trim() - }) - }) - } - - // Check for empty catch blocks - const emptyCatchRegex = /catch\s*\([^)]*\)\s*\{\s*\}/g - let match - while ((match = emptyCatchRegex.exec(content)) !== null) { - const lineNumber = content.substring(0, match.index).split("\n").length - issues.critical.push({ - file: file.path, - line: lineNumber, - type: "empty-catch", - message: "Empty catch block silently swallows errors", - code: match[0] - }) - } - - // Check for magic numbers - const magicNumberRegex = /(? { - const trimmed = line.trim() - if (trimmed.length > 30 && !trimmed.startsWith("//")) { - if (!lineHashes.has(trimmed)) { - lineHashes.set(trimmed, []) - } - lineHashes.get(trimmed).push(idx + 1) - } - }) - - lineHashes.forEach((occurrences, line) => { - if (occurrences.length > 2) { - issues.medium.push({ - file: file.path, - line: occurrences[0], - type: "duplicate-code", - message: `Duplicate code found at lines: ${occurrences.join(", ")}`, - code: line - }) - } - }) - } - - return issues -} -``` - -### 2. Security Review - -```javascript -function reviewSecurity(files) { - const issues = { - critical: [], - high: [], - medium: [], - low: [] - } - - for (const file of files) { - const content = file.content - - // Check for eval/exec usage - const evalMatches = Grep("\\b(eval|exec|Function\\(|setTimeout\\(.*string|setInterval\\(.*string)\\b", { - path: file.path, - "-n": true - }) - if (evalMatches) { - evalMatches.forEach(match => { - issues.high.push({ - file: file.path, - line: match.lineNumber, - type: "dangerous-eval", - message: "eval/exec usage can lead to code injection vulnerabilities", - code: match.line.trim() - }) - }) - } - - // Check for innerHTML/dangerouslySetInnerHTML - const innerHTMLMatches = Grep("(innerHTML|dangerouslySetInnerHTML)", { - path: file.path, - "-n": true - }) - if (innerHTMLMatches) { - innerHTMLMatches.forEach(match => { - issues.high.push({ - file: file.path, - line: match.lineNumber, - type: "xss-risk", - message: "Direct HTML injection can lead to XSS vulnerabilities", - code: match.line.trim() - }) - }) - } - - // Check for hardcoded secrets - const secretPatterns = [ - /api[_-]?key\s*=\s*['"][^'"]{20,}['"]/i, - /password\s*=\s*['"][^'"]+['"]/i, - /secret\s*=\s*['"][^'"]{20,}['"]/i, - /token\s*=\s*['"][^'"]{20,}['"]/i, - /aws[_-]?access[_-]?key/i, - /private[_-]?key\s*=\s*['"][^'"]+['"]/i - ] - - secretPatterns.forEach(pattern => { - const matches = content.match(new RegExp(pattern, "gm")) - if (matches) { - matches.forEach(match => { - const lineNumber = content.substring(0, content.indexOf(match)).split("\n").length - issues.critical.push({ - file: file.path, - line: lineNumber, - type: "hardcoded-secret", - message: "Hardcoded secrets should be moved to environment variables", - code: match.replace(/['"][^'"]+['"]/, "'***'") // Redact secret - }) - }) - } - }) - - // Check for SQL injection vectors - const sqlInjectionMatches = Grep("(query|execute)\\s*\\(.*\\+.*\\)", { - path: file.path, - "-n": true - }) - if (sqlInjectionMatches) { - sqlInjectionMatches.forEach(match => { - if (!match.line.includes("//") && !match.line.includes("prepared")) { - issues.critical.push({ - file: file.path, - line: match.lineNumber, - type: "sql-injection", - message: "String concatenation in SQL queries can lead to SQL injection", - code: match.line.trim() - }) - } - }) - } - - // Check for insecure random - const insecureRandomMatches = Grep("Math\\.random\\(\\)", { - path: file.path, - "-n": true - }) - if (insecureRandomMatches) { - insecureRandomMatches.forEach(match => { - // Check if used for security purposes - const context = content.substring( - Math.max(0, content.indexOf(match.line) - 200), - content.indexOf(match.line) + 200 - ) - if (context.match(/token|key|secret|password|session/i)) { - issues.medium.push({ - file: file.path, - line: match.lineNumber, - type: "insecure-random", - message: "Math.random() is not cryptographically secure, use crypto.randomBytes()", - code: match.line.trim() - }) - } - }) - } - - // Check for missing input validation - const functionMatches = Grep("(function|const.*=.*\\(|async.*\\()", { - path: file.path, - "-n": true - }) - if (functionMatches) { - functionMatches.forEach(match => { - // Simple heuristic: check if function has parameters but no validation - if (match.line.includes("(") && !match.line.includes("()")) { - const nextLines = content.split("\n").slice(match.lineNumber, match.lineNumber + 5).join("\n") - const hasValidation = nextLines.match(/if\s*\(|throw|assert|validate|check/) - - if (!hasValidation && !match.line.includes("test") && !match.line.includes("mock")) { - issues.low.push({ - file: file.path, - line: match.lineNumber, - type: "missing-validation", - message: "Function parameters should be validated", - code: match.line.trim() - }) - } - } - }) - } - } - - return issues -} -``` - -### 3. Architecture Review - -```javascript -function reviewArchitecture(files) { - const issues = { - critical: [], - high: [], - medium: [], - low: [] - } - - for (const file of files) { - const content = file.content - const lines = content.split("\n") - - // Check for parent directory imports - const importMatches = Grep("from\\s+['\"](\\.\\./)+", { - path: file.path, - "-n": true - }) - if (importMatches) { - importMatches.forEach(match => { - const parentLevels = (match.line.match(/\.\.\//g) || []).length - - if (parentLevels > 2) { - issues.high.push({ - file: file.path, - line: match.lineNumber, - type: "excessive-parent-imports", - message: `Import traverses ${parentLevels} parent directories, consider restructuring`, - code: match.line.trim() - }) - } else if (parentLevels === 2) { - issues.medium.push({ - file: file.path, - line: match.lineNumber, - type: "parent-imports", - message: "Consider using absolute imports or restructuring modules", - code: match.line.trim() - }) - } - }) - } - - // Check for large files - const lineCount = lines.length - if (lineCount > 500) { - issues.medium.push({ - file: file.path, - line: 1, - type: "large-file", - message: `File has ${lineCount} lines, consider splitting into smaller modules`, - code: `Total lines: ${lineCount}` - }) - } - - // Check for circular dependencies (simple heuristic) - const imports = lines - .filter(line => line.match(/^import.*from/)) - .map(line => { - const match = line.match(/from\s+['"](.+?)['"]/) - return match ? match[1] : null - }) - .filter(Boolean) - - // Check if any imported file imports this file back - for (const importPath of imports) { - const resolvedPath = resolveImportPath(file.path, importPath) - if (resolvedPath && Bash(`test -f ${resolvedPath}`).exitCode === 0) { - const importedContent = Read(resolvedPath) - const reverseImport = importedContent.includes(file.path.replace(/\.[jt]sx?$/, "")) - - if (reverseImport) { - issues.critical.push({ - file: file.path, - line: 1, - type: "circular-dependency", - message: `Circular dependency detected with ${resolvedPath}`, - code: `${file.path} ↔ ${resolvedPath}` - }) - } - } - } - - // Check for tight coupling (many imports from same module) - const importCounts = {} - imports.forEach(imp => { - const baseModule = imp.split("/")[0] - importCounts[baseModule] = (importCounts[baseModule] || 0) + 1 - }) - - Object.entries(importCounts).forEach(([module, count]) => { - if (count > 5) { - issues.medium.push({ - file: file.path, - line: 1, - type: "tight-coupling", - message: `File imports ${count} items from '${module}', consider facade pattern`, - code: `Imports from ${module}: ${count}` - }) - } - }) - - // Check for missing abstractions (long functions) - const functionRegex = /(function|const.*=.*\(|async.*\()/g - let match - while ((match = functionRegex.exec(content)) !== null) { - const startLine = content.substring(0, match.index).split("\n").length - const functionBody = extractFunctionBody(content, match.index) - const functionLines = functionBody.split("\n").length - - if (functionLines > 50) { - issues.medium.push({ - file: file.path, - line: startLine, - type: "long-function", - message: `Function has ${functionLines} lines, consider extracting smaller functions`, - code: match[0].trim() - }) - } - } - } - - return issues -} - -function resolveImportPath(fromFile, importPath) { - if (importPath.startsWith(".")) { - const dir = fromFile.substring(0, fromFile.lastIndexOf("/")) - const resolved = `${dir}/${importPath}`.replace(/\/\.\//g, "/") - - // Try with extensions - for (const ext of [".ts", ".js", ".tsx", ".jsx"]) { - if (Bash(`test -f ${resolved}${ext}`).exitCode === 0) { - return `${resolved}${ext}` - } - } - } - return null -} - -function extractFunctionBody(content, startIndex) { - let braceCount = 0 - let inFunction = false - let body = "" - - for (let i = startIndex; i < content.length; i++) { - const char = content[i] - - if (char === "{") { - braceCount++ - inFunction = true - } else if (char === "}") { - braceCount-- - } - - if (inFunction) { - body += char - } - - if (inFunction && braceCount === 0) { - break - } - } - - return body -} -``` - -### 4. Requirements Verification - -```javascript -function verifyRequirements(plan, files, gitDiff) { - const issues = { - critical: [], - high: [], - medium: [], - low: [] - } - - // Extract acceptance criteria from plan - const acceptanceCriteria = extractAcceptanceCriteria(plan) - - // Verify each criterion - for (const criterion of acceptanceCriteria) { - const verified = verifyCriterion(criterion, files, gitDiff) - - if (!verified.met) { - issues.high.push({ - file: "plan", - line: criterion.lineNumber, - type: "unmet-acceptance-criteria", - message: `Acceptance criterion not met: ${criterion.text}`, - code: criterion.text - }) - } else if (verified.partial) { - issues.medium.push({ - file: "plan", - line: criterion.lineNumber, - type: "partial-acceptance-criteria", - message: `Acceptance criterion partially met: ${criterion.text}`, - code: criterion.text - }) - } - } - - // Check for missing error handling - const errorHandlingRequired = plan.match(/error handling|exception|validation/i) - if (errorHandlingRequired) { - const hasErrorHandling = files.some(file => - file.content.match(/try\s*\{|catch\s*\(|throw\s+new|\.catch\(/) - ) - - if (!hasErrorHandling) { - issues.high.push({ - file: "implementation", - line: 1, - type: "missing-error-handling", - message: "Plan requires error handling but none found in implementation", - code: "No try-catch or error handling detected" - }) - } - } - - // Check for missing tests - const testingRequired = plan.match(/test|testing|coverage/i) - if (testingRequired) { - const hasTests = files.some(file => - file.path.match(/\.(test|spec)\.[jt]sx?$/) - ) - - if (!hasTests) { - issues.medium.push({ - file: "implementation", - line: 1, - type: "missing-tests", - message: "Plan requires tests but no test files found", - code: "No test files detected" - }) - } - } - - return issues -} - -function extractAcceptanceCriteria(plan) { - const criteria = [] - const lines = plan.split("\n") - - let inAcceptanceSection = false - lines.forEach((line, idx) => { - if (line.match(/acceptance criteria/i)) { - inAcceptanceSection = true - } else if (line.match(/^##/)) { - inAcceptanceSection = false - } else if (inAcceptanceSection && line.match(/^[-*]\s+/)) { - criteria.push({ - text: line.replace(/^[-*]\s+/, "").trim(), - lineNumber: idx + 1 - }) - } - }) - - return criteria -} - -function verifyCriterion(criterion, files, gitDiff) { - // Extract keywords from criterion - const keywords = criterion.text.toLowerCase().match(/\b\w{4,}\b/g) || [] - - // Check if keywords appear in implementation - let matchCount = 0 - for (const file of files) { - const content = file.content.toLowerCase() - for (const keyword of keywords) { - if (content.includes(keyword)) { - matchCount++ - } - } - } - - const matchRatio = matchCount / keywords.length - - return { - met: matchRatio >= 0.7, - partial: matchRatio >= 0.4 && matchRatio < 0.7, - matchRatio: matchRatio - } -} -``` - -## Verdict Determination - -```javascript -function determineVerdict(qualityIssues, securityIssues, architectureIssues, requirementIssues) { - const allIssues = { - critical: [ - ...qualityIssues.critical, - ...securityIssues.critical, - ...architectureIssues.critical, - ...requirementIssues.critical - ], - high: [ - ...qualityIssues.high, - ...securityIssues.high, - ...architectureIssues.high, - ...requirementIssues.high - ], - medium: [ - ...qualityIssues.medium, - ...securityIssues.medium, - ...architectureIssues.medium, - ...requirementIssues.medium - ], - low: [ - ...qualityIssues.low, - ...securityIssues.low, - ...architectureIssues.low, - ...requirementIssues.low - ] - } - - // BLOCK: Any critical issues - if (allIssues.critical.length > 0) { - return { - verdict: "BLOCK", - reason: `${allIssues.critical.length} critical issue(s) must be fixed`, - blocking_issues: allIssues.critical - } - } - - // CONDITIONAL: High or medium issues - if (allIssues.high.length > 0 || allIssues.medium.length > 0) { - return { - verdict: "CONDITIONAL", - reason: `${allIssues.high.length} high and ${allIssues.medium.length} medium issue(s) should be addressed`, - blocking_issues: [] - } - } - - // APPROVE: Only low issues or none - return { - verdict: "APPROVE", - reason: allIssues.low.length > 0 - ? `${allIssues.low.length} low-priority issue(s) noted` - : "No issues found", - blocking_issues: [] - } -} -``` - -## Report Formatting - -```javascript -function formatCodeReviewReport(report) { - const { verdict, dimensions, recommendations, blocking_issues } = report - - let markdown = `# Code Review Report\n\n` - markdown += `**Verdict**: ${verdict}\n\n` - - if (blocking_issues.length > 0) { - markdown += `## Blocking Issues\n\n` - blocking_issues.forEach(issue => { - markdown += `- **${issue.type}** (${issue.file}:${issue.line})\n` - markdown += ` ${issue.message}\n` - markdown += ` \`\`\`\n ${issue.code}\n \`\`\`\n\n` - }) - } - - markdown += `## Review Dimensions\n\n` - - markdown += `### Quality Issues\n` - markdown += formatIssuesByDimension(dimensions.quality) - - markdown += `### Security Issues\n` - markdown += formatIssuesByDimension(dimensions.security) - - markdown += `### Architecture Issues\n` - markdown += formatIssuesByDimension(dimensions.architecture) - - markdown += `### Requirements Issues\n` - markdown += formatIssuesByDimension(dimensions.requirements) - - if (recommendations.length > 0) { - markdown += `## Recommendations\n\n` - recommendations.forEach((rec, i) => { - markdown += `${i + 1}. ${rec}\n` - }) - } - - return markdown -} - -function formatIssuesByDimension(issues) { - let markdown = "" - - const severities = ["critical", "high", "medium", "low"] - severities.forEach(severity => { - if (issues[severity].length > 0) { - markdown += `\n**${severity.toUpperCase()}** (${issues[severity].length})\n\n` - issues[severity].forEach(issue => { - markdown += `- ${issue.message} (${issue.file}:${issue.line})\n` - markdown += ` \`${issue.code}\`\n\n` - }) - } - }) - - return markdown || "No issues found.\n\n" -} -``` diff --git a/.claude/skills_lib/team-lifecycle-v2/roles/reviewer/commands/spec-quality.md b/.claude/skills_lib/team-lifecycle-v2/roles/reviewer/commands/spec-quality.md deleted file mode 100644 index 63aa6f74..00000000 --- a/.claude/skills_lib/team-lifecycle-v2/roles/reviewer/commands/spec-quality.md +++ /dev/null @@ -1,845 +0,0 @@ -# Spec Quality Command - -## Purpose -5-dimension spec quality check with readiness report generation and quality gate determination. - -## Quality Dimensions - -### 1. Completeness (Weight: 25%) - -```javascript -function scoreCompleteness(specDocs) { - const requiredSections = { - "product-brief": [ - "Vision Statement", - "Problem Statement", - "Target Audience", - "Success Metrics", - "Constraints" - ], - "prd": [ - "Goals", - "Requirements", - "User Stories", - "Acceptance Criteria", - "Non-Functional Requirements" - ], - "architecture": [ - "System Overview", - "Component Design", - "Data Models", - "API Specifications", - "Technology Stack" - ], - "user-stories": [ - "Story List", - "Acceptance Criteria", - "Priority", - "Estimation" - ], - "implementation-plan": [ - "Task Breakdown", - "Dependencies", - "Timeline", - "Resource Allocation" - ], - "test-strategy": [ - "Test Scope", - "Test Cases", - "Coverage Goals", - "Test Environment" - ] - } - - let totalScore = 0 - let totalWeight = 0 - const details = [] - - for (const doc of specDocs) { - const phase = doc.phase - const expectedSections = requiredSections[phase] || [] - - if (expectedSections.length === 0) continue - - let presentCount = 0 - let substantialCount = 0 - - for (const section of expectedSections) { - const sectionRegex = new RegExp(`##\\s+${section}`, "i") - const sectionMatch = doc.content.match(sectionRegex) - - if (sectionMatch) { - presentCount++ - - // Check if section has substantial content (not just header) - const sectionIndex = doc.content.indexOf(sectionMatch[0]) - const nextSectionIndex = doc.content.indexOf("\n##", sectionIndex + 1) - const sectionContent = nextSectionIndex > -1 - ? doc.content.substring(sectionIndex, nextSectionIndex) - : doc.content.substring(sectionIndex) - - // Substantial = more than 100 chars excluding header - const contentWithoutHeader = sectionContent.replace(sectionRegex, "").trim() - if (contentWithoutHeader.length > 100) { - substantialCount++ - } - } - } - - const presentRatio = presentCount / expectedSections.length - const substantialRatio = substantialCount / expectedSections.length - - // Score: 50% for presence, 50% for substance - const docScore = (presentRatio * 50) + (substantialRatio * 50) - - totalScore += docScore - totalWeight += 100 - - details.push({ - phase: phase, - score: docScore, - present: presentCount, - substantial: substantialCount, - expected: expectedSections.length, - missing: expectedSections.filter(s => !doc.content.match(new RegExp(`##\\s+${s}`, "i"))) - }) - } - - const overallScore = totalWeight > 0 ? (totalScore / totalWeight) * 100 : 0 - - return { - score: overallScore, - weight: 25, - weighted_score: overallScore * 0.25, - details: details - } -} -``` - -### 2. Consistency (Weight: 20%) - -```javascript -function scoreConsistency(specDocs) { - const issues = [] - - // 1. Terminology consistency - const terminologyMap = new Map() - - for (const doc of specDocs) { - // Extract key terms (capitalized phrases, technical terms) - const terms = doc.content.match(/\b[A-Z][a-z]+(?:\s+[A-Z][a-z]+)*\b/g) || [] - - terms.forEach(term => { - const normalized = term.toLowerCase() - if (!terminologyMap.has(normalized)) { - terminologyMap.set(normalized, new Set()) - } - terminologyMap.get(normalized).add(term) - }) - } - - // Find inconsistent terminology (same concept, different casing/spelling) - terminologyMap.forEach((variants, normalized) => { - if (variants.size > 1) { - issues.push({ - type: "terminology", - severity: "medium", - message: `Inconsistent terminology: ${[...variants].join(", ")}`, - suggestion: `Standardize to one variant` - }) - } - }) - - // 2. Format consistency - const headerStyles = new Map() - for (const doc of specDocs) { - const headers = doc.content.match(/^#{1,6}\s+.+$/gm) || [] - headers.forEach(header => { - const level = header.match(/^#+/)[0].length - const style = header.includes("**") ? "bold" : "plain" - const key = `level-${level}` - - if (!headerStyles.has(key)) { - headerStyles.set(key, new Set()) - } - headerStyles.get(key).add(style) - }) - } - - headerStyles.forEach((styles, level) => { - if (styles.size > 1) { - issues.push({ - type: "format", - severity: "low", - message: `Inconsistent header style at ${level}: ${[...styles].join(", ")}`, - suggestion: "Use consistent header formatting" - }) - } - }) - - // 3. Reference consistency - const references = new Map() - for (const doc of specDocs) { - // Extract references to other documents/sections - const refs = doc.content.match(/\[.*?\]\(.*?\)/g) || [] - refs.forEach(ref => { - const linkMatch = ref.match(/\((.*?)\)/) - if (linkMatch) { - const link = linkMatch[1] - if (!references.has(link)) { - references.set(link, []) - } - references.get(link).push(doc.phase) - } - }) - } - - // Check for broken references - references.forEach((sources, link) => { - if (link.startsWith("./") || link.startsWith("../")) { - // Check if file exists - const exists = Bash(`test -f ${link}`).exitCode === 0 - if (!exists) { - issues.push({ - type: "reference", - severity: "high", - message: `Broken reference: ${link} (referenced in ${sources.join(", ")})`, - suggestion: "Fix or remove broken reference" - }) - } - } - }) - - // 4. Naming convention consistency - const namingPatterns = { - camelCase: /\b[a-z]+(?:[A-Z][a-z]+)+\b/g, - PascalCase: /\b[A-Z][a-z]+(?:[A-Z][a-z]+)+\b/g, - snake_case: /\b[a-z]+(?:_[a-z]+)+\b/g, - kebab_case: /\b[a-z]+(?:-[a-z]+)+\b/g - } - - const namingCounts = {} - for (const doc of specDocs) { - Object.entries(namingPatterns).forEach(([pattern, regex]) => { - const matches = doc.content.match(regex) || [] - namingCounts[pattern] = (namingCounts[pattern] || 0) + matches.length - }) - } - - const dominantPattern = Object.entries(namingCounts) - .sort((a, b) => b[1] - a[1])[0]?.[0] - - Object.entries(namingCounts).forEach(([pattern, count]) => { - if (pattern !== dominantPattern && count > 10) { - issues.push({ - type: "naming", - severity: "low", - message: `Mixed naming conventions: ${pattern} (${count} occurrences) vs ${dominantPattern}`, - suggestion: `Standardize to ${dominantPattern}` - }) - } - }) - - // Calculate score based on issues - const severityWeights = { high: 10, medium: 5, low: 2 } - const totalPenalty = issues.reduce((sum, issue) => sum + severityWeights[issue.severity], 0) - const maxPenalty = 100 // Arbitrary max for normalization - - const score = Math.max(0, 100 - (totalPenalty / maxPenalty) * 100) - - return { - score: score, - weight: 20, - weighted_score: score * 0.20, - issues: issues, - details: { - terminology_issues: issues.filter(i => i.type === "terminology").length, - format_issues: issues.filter(i => i.type === "format").length, - reference_issues: issues.filter(i => i.type === "reference").length, - naming_issues: issues.filter(i => i.type === "naming").length - } - } -} -``` - -### 3. Traceability (Weight: 25%) - -```javascript -function scoreTraceability(specDocs) { - const chains = [] - - // Extract traceability elements - const goals = extractElements(specDocs, "product-brief", /^[-*]\s+Goal:\s*(.+)$/gm) - const requirements = extractElements(specDocs, "prd", /^[-*]\s+(?:REQ-\d+|Requirement):\s*(.+)$/gm) - const components = extractElements(specDocs, "architecture", /^[-*]\s+(?:Component|Module):\s*(.+)$/gm) - const stories = extractElements(specDocs, "user-stories", /^[-*]\s+(?:US-\d+|Story):\s*(.+)$/gm) - - // Build traceability chains: Goals → Requirements → Components → Stories - for (const goal of goals) { - const chain = { - goal: goal.text, - requirements: [], - components: [], - stories: [], - complete: false - } - - // Find requirements that reference this goal - const goalKeywords = extractKeywords(goal.text) - for (const req of requirements) { - if (hasKeywordOverlap(req.text, goalKeywords, 0.3)) { - chain.requirements.push(req.text) - - // Find components that implement this requirement - const reqKeywords = extractKeywords(req.text) - for (const comp of components) { - if (hasKeywordOverlap(comp.text, reqKeywords, 0.3)) { - chain.components.push(comp.text) - } - } - - // Find stories that implement this requirement - for (const story of stories) { - if (hasKeywordOverlap(story.text, reqKeywords, 0.3)) { - chain.stories.push(story.text) - } - } - } - } - - // Check if chain is complete - chain.complete = chain.requirements.length > 0 && - chain.components.length > 0 && - chain.stories.length > 0 - - chains.push(chain) - } - - // Calculate score - const completeChains = chains.filter(c => c.complete).length - const totalChains = chains.length - const score = totalChains > 0 ? (completeChains / totalChains) * 100 : 0 - - // Identify weak links - const weakLinks = [] - chains.forEach((chain, idx) => { - if (!chain.complete) { - if (chain.requirements.length === 0) { - weakLinks.push(`Goal ${idx + 1} has no linked requirements`) - } - if (chain.components.length === 0) { - weakLinks.push(`Goal ${idx + 1} has no linked components`) - } - if (chain.stories.length === 0) { - weakLinks.push(`Goal ${idx + 1} has no linked stories`) - } - } - }) - - return { - score: score, - weight: 25, - weighted_score: score * 0.25, - details: { - total_chains: totalChains, - complete_chains: completeChains, - weak_links: weakLinks - }, - chains: chains - } -} - -function extractElements(specDocs, phase, regex) { - const elements = [] - const doc = specDocs.find(d => d.phase === phase) - - if (doc) { - let match - while ((match = regex.exec(doc.content)) !== null) { - elements.push({ - text: match[1].trim(), - phase: phase - }) - } - } - - return elements -} - -function extractKeywords(text) { - // Extract meaningful words (4+ chars, not common words) - const commonWords = new Set(["that", "this", "with", "from", "have", "will", "should", "must", "can"]) - const words = text.toLowerCase().match(/\b\w{4,}\b/g) || [] - return words.filter(w => !commonWords.has(w)) -} - -function hasKeywordOverlap(text, keywords, threshold) { - const textLower = text.toLowerCase() - const matchCount = keywords.filter(kw => textLower.includes(kw)).length - return matchCount / keywords.length >= threshold -} -``` - -### 4. Depth (Weight: 20%) - -```javascript -function scoreDepth(specDocs) { - const dimensions = [] - - // 1. Acceptance Criteria Testability - const acDoc = specDocs.find(d => d.phase === "prd" || d.phase === "user-stories") - if (acDoc) { - const acMatches = acDoc.content.match(/Acceptance Criteria:[\s\S]*?(?=\n##|\n\n[-*]|$)/gi) || [] - let testableCount = 0 - let totalCount = 0 - - acMatches.forEach(section => { - const criteria = section.match(/^[-*]\s+(.+)$/gm) || [] - totalCount += criteria.length - - criteria.forEach(criterion => { - // Testable if contains measurable verbs or specific conditions - const testablePatterns = [ - /\b(should|must|will)\s+(display|show|return|validate|check|verify|calculate|send|receive)\b/i, - /\b(when|if|given)\b.*\b(then|should|must)\b/i, - /\b\d+\b/, // Contains numbers (measurable) - /\b(success|error|fail|pass)\b/i - ] - - const isTestable = testablePatterns.some(pattern => pattern.test(criterion)) - if (isTestable) testableCount++ - }) - }) - - const acScore = totalCount > 0 ? (testableCount / totalCount) * 100 : 0 - dimensions.push({ - name: "Acceptance Criteria Testability", - score: acScore, - testable: testableCount, - total: totalCount - }) - } - - // 2. ADR Justification - const archDoc = specDocs.find(d => d.phase === "architecture") - if (archDoc) { - const adrMatches = archDoc.content.match(/##\s+(?:ADR|Decision)[\s\S]*?(?=\n##|$)/gi) || [] - let justifiedCount = 0 - let totalCount = adrMatches.length - - adrMatches.forEach(adr => { - // Justified if contains rationale, alternatives, or consequences - const hasJustification = adr.match(/\b(rationale|reason|because|alternative|consequence|trade-?off)\b/i) - if (hasJustification) justifiedCount++ - }) - - const adrScore = totalCount > 0 ? (justifiedCount / totalCount) * 100 : 100 // Default 100 if no ADRs - dimensions.push({ - name: "ADR Justification", - score: adrScore, - justified: justifiedCount, - total: totalCount - }) - } - - // 3. User Stories Estimability - const storiesDoc = specDocs.find(d => d.phase === "user-stories") - if (storiesDoc) { - const storyMatches = storiesDoc.content.match(/^[-*]\s+(?:US-\d+|Story)[\s\S]*?(?=\n[-*]|$)/gim) || [] - let estimableCount = 0 - let totalCount = storyMatches.length - - storyMatches.forEach(story => { - // Estimable if has clear scope, AC, and no ambiguity - const hasScope = story.match(/\b(as a|I want|so that)\b/i) - const hasAC = story.match(/acceptance criteria/i) - const hasEstimate = story.match(/\b(points?|hours?|days?|estimate)\b/i) - - if ((hasScope && hasAC) || hasEstimate) estimableCount++ - }) - - const storiesScore = totalCount > 0 ? (estimableCount / totalCount) * 100 : 0 - dimensions.push({ - name: "User Stories Estimability", - score: storiesScore, - estimable: estimableCount, - total: totalCount - }) - } - - // 4. Technical Detail Sufficiency - const techDocs = specDocs.filter(d => d.phase === "architecture" || d.phase === "implementation-plan") - let detailScore = 0 - - if (techDocs.length > 0) { - const detailIndicators = [ - /```[\s\S]*?```/, // Code blocks - /\b(API|endpoint|schema|model|interface|class|function)\b/i, - /\b(GET|POST|PUT|DELETE|PATCH)\b/, // HTTP methods - /\b(database|table|collection|index)\b/i, - /\b(authentication|authorization|security)\b/i - ] - - let indicatorCount = 0 - techDocs.forEach(doc => { - detailIndicators.forEach(pattern => { - if (pattern.test(doc.content)) indicatorCount++ - }) - }) - - detailScore = Math.min(100, (indicatorCount / (detailIndicators.length * techDocs.length)) * 100) - dimensions.push({ - name: "Technical Detail Sufficiency", - score: detailScore, - indicators_found: indicatorCount, - indicators_expected: detailIndicators.length * techDocs.length - }) - } - - // Calculate overall depth score - const overallScore = dimensions.reduce((sum, d) => sum + d.score, 0) / dimensions.length - - return { - score: overallScore, - weight: 20, - weighted_score: overallScore * 0.20, - dimensions: dimensions - } -} -``` - -### 5. Requirement Coverage (Weight: 10%) - -```javascript -function scoreRequirementCoverage(specDocs, originalRequirements) { - // Extract original requirements from task description or initial brief - const originalReqs = originalRequirements || extractOriginalRequirements(specDocs) - - if (originalReqs.length === 0) { - return { - score: 100, // No requirements to cover - weight: 10, - weighted_score: 10, - details: { - total: 0, - covered: 0, - uncovered: [] - } - } - } - - // Extract all requirements from spec documents - const specReqs = [] - for (const doc of specDocs) { - const reqMatches = doc.content.match(/^[-*]\s+(?:REQ-\d+|Requirement|Feature):\s*(.+)$/gm) || [] - reqMatches.forEach(match => { - specReqs.push(match.replace(/^[-*]\s+(?:REQ-\d+|Requirement|Feature):\s*/, "").trim()) - }) - } - - // Map original requirements to spec requirements - const coverage = [] - for (const origReq of originalReqs) { - const keywords = extractKeywords(origReq) - const covered = specReqs.some(specReq => hasKeywordOverlap(specReq, keywords, 0.4)) - - coverage.push({ - requirement: origReq, - covered: covered - }) - } - - const coveredCount = coverage.filter(c => c.covered).length - const score = (coveredCount / originalReqs.length) * 100 - - return { - score: score, - weight: 10, - weighted_score: score * 0.10, - details: { - total: originalReqs.length, - covered: coveredCount, - uncovered: coverage.filter(c => !c.covered).map(c => c.requirement) - } - } -} - -function extractOriginalRequirements(specDocs) { - // Try to find original requirements in product brief - const briefDoc = specDocs.find(d => d.phase === "product-brief") - if (!briefDoc) return [] - - const reqSection = briefDoc.content.match(/##\s+(?:Requirements|Objectives)[\s\S]*?(?=\n##|$)/i) - if (!reqSection) return [] - - const reqs = reqSection[0].match(/^[-*]\s+(.+)$/gm) || [] - return reqs.map(r => r.replace(/^[-*]\s+/, "").trim()) -} -``` - -## Quality Gate Determination - -```javascript -function determineQualityGate(overallScore, coverageScore) { - // PASS: Score ≥80% AND coverage ≥70% - if (overallScore >= 80 && coverageScore >= 70) { - return { - gate: "PASS", - message: "Specification meets quality standards and is ready for implementation", - action: "Proceed to implementation phase" - } - } - - // FAIL: Score <60% OR coverage <50% - if (overallScore < 60 || coverageScore < 50) { - return { - gate: "FAIL", - message: "Specification requires major revisions before implementation", - action: "Address critical gaps and resubmit for review" - } - } - - // REVIEW: Between PASS and FAIL - return { - gate: "REVIEW", - message: "Specification needs improvements but may proceed with caution", - action: "Address recommendations and consider re-review" - } -} -``` - -## Readiness Report Generation - -```javascript -function formatReadinessReport(report, specDocs) { - const { overall_score, quality_gate, dimensions, phase_gates } = report - - let markdown = `# Specification Readiness Report\n\n` - markdown += `**Generated**: ${new Date().toISOString()}\n\n` - markdown += `**Overall Score**: ${overall_score.toFixed(1)}%\n\n` - markdown += `**Quality Gate**: ${quality_gate.gate} - ${quality_gate.message}\n\n` - markdown += `**Recommended Action**: ${quality_gate.action}\n\n` - - markdown += `---\n\n` - - markdown += `## Dimension Scores\n\n` - markdown += `| Dimension | Score | Weight | Weighted Score |\n` - markdown += `|-----------|-------|--------|----------------|\n` - - Object.entries(dimensions).forEach(([name, data]) => { - markdown += `| ${name} | ${data.score.toFixed(1)}% | ${data.weight}% | ${data.weighted_score.toFixed(1)}% |\n` - }) - - markdown += `\n---\n\n` - - // Completeness Details - markdown += `## Completeness Analysis\n\n` - dimensions.completeness.details.forEach(detail => { - markdown += `### ${detail.phase}\n` - markdown += `- Score: ${detail.score.toFixed(1)}%\n` - markdown += `- Sections Present: ${detail.present}/${detail.expected}\n` - markdown += `- Substantial Content: ${detail.substantial}/${detail.expected}\n` - if (detail.missing.length > 0) { - markdown += `- Missing: ${detail.missing.join(", ")}\n` - } - markdown += `\n` - }) - - // Consistency Details - markdown += `## Consistency Analysis\n\n` - if (dimensions.consistency.issues.length > 0) { - markdown += `**Issues Found**: ${dimensions.consistency.issues.length}\n\n` - dimensions.consistency.issues.forEach(issue => { - markdown += `- **${issue.severity.toUpperCase()}**: ${issue.message}\n` - markdown += ` *Suggestion*: ${issue.suggestion}\n\n` - }) - } else { - markdown += `No consistency issues found.\n\n` - } - - // Traceability Details - markdown += `## Traceability Analysis\n\n` - markdown += `- Complete Chains: ${dimensions.traceability.details.complete_chains}/${dimensions.traceability.details.total_chains}\n\n` - if (dimensions.traceability.details.weak_links.length > 0) { - markdown += `**Weak Links**:\n` - dimensions.traceability.details.weak_links.forEach(link => { - markdown += `- ${link}\n` - }) - markdown += `\n` - } - - // Depth Details - markdown += `## Depth Analysis\n\n` - dimensions.depth.dimensions.forEach(dim => { - markdown += `### ${dim.name}\n` - markdown += `- Score: ${dim.score.toFixed(1)}%\n` - if (dim.testable !== undefined) { - markdown += `- Testable: ${dim.testable}/${dim.total}\n` - } - if (dim.justified !== undefined) { - markdown += `- Justified: ${dim.justified}/${dim.total}\n` - } - if (dim.estimable !== undefined) { - markdown += `- Estimable: ${dim.estimable}/${dim.total}\n` - } - markdown += `\n` - }) - - // Coverage Details - markdown += `## Requirement Coverage\n\n` - markdown += `- Covered: ${dimensions.coverage.details.covered}/${dimensions.coverage.details.total}\n` - if (dimensions.coverage.details.uncovered.length > 0) { - markdown += `\n**Uncovered Requirements**:\n` - dimensions.coverage.details.uncovered.forEach(req => { - markdown += `- ${req}\n` - }) - } - markdown += `\n` - - // Phase Gates - if (phase_gates) { - markdown += `---\n\n` - markdown += `## Phase-Level Quality Gates\n\n` - Object.entries(phase_gates).forEach(([phase, gate]) => { - markdown += `### ${phase}\n` - markdown += `- Gate: ${gate.status}\n` - markdown += `- Score: ${gate.score.toFixed(1)}%\n` - if (gate.issues.length > 0) { - markdown += `- Issues: ${gate.issues.join(", ")}\n` - } - markdown += `\n` - }) - } - - return markdown -} -``` - -## Spec Summary Generation - -```javascript -function formatSpecSummary(specDocs, report) { - let markdown = `# Specification Summary\n\n` - - markdown += `**Overall Quality Score**: ${report.overall_score.toFixed(1)}%\n` - markdown += `**Quality Gate**: ${report.quality_gate.gate}\n\n` - - markdown += `---\n\n` - - // Document Overview - markdown += `## Documents Reviewed\n\n` - specDocs.forEach(doc => { - markdown += `### ${doc.phase}\n` - markdown += `- Path: ${doc.path}\n` - markdown += `- Size: ${doc.content.length} characters\n` - - // Extract key sections - const sections = doc.content.match(/^##\s+(.+)$/gm) || [] - if (sections.length > 0) { - markdown += `- Sections: ${sections.map(s => s.replace(/^##\s+/, "")).join(", ")}\n` - } - markdown += `\n` - }) - - markdown += `---\n\n` - - // Key Findings - markdown += `## Key Findings\n\n` - - // Strengths - const strengths = [] - Object.entries(report.dimensions).forEach(([name, data]) => { - if (data.score >= 80) { - strengths.push(`${name}: ${data.score.toFixed(1)}%`) - } - }) - - if (strengths.length > 0) { - markdown += `### Strengths\n` - strengths.forEach(s => markdown += `- ${s}\n`) - markdown += `\n` - } - - // Areas for Improvement - const improvements = [] - Object.entries(report.dimensions).forEach(([name, data]) => { - if (data.score < 70) { - improvements.push(`${name}: ${data.score.toFixed(1)}%`) - } - }) - - if (improvements.length > 0) { - markdown += `### Areas for Improvement\n` - improvements.forEach(i => markdown += `- ${i}\n`) - markdown += `\n` - } - - // Recommendations - if (report.recommendations && report.recommendations.length > 0) { - markdown += `### Recommendations\n` - report.recommendations.forEach((rec, i) => { - markdown += `${i + 1}. ${rec}\n` - }) - markdown += `\n` - } - - return markdown -} -``` - -## Phase-Level Quality Gates - -```javascript -function calculatePhaseGates(specDocs) { - const gates = {} - - for (const doc of specDocs) { - const phase = doc.phase - const issues = [] - let score = 100 - - // Check minimum content threshold - if (doc.content.length < 500) { - issues.push("Insufficient content") - score -= 30 - } - - // Check for required sections (phase-specific) - const requiredSections = getRequiredSections(phase) - const missingSections = requiredSections.filter(section => - !doc.content.match(new RegExp(`##\\s+${section}`, "i")) - ) - - if (missingSections.length > 0) { - issues.push(`Missing sections: ${missingSections.join(", ")}`) - score -= missingSections.length * 15 - } - - // Determine gate status - let status = "PASS" - if (score < 60) status = "FAIL" - else if (score < 80) status = "REVIEW" - - gates[phase] = { - status: status, - score: Math.max(0, score), - issues: issues - } - } - - return gates -} - -function getRequiredSections(phase) { - const sectionMap = { - "product-brief": ["Vision", "Problem", "Target Audience"], - "prd": ["Goals", "Requirements", "User Stories"], - "architecture": ["Overview", "Components", "Data Models"], - "user-stories": ["Stories", "Acceptance Criteria"], - "implementation-plan": ["Tasks", "Dependencies"], - "test-strategy": ["Test Cases", "Coverage"] - } - - return sectionMap[phase] || [] -} -``` diff --git a/.claude/skills_lib/team-lifecycle-v2/roles/reviewer/role.md b/.claude/skills_lib/team-lifecycle-v2/roles/reviewer/role.md deleted file mode 100644 index 61f9702a..00000000 --- a/.claude/skills_lib/team-lifecycle-v2/roles/reviewer/role.md +++ /dev/null @@ -1,429 +0,0 @@ -# Reviewer Role - -## 1. Role Identity - -- **Name**: reviewer -- **Task Prefix**: REVIEW-* + QUALITY-* -- **Output Tag**: `[reviewer]` -- **Responsibility**: Discover Task → Branch by Prefix → Review/Score → Report - -## 2. Role Boundaries - -### MUST -- Only process REVIEW-* and QUALITY-* tasks -- Communicate only with coordinator -- Generate readiness-report.md for QUALITY tasks -- Tag all outputs with `[reviewer]` - -### MUST NOT -- Create tasks -- Contact other workers directly -- Modify source code -- Skip quality dimensions -- Approve without verification - -## 3. Message Types - -| Type | Direction | Purpose | Format | -|------|-----------|---------|--------| -| `task_request` | FROM coordinator | Receive REVIEW-*/QUALITY-* task assignment | `{ type: "task_request", task_id, description, review_mode }` | -| `task_complete` | TO coordinator | Report review success | `{ type: "task_complete", task_id, status: "success", verdict, score, issues }` | -| `task_failed` | TO coordinator | Report review failure | `{ type: "task_failed", task_id, error }` | - -## 4. Message Bus - -**Primary**: Use `team_msg` for all coordinator communication with `[reviewer]` tag: -```javascript -// Code review completion -team_msg({ - to: "coordinator", - type: "task_complete", - task_id: "REVIEW-001", - status: "success", - verdict: "APPROVE", - issues: { critical: 0, high: 2, medium: 5, low: 3 }, - recommendations: ["Fix console.log statements", "Add error handling"] -}, "[reviewer]") - -// Spec quality completion -team_msg({ - to: "coordinator", - type: "task_complete", - task_id: "QUALITY-001", - status: "success", - overall_score: 85.5, - quality_gate: "PASS", - dimensions: { - completeness: 90, - consistency: 85, - traceability: 80, - depth: 88, - coverage: 82 - } -}, "[reviewer]") -``` - -**CLI Fallback**: When message bus unavailable, write to `.workflow/.team/messages/reviewer-{timestamp}.json` - -## 5. Toolbox - -### Available Commands -- `commands/code-review.md` - 4-dimension code review (quality, security, architecture, requirements) -- `commands/spec-quality.md` - 5-dimension spec quality check (completeness, consistency, traceability, depth, coverage) - -### CLI Capabilities -- None (uses Grep-based analysis) - -## 6. Execution (5-Phase) - Dual-Prefix - -### Phase 1: Task Discovery - -**Dual Prefix Filter**: -```javascript -const tasks = Glob(".workflow/.team/tasks/{REVIEW,QUALITY}-*.json") - .filter(task => task.status === "pending" && task.assigned_to === "reviewer") - -// Determine review mode -const reviewMode = task.task_id.startsWith("REVIEW-") ? "code" : "spec" -``` - -### Phase 2: Context Loading (Branch by Mode) - -**Code Review Context (REVIEW-*)**: -```javascript -if (reviewMode === "code") { - // Load plan - const planPath = task.metadata?.plan_path || ".workflow/plan.md" - const plan = Read(planPath) - - // Get git diff - const implTaskId = task.metadata?.impl_task_id - const gitDiff = Bash("git diff HEAD").stdout - - // Load modified files - const modifiedFiles = Bash("git diff --name-only HEAD").stdout.split("\n").filter(Boolean) - const fileContents = modifiedFiles.map(f => ({ - path: f, - content: Read(f) - })) - - // Load test results if available - const testTaskId = task.metadata?.test_task_id - const testResults = testTaskId ? Read(`.workflow/.team/tasks/${testTaskId}.json`) : null -} -``` - -**Spec Quality Context (QUALITY-*)**: -```javascript -if (reviewMode === "spec") { - // Load session folder - const sessionFolder = task.metadata?.session_folder || ".workflow/.sessions/latest" - - // Load quality gates - const qualityGates = task.metadata?.quality_gates || { - pass_threshold: 80, - fail_threshold: 60, - coverage_threshold: 70 - } - - // Load all spec documents - const specDocs = Glob(`${sessionFolder}/**/*.md`).map(path => ({ - path: path, - content: Read(path), - phase: extractPhase(path) - })) -} -``` - -### Phase 3: Review Execution (Delegate by Mode) - -**Code Review**: -```javascript -if (reviewMode === "code") { - const codeReviewCommand = Read("commands/code-review.md") - // Command handles: - // - reviewQuality (ts-ignore, any, console.log, empty catch) - // - reviewSecurity (eval/exec, secrets, SQL injection, XSS) - // - reviewArchitecture (parent imports, large files) - // - verifyRequirements (plan acceptance criteria vs implementation) - // - Verdict determination (BLOCK/CONDITIONAL/APPROVE) -} -``` - -**Spec Quality**: -```javascript -if (reviewMode === "spec") { - const specQualityCommand = Read("commands/spec-quality.md") - // Command handles: - // - scoreCompleteness (section content checks) - // - scoreConsistency (terminology, format, references) - // - scoreTraceability (goals → reqs → arch → stories chain) - // - scoreDepth (AC testable, ADRs justified, stories estimable) - // - scoreRequirementCoverage (original requirements → document mapping) - // - Quality gate determination (PASS ≥80%, FAIL <60%, else REVIEW) - // - readiness-report.md generation - // - spec-summary.md generation -} -``` - -### Phase 4: Report Generation (Branch by Mode) - -**Code Review Report**: -```javascript -if (reviewMode === "code") { - const report = { - verdict: verdict, // BLOCK | CONDITIONAL | APPROVE - dimensions: { - quality: qualityIssues, - security: securityIssues, - architecture: architectureIssues, - requirements: requirementIssues - }, - recommendations: recommendations, - blocking_issues: blockingIssues - } - - // Write review report - Write(`.workflow/.team/reviews/${task.task_id}-report.md`, formatCodeReviewReport(report)) -} -``` - -**Spec Quality Report**: -```javascript -if (reviewMode === "spec") { - const report = { - overall_score: overallScore, - quality_gate: qualityGate, // PASS | REVIEW | FAIL - dimensions: { - completeness: completenessScore, - consistency: consistencyScore, - traceability: traceabilityScore, - depth: depthScore, - coverage: coverageScore - }, - phase_gates: phaseGates, - recommendations: recommendations - } - - // Write readiness report - Write(`${sessionFolder}/readiness-report.md`, formatReadinessReport(report)) - - // Write spec summary - Write(`${sessionFolder}/spec-summary.md`, formatSpecSummary(specDocs, report)) -} -``` - -### Phase 5: Report to Coordinator (Branch by Mode) - -**Code Review Completion**: -```javascript -if (reviewMode === "code") { - team_msg({ - to: "coordinator", - type: "task_complete", - task_id: task.task_id, - status: "success", - verdict: verdict, - issues: { - critical: blockingIssues.length, - high: highIssues.length, - medium: mediumIssues.length, - low: lowIssues.length - }, - recommendations: recommendations, - report_path: `.workflow/.team/reviews/${task.task_id}-report.md`, - timestamp: new Date().toISOString() - }, "[reviewer]") -} -``` - -**Spec Quality Completion**: -```javascript -if (reviewMode === "spec") { - team_msg({ - to: "coordinator", - type: "task_complete", - task_id: task.task_id, - status: "success", - overall_score: overallScore, - quality_gate: qualityGate, - dimensions: { - completeness: completenessScore, - consistency: consistencyScore, - traceability: traceabilityScore, - depth: depthScore, - coverage: coverageScore - }, - report_path: `${sessionFolder}/readiness-report.md`, - summary_path: `${sessionFolder}/spec-summary.md`, - timestamp: new Date().toISOString() - }, "[reviewer]") -} -``` - -## 7. Code Review Dimensions - -### Quality Dimension - -**Anti-patterns**: -- `@ts-ignore` / `@ts-expect-error` without justification -- `any` type usage -- `console.log` in production code -- Empty catch blocks -- Magic numbers -- Duplicate code - -**Severity**: -- Critical: Empty catch, any in public APIs -- High: @ts-ignore without comment, console.log -- Medium: Magic numbers, duplicate code -- Low: Minor style issues - -### Security Dimension - -**Vulnerabilities**: -- `eval()` / `exec()` usage -- `innerHTML` / `dangerouslySetInnerHTML` -- Hardcoded secrets (API keys, passwords) -- SQL injection vectors -- XSS vulnerabilities -- Insecure dependencies - -**Severity**: -- Critical: Hardcoded secrets, SQL injection -- High: eval/exec, innerHTML -- Medium: Insecure dependencies -- Low: Missing input validation - -### Architecture Dimension - -**Issues**: -- Parent directory imports (`../../../`) -- Large files (>500 lines) -- Circular dependencies -- Missing abstractions -- Tight coupling - -**Severity**: -- Critical: Circular dependencies -- High: Excessive parent imports (>2 levels) -- Medium: Large files, tight coupling -- Low: Minor structure issues - -### Requirements Dimension - -**Verification**: -- Acceptance criteria coverage -- Feature completeness -- Edge case handling -- Error handling - -**Severity**: -- Critical: Missing core functionality -- High: Incomplete acceptance criteria -- Medium: Missing edge cases -- Low: Minor feature gaps - -## 8. Spec Quality Dimensions - -### Completeness (Weight: 25%) - -**Checks**: -- All required sections present -- Section content depth (not just headers) -- Cross-phase coverage -- Artifact completeness - -**Scoring**: -- 100%: All sections with substantial content -- 75%: All sections present, some thin -- 50%: Missing 1-2 sections -- 25%: Missing 3+ sections -- 0%: Critical sections missing - -### Consistency (Weight: 20%) - -**Checks**: -- Terminology consistency -- Format consistency -- Reference consistency -- Naming conventions - -**Scoring**: -- 100%: Fully consistent -- 75%: Minor inconsistencies (1-2) -- 50%: Moderate inconsistencies (3-5) -- 25%: Major inconsistencies (6+) -- 0%: Chaotic inconsistency - -### Traceability (Weight: 25%) - -**Checks**: -- Goals → Requirements chain -- Requirements → Architecture chain -- Architecture → User Stories chain -- Bidirectional references - -**Scoring**: -- 100%: Full traceability chain -- 75%: 1 weak link -- 50%: 2 weak links -- 25%: 3+ weak links -- 0%: No traceability - -### Depth (Weight: 20%) - -**Checks**: -- Acceptance criteria testable -- ADRs justified -- User stories estimable -- Technical details sufficient - -**Scoring**: -- 100%: All items detailed -- 75%: 1-2 shallow items -- 50%: 3-5 shallow items -- 25%: 6+ shallow items -- 0%: All items shallow - -### Coverage (Weight: 10%) - -**Checks**: -- Original requirements mapped -- All features documented -- All constraints addressed -- All stakeholders considered - -**Scoring**: -- 100%: Full coverage (100%) -- 75%: High coverage (80-99%) -- 50%: Moderate coverage (60-79%) -- 25%: Low coverage (40-59%) -- 0%: Minimal coverage (<40%) - -## 9. Verdict/Gate Determination - -### Code Review Verdicts - -| Verdict | Criteria | Action | -|---------|----------|--------| -| **BLOCK** | Critical issues present | Must fix before merge | -| **CONDITIONAL** | High/medium issues only | Fix recommended, merge allowed | -| **APPROVE** | Low issues or none | Ready to merge | - -### Spec Quality Gates - -| Gate | Criteria | Action | -|------|----------|--------| -| **PASS** | Score ≥80% AND coverage ≥70% | Ready for implementation | -| **REVIEW** | Score 60-79% OR coverage 50-69% | Revisions recommended | -| **FAIL** | Score <60% OR coverage <50% | Major revisions required | - -## 10. Error Handling - -| Error Type | Recovery Strategy | Escalation | -|------------|-------------------|------------| -| Missing context | Request from coordinator | Immediate escalation | -| Invalid review mode | Abort with error | Report to coordinator | -| Analysis failure | Retry with verbose logging | Report after 2 failures | -| Report generation failure | Use fallback template | Report with partial results | diff --git a/.claude/skills_lib/team-lifecycle-v2/roles/tester/commands/validate.md b/.claude/skills_lib/team-lifecycle-v2/roles/tester/commands/validate.md deleted file mode 100644 index 05ec30c4..00000000 --- a/.claude/skills_lib/team-lifecycle-v2/roles/tester/commands/validate.md +++ /dev/null @@ -1,538 +0,0 @@ -# Validate Command - -## Purpose -Test-fix cycle with strategy engine for automated test failure resolution. - -## Configuration - -```javascript -const MAX_ITERATIONS = 10 -const PASS_RATE_TARGET = 95 // percentage -``` - -## Main Iteration Loop - -```javascript -function runTestFixCycle(task, framework, affectedTests, modifiedFiles) { - let iteration = 0 - let bestPassRate = 0 - let bestResults = null - - while (iteration < MAX_ITERATIONS) { - iteration++ - - // Phase 1: Run Tests - const testCommand = buildTestCommand(framework, affectedTests, iteration === 1) - const testOutput = Bash(testCommand, { timeout: 120000 }) - const results = parseTestResults(testOutput.stdout + testOutput.stderr, framework) - - const passRate = results.total > 0 ? (results.passed / results.total * 100) : 0 - - // Track best result - if (passRate > bestPassRate) { - bestPassRate = passRate - bestResults = results - } - - // Progress update for long cycles - if (iteration > 5) { - team_msg({ - to: "coordinator", - type: "progress_update", - task_id: task.task_id, - iteration: iteration, - pass_rate: passRate.toFixed(1), - tests_passed: results.passed, - tests_failed: results.failed, - message: `Test-fix cycle iteration ${iteration}/${MAX_ITERATIONS}` - }, "[tester]") - } - - // Phase 2: Check Success - if (passRate >= PASS_RATE_TARGET) { - // Quality gate: Run full suite if only affected tests passed - if (affectedTests.length > 0 && iteration === 1) { - team_msg({ - to: "coordinator", - type: "progress_update", - task_id: task.task_id, - message: "Affected tests passed, running full suite..." - }, "[tester]") - - const fullSuiteCommand = buildTestCommand(framework, [], false) - const fullOutput = Bash(fullSuiteCommand, { timeout: 300000 }) - const fullResults = parseTestResults(fullOutput.stdout + fullOutput.stderr, framework) - const fullPassRate = fullResults.total > 0 ? (fullResults.passed / fullResults.total * 100) : 0 - - if (fullPassRate >= PASS_RATE_TARGET) { - return { - success: true, - results: fullResults, - iterations: iteration, - full_suite_run: true - } - } else { - // Full suite failed, continue fixing - results = fullResults - passRate = fullPassRate - } - } else { - return { - success: true, - results: results, - iterations: iteration, - full_suite_run: affectedTests.length === 0 - } - } - } - - // Phase 3: Analyze Failures - if (results.failures.length === 0) { - break // No failures to fix - } - - const classified = classifyFailures(results.failures) - - // Phase 4: Select Strategy - const strategy = selectStrategy(iteration, passRate, results.failures) - - team_msg({ - to: "coordinator", - type: "progress_update", - task_id: task.task_id, - iteration: iteration, - strategy: strategy, - failures: { - critical: classified.critical.length, - high: classified.high.length, - medium: classified.medium.length, - low: classified.low.length - } - }, "[tester]") - - // Phase 5: Apply Fixes - const fixResult = applyFixes(strategy, results.failures, framework, modifiedFiles) - - if (!fixResult.success) { - // Fix application failed, try next iteration with different strategy - continue - } - } - - // Max iterations reached - return { - success: false, - results: bestResults, - iterations: MAX_ITERATIONS, - best_pass_rate: bestPassRate, - error: "Max iterations reached without achieving target pass rate" - } -} -``` - -## Strategy Selection - -```javascript -function selectStrategy(iteration, passRate, failures) { - const classified = classifyFailures(failures) - - // Conservative: Early iterations or high pass rate - if (iteration <= 3 || passRate >= 80) { - return "conservative" - } - - // Surgical: Specific failure patterns - if (classified.critical.length > 0 && classified.critical.length < 5) { - return "surgical" - } - - // Aggressive: Low pass rate or many iterations - if (passRate < 50 || iteration > 7) { - return "aggressive" - } - - return "conservative" -} -``` - -## Fix Application - -### Conservative Strategy - -```javascript -function applyConservativeFixes(failures, framework, modifiedFiles) { - const classified = classifyFailures(failures) - - // Fix only the first critical failure - if (classified.critical.length > 0) { - const failure = classified.critical[0] - return fixSingleFailure(failure, framework, modifiedFiles) - } - - // If no critical, fix first high priority - if (classified.high.length > 0) { - const failure = classified.high[0] - return fixSingleFailure(failure, framework, modifiedFiles) - } - - return { success: false, error: "No fixable failures found" } -} -``` - -### Surgical Strategy - -```javascript -function applySurgicalFixes(failures, framework, modifiedFiles) { - // Identify common pattern - const pattern = identifyCommonPattern(failures) - - if (!pattern) { - return { success: false, error: "No common pattern identified" } - } - - // Apply pattern-based fix across all occurrences - const fixes = [] - - for (const failure of failures) { - if (matchesPattern(failure, pattern)) { - const fix = generatePatternFix(failure, pattern, framework) - fixes.push(fix) - } - } - - // Apply all fixes in batch - for (const fix of fixes) { - applyFix(fix, modifiedFiles) - } - - return { - success: true, - fixes_applied: fixes.length, - pattern: pattern - } -} - -function identifyCommonPattern(failures) { - // Group failures by error type - const errorTypes = {} - - for (const failure of failures) { - const errorType = extractErrorType(failure.error) - if (!errorTypes[errorType]) { - errorTypes[errorType] = [] - } - errorTypes[errorType].push(failure) - } - - // Find most common error type - let maxCount = 0 - let commonPattern = null - - for (const [errorType, instances] of Object.entries(errorTypes)) { - if (instances.length > maxCount) { - maxCount = instances.length - commonPattern = { - type: errorType, - instances: instances, - count: instances.length - } - } - } - - return maxCount >= 3 ? commonPattern : null -} - -function extractErrorType(error) { - const errorLower = error.toLowerCase() - - if (errorLower.includes("cannot find module")) return "missing_import" - if (errorLower.includes("is not defined")) return "undefined_variable" - if (errorLower.includes("expected") && errorLower.includes("received")) return "assertion_mismatch" - if (errorLower.includes("timeout")) return "timeout" - if (errorLower.includes("syntaxerror")) return "syntax_error" - - return "unknown" -} -``` - -### Aggressive Strategy - -```javascript -function applyAggressiveFixes(failures, framework, modifiedFiles) { - const classified = classifyFailures(failures) - const fixes = [] - - // Fix all critical failures - for (const failure of classified.critical) { - const fix = generateFix(failure, framework, modifiedFiles) - if (fix) { - fixes.push(fix) - } - } - - // Fix all high priority failures - for (const failure of classified.high) { - const fix = generateFix(failure, framework, modifiedFiles) - if (fix) { - fixes.push(fix) - } - } - - // Apply all fixes - for (const fix of fixes) { - applyFix(fix, modifiedFiles) - } - - return { - success: fixes.length > 0, - fixes_applied: fixes.length - } -} -``` - -### Fix Generation - -```javascript -function generateFix(failure, framework, modifiedFiles) { - const errorType = extractErrorType(failure.error) - - switch (errorType) { - case "missing_import": - return generateImportFix(failure, modifiedFiles) - - case "undefined_variable": - return generateVariableFix(failure, modifiedFiles) - - case "assertion_mismatch": - return generateAssertionFix(failure, framework) - - case "timeout": - return generateTimeoutFix(failure, framework) - - case "syntax_error": - return generateSyntaxFix(failure, modifiedFiles) - - default: - return null - } -} - -function generateImportFix(failure, modifiedFiles) { - // Extract module name from error - const moduleMatch = failure.error.match(/Cannot find module ['"](.+?)['"]/) - if (!moduleMatch) return null - - const moduleName = moduleMatch[1] - - // Find test file - const testFile = extractTestFile(failure.test) - if (!testFile) return null - - // Check if module exists in modified files - const sourceFile = modifiedFiles.find(f => - f.includes(moduleName) || f.endsWith(`${moduleName}.ts`) || f.endsWith(`${moduleName}.js`) - ) - - if (!sourceFile) return null - - // Generate import statement - const relativePath = calculateRelativePath(testFile, sourceFile) - const importStatement = `import { } from '${relativePath}'` - - return { - file: testFile, - type: "add_import", - content: importStatement, - line: 1 // Add at top of file - } -} - -function generateAssertionFix(failure, framework) { - // Extract expected vs received values - const expectedMatch = failure.error.match(/Expected:\s*(.+?)(?:\n|$)/) - const receivedMatch = failure.error.match(/Received:\s*(.+?)(?:\n|$)/) - - if (!expectedMatch || !receivedMatch) return null - - const expected = expectedMatch[1].trim() - const received = receivedMatch[1].trim() - - // Find test file and line - const testFile = extractTestFile(failure.test) - const testLine = extractTestLine(failure.error) - - if (!testFile || !testLine) return null - - return { - file: testFile, - type: "update_assertion", - line: testLine, - old_value: expected, - new_value: received, - note: "Auto-updated assertion based on actual behavior" - } -} -``` - -## Test Result Parsing - -```javascript -function parseTestResults(output, framework) { - const results = { - total: 0, - passed: 0, - failed: 0, - skipped: 0, - failures: [] - } - - if (framework === "jest" || framework === "vitest") { - // Parse summary line - const summaryMatch = output.match(/Tests:\s+(?:(\d+)\s+failed,\s+)?(?:(\d+)\s+passed,\s+)?(\d+)\s+total/) - if (summaryMatch) { - results.failed = summaryMatch[1] ? parseInt(summaryMatch[1]) : 0 - results.passed = summaryMatch[2] ? parseInt(summaryMatch[2]) : 0 - results.total = parseInt(summaryMatch[3]) - } - - // Alternative format - if (results.total === 0) { - const altMatch = output.match(/(\d+)\s+passed.*?(\d+)\s+total/) - if (altMatch) { - results.passed = parseInt(altMatch[1]) - results.total = parseInt(altMatch[2]) - results.failed = results.total - results.passed - } - } - - // Extract failure details - const failureRegex = /●\s+(.*?)\n\n([\s\S]*?)(?=\n\n●|\n\nTest Suites:|\n\n$)/g - let match - while ((match = failureRegex.exec(output)) !== null) { - results.failures.push({ - test: match[1].trim(), - error: match[2].trim() - }) - } - - } else if (framework === "pytest") { - // Parse pytest summary - const summaryMatch = output.match(/=+\s+(?:(\d+)\s+failed,?\s+)?(?:(\d+)\s+passed)?/) - if (summaryMatch) { - results.failed = summaryMatch[1] ? parseInt(summaryMatch[1]) : 0 - results.passed = summaryMatch[2] ? parseInt(summaryMatch[2]) : 0 - results.total = results.failed + results.passed - } - - // Extract failure details - const failureRegex = /FAILED\s+(.*?)\s+-\s+([\s\S]*?)(?=\n_+|FAILED|=+\s+\d+)/g - let match - while ((match = failureRegex.exec(output)) !== null) { - results.failures.push({ - test: match[1].trim(), - error: match[2].trim() - }) - } - } - - return results -} -``` - -## Test Command Building - -```javascript -function buildTestCommand(framework, affectedTests, isFirstRun) { - const testFiles = affectedTests.length > 0 ? affectedTests.join(" ") : "" - - switch (framework) { - case "vitest": - return testFiles - ? `vitest run ${testFiles} --reporter=verbose` - : `vitest run --reporter=verbose` - - case "jest": - return testFiles - ? `jest ${testFiles} --no-coverage --verbose` - : `jest --no-coverage --verbose` - - case "mocha": - return testFiles - ? `mocha ${testFiles} --reporter spec` - : `mocha --reporter spec` - - case "pytest": - return testFiles - ? `pytest ${testFiles} -v --tb=short` - : `pytest -v --tb=short` - - default: - throw new Error(`Unsupported test framework: ${framework}`) - } -} -``` - -## Utility Functions - -### Extract Test File - -```javascript -function extractTestFile(testName) { - // Extract file path from test name - // Format: "path/to/file.test.ts > describe block > test name" - const fileMatch = testName.match(/^(.*?\.(?:test|spec)\.[jt]sx?)/) - return fileMatch ? fileMatch[1] : null -} -``` - -### Extract Test Line - -```javascript -function extractTestLine(error) { - // Extract line number from error stack - const lineMatch = error.match(/:(\d+):\d+/) - return lineMatch ? parseInt(lineMatch[1]) : null -} -``` - -### Calculate Relative Path - -```javascript -function calculateRelativePath(fromFile, toFile) { - const fromParts = fromFile.split("/") - const toParts = toFile.split("/") - - // Remove filename - fromParts.pop() - - // Find common base - let commonLength = 0 - while (commonLength < fromParts.length && - commonLength < toParts.length && - fromParts[commonLength] === toParts[commonLength]) { - commonLength++ - } - - // Build relative path - const upLevels = fromParts.length - commonLength - const downPath = toParts.slice(commonLength) - - const relativeParts = [] - for (let i = 0; i < upLevels; i++) { - relativeParts.push("..") - } - relativeParts.push(...downPath) - - let path = relativeParts.join("/") - - // Remove file extension - path = path.replace(/\.[jt]sx?$/, "") - - // Ensure starts with ./ - if (!path.startsWith(".")) { - path = "./" + path - } - - return path -} -``` diff --git a/.claude/skills_lib/team-lifecycle-v2/roles/tester/role.md b/.claude/skills_lib/team-lifecycle-v2/roles/tester/role.md deleted file mode 100644 index 83283ea0..00000000 --- a/.claude/skills_lib/team-lifecycle-v2/roles/tester/role.md +++ /dev/null @@ -1,385 +0,0 @@ -# Tester Role - -## 1. Role Identity - -- **Name**: tester -- **Task Prefix**: TEST-* -- **Output Tag**: `[tester]` -- **Responsibility**: Detect Framework → Run Tests → Fix Cycle → Report Results - -## 2. Role Boundaries - -### MUST -- Only process TEST-* tasks -- Communicate only with coordinator -- Use detected test framework -- Run affected tests before full suite -- Tag all outputs with `[tester]` - -### MUST NOT -- Create tasks -- Contact other workers directly -- Modify production code beyond test fixes -- Skip framework detection -- Run full suite without affected tests first - -## 3. Message Types - -| Type | Direction | Purpose | Format | -|------|-----------|---------|--------| -| `task_request` | FROM coordinator | Receive TEST-* task assignment | `{ type: "task_request", task_id, description, impl_task_id }` | -| `task_complete` | TO coordinator | Report test success | `{ type: "task_complete", task_id, status: "success", pass_rate, tests_run, iterations }` | -| `task_failed` | TO coordinator | Report test failure | `{ type: "task_failed", task_id, error, failures, pass_rate }` | -| `progress_update` | TO coordinator | Report fix cycle progress | `{ type: "progress_update", task_id, iteration, pass_rate, strategy }` | - -## 4. Message Bus - -**Primary**: Use `team_msg` for all coordinator communication with `[tester]` tag: -```javascript -team_msg({ - to: "coordinator", - type: "task_complete", - task_id: "TEST-001", - status: "success", - pass_rate: 98.5, - tests_run: 45, - iterations: 3, - framework: "vitest" -}, "[tester]") -``` - -**CLI Fallback**: When message bus unavailable, write to `.workflow/.team/messages/tester-{timestamp}.json` - -## 5. Toolbox - -### Available Commands -- `commands/validate.md` - Test-fix cycle with strategy engine - -### CLI Capabilities -- None (uses project's test framework directly via Bash) - -## 6. Execution (5-Phase) - -### Phase 1: Task Discovery - -**Task Loading**: -```javascript -const tasks = Glob(".workflow/.team/tasks/TEST-*.json") - .filter(task => task.status === "pending" && task.assigned_to === "tester") -``` - -**Implementation Task Linking**: -```javascript -const implTaskId = task.metadata?.impl_task_id -const implTask = implTaskId ? Read(`.workflow/.team/tasks/${implTaskId}.json`) : null -const modifiedFiles = implTask?.metadata?.files_modified || [] -``` - -### Phase 2: Test Framework Detection - -**Framework Detection**: -```javascript -function detectTestFramework() { - // Check package.json for test frameworks - const packageJson = Read("package.json") - const pkg = JSON.parse(packageJson) - - // Priority 1: Check dependencies - if (pkg.devDependencies?.vitest || pkg.dependencies?.vitest) { - return "vitest" - } - if (pkg.devDependencies?.jest || pkg.dependencies?.jest) { - return "jest" - } - if (pkg.devDependencies?.mocha || pkg.dependencies?.mocha) { - return "mocha" - } - if (pkg.devDependencies?.pytest || pkg.dependencies?.pytest) { - return "pytest" - } - - // Priority 2: Check test scripts - const testScript = pkg.scripts?.test || "" - if (testScript.includes("vitest")) return "vitest" - if (testScript.includes("jest")) return "jest" - if (testScript.includes("mocha")) return "mocha" - if (testScript.includes("pytest")) return "pytest" - - // Priority 3: Check config files - const configFiles = Glob("{vitest,jest,mocha}.config.{js,ts,json}") - if (configFiles.some(f => f.includes("vitest"))) return "vitest" - if (configFiles.some(f => f.includes("jest"))) return "jest" - if (configFiles.some(f => f.includes("mocha"))) return "mocha" - - if (Bash("test -f pytest.ini").exitCode === 0) return "pytest" - - return "unknown" -} -``` - -**Affected Test Discovery**: -```javascript -function findAffectedTests(modifiedFiles) { - const testFiles = [] - - for (const file of modifiedFiles) { - const baseName = file.replace(/\.(ts|js|tsx|jsx|py)$/, "") - const dir = file.substring(0, file.lastIndexOf("/")) - - const testVariants = [ - // Same directory variants - `${baseName}.test.ts`, - `${baseName}.test.js`, - `${baseName}.spec.ts`, - `${baseName}.spec.js`, - `${baseName}_test.py`, - `test_${baseName.split("/").pop()}.py`, - - // Test directory variants - `${file.replace(/^src\//, "tests/")}`, - `${file.replace(/^src\//, "__tests__/")}`, - `${file.replace(/^src\//, "test/")}`, - `${dir}/__tests__/${file.split("/").pop().replace(/\.(ts|js|tsx|jsx)$/, ".test.ts")}`, - - // Python variants - `${file.replace(/^src\//, "tests/").replace(/\.py$/, "_test.py")}`, - `${file.replace(/^src\//, "tests/test_")}` - ] - - for (const variant of testVariants) { - if (Bash(`test -f ${variant}`).exitCode === 0) { - testFiles.push(variant) - } - } - } - - return [...new Set(testFiles)] // Deduplicate -} -``` - -### Phase 3: Test Execution & Fix Cycle - -**Delegate to Command**: -```javascript -const validateCommand = Read("commands/validate.md") -// Command handles: -// - MAX_ITERATIONS=10, PASS_RATE_TARGET=95 -// - Main iteration loop with strategy selection -// - Quality gate check (affected tests → full suite) -// - applyFixes by strategy (conservative/aggressive/surgical) -// - Progress updates for long cycles (iteration > 5) -``` - -### Phase 4: Result Analysis - -**Test Result Parsing**: -```javascript -function parseTestResults(output, framework) { - const results = { - total: 0, - passed: 0, - failed: 0, - skipped: 0, - failures: [] - } - - if (framework === "jest" || framework === "vitest") { - // Parse Jest/Vitest output - const totalMatch = output.match(/Tests:\s+(\d+)\s+total/) - const passedMatch = output.match(/(\d+)\s+passed/) - const failedMatch = output.match(/(\d+)\s+failed/) - const skippedMatch = output.match(/(\d+)\s+skipped/) - - results.total = totalMatch ? parseInt(totalMatch[1]) : 0 - results.passed = passedMatch ? parseInt(passedMatch[1]) : 0 - results.failed = failedMatch ? parseInt(failedMatch[1]) : 0 - results.skipped = skippedMatch ? parseInt(skippedMatch[1]) : 0 - - // Extract failure details - const failureRegex = /●\s+(.*?)\n\n\s+(.*?)(?=\n\n●|\n\nTest Suites:)/gs - let match - while ((match = failureRegex.exec(output)) !== null) { - results.failures.push({ - test: match[1].trim(), - error: match[2].trim() - }) - } - } else if (framework === "pytest") { - // Parse pytest output - const summaryMatch = output.match(/=+\s+(\d+)\s+failed,\s+(\d+)\s+passed/) - if (summaryMatch) { - results.failed = parseInt(summaryMatch[1]) - results.passed = parseInt(summaryMatch[2]) - results.total = results.failed + results.passed - } - - // Extract failure details - const failureRegex = /FAILED\s+(.*?)\s+-\s+(.*?)(?=\n_+|\nFAILED|$)/gs - let match - while ((match = failureRegex.exec(output)) !== null) { - results.failures.push({ - test: match[1].trim(), - error: match[2].trim() - }) - } - } - - return results -} -``` - -**Failure Classification**: -```javascript -function classifyFailures(failures) { - const classified = { - critical: [], // Syntax errors, missing imports - high: [], // Assertion failures, logic errors - medium: [], // Timeout, flaky tests - low: [] // Warnings, deprecations - } - - for (const failure of failures) { - const error = failure.error.toLowerCase() - - if (error.includes("syntaxerror") || - error.includes("cannot find module") || - error.includes("is not defined")) { - classified.critical.push(failure) - } else if (error.includes("expected") || - error.includes("assertion") || - error.includes("toBe") || - error.includes("toEqual")) { - classified.high.push(failure) - } else if (error.includes("timeout") || - error.includes("async")) { - classified.medium.push(failure) - } else { - classified.low.push(failure) - } - } - - return classified -} -``` - -### Phase 5: Report to Coordinator - -**Success Report**: -```javascript -team_msg({ - to: "coordinator", - type: "task_complete", - task_id: task.task_id, - status: "success", - pass_rate: (results.passed / results.total * 100).toFixed(1), - tests_run: results.total, - tests_passed: results.passed, - tests_failed: results.failed, - iterations: iterationCount, - framework: framework, - affected_tests: affectedTests.length, - full_suite_run: fullSuiteRun, - timestamp: new Date().toISOString() -}, "[tester]") -``` - -**Failure Report**: -```javascript -const classified = classifyFailures(results.failures) - -team_msg({ - to: "coordinator", - type: "task_failed", - task_id: task.task_id, - error: "Test failures exceeded threshold", - pass_rate: (results.passed / results.total * 100).toFixed(1), - tests_run: results.total, - failures: { - critical: classified.critical.length, - high: classified.high.length, - medium: classified.medium.length, - low: classified.low.length - }, - failure_details: classified, - iterations: iterationCount, - framework: framework, - timestamp: new Date().toISOString() -}, "[tester]") -``` - -## 7. Strategy Engine - -### Strategy Selection - -```javascript -function selectStrategy(iteration, passRate, failures) { - const classified = classifyFailures(failures) - - // Conservative: Early iterations or high pass rate - if (iteration <= 3 || passRate >= 80) { - return "conservative" - } - - // Surgical: Specific failure patterns - if (classified.critical.length > 0 && classified.critical.length < 5) { - return "surgical" - } - - // Aggressive: Low pass rate or many iterations - if (passRate < 50 || iteration > 7) { - return "aggressive" - } - - return "conservative" -} -``` - -### Fix Application - -```javascript -function applyFixes(strategy, failures, framework) { - if (strategy === "conservative") { - // Fix only critical failures one at a time - const critical = classifyFailures(failures).critical - if (critical.length > 0) { - return fixFailure(critical[0], framework) - } - } else if (strategy === "surgical") { - // Fix specific pattern across all occurrences - const pattern = identifyCommonPattern(failures) - return fixPattern(pattern, framework) - } else if (strategy === "aggressive") { - // Fix all failures in batch - return fixAllFailures(failures, framework) - } -} -``` - -## 8. Error Handling - -| Error Type | Recovery Strategy | Escalation | -|------------|-------------------|------------| -| Framework not detected | Prompt user for framework | Immediate escalation | -| No tests found | Report to coordinator | Manual intervention | -| Test command fails | Retry with verbose output | Report after 2 failures | -| Infinite fix loop | Abort after MAX_ITERATIONS | Report iteration history | -| Pass rate below target | Report best attempt | Include failure classification | - -## 9. Configuration - -| Parameter | Default | Description | -|-----------|---------|-------------| -| MAX_ITERATIONS | 10 | Maximum fix-test cycles | -| PASS_RATE_TARGET | 95 | Target pass rate (%) | -| AFFECTED_TESTS_FIRST | true | Run affected tests before full suite | -| PARALLEL_TESTS | true | Enable parallel test execution | -| TIMEOUT_PER_TEST | 30000 | Timeout per test (ms) | - -## 10. Test Framework Commands - -| Framework | Affected Tests Command | Full Suite Command | -|-----------|------------------------|-------------------| -| vitest | `vitest run ${files.join(" ")}` | `vitest run` | -| jest | `jest ${files.join(" ")} --no-coverage` | `jest --no-coverage` | -| mocha | `mocha ${files.join(" ")}` | `mocha` | -| pytest | `pytest ${files.join(" ")} -v` | `pytest -v` | diff --git a/.claude/skills_lib/team-lifecycle-v2/roles/writer/commands/generate-doc.md b/.claude/skills_lib/team-lifecycle-v2/roles/writer/commands/generate-doc.md deleted file mode 100644 index 67c89708..00000000 --- a/.claude/skills_lib/team-lifecycle-v2/roles/writer/commands/generate-doc.md +++ /dev/null @@ -1,698 +0,0 @@ -# Command: Generate Document - -Multi-CLI document generation for 4 document types: Product Brief, Requirements/PRD, Architecture, Epics & Stories. - -## Pre-Steps (All Document Types) - -```javascript -// 1. Load document standards -const docStandards = Read('../../specs/document-standards.md') - -// 2. Load appropriate template -const templateMap = { - 'product-brief': '../../templates/product-brief.md', - 'requirements': '../../templates/requirements-prd.md', - 'architecture': '../../templates/architecture-doc.md', - 'epics': '../../templates/epics-template.md' -} -const template = Read(templateMap[docType]) - -// 3. Build shared context -const seedAnalysis = specConfig?.seed_analysis || - (priorDocs.discoveryContext ? JSON.parse(priorDocs.discoveryContext).seed_analysis : {}) - -const sharedContext = ` -SEED: ${specConfig?.topic || ''} -PROBLEM: ${seedAnalysis.problem_statement || ''} -TARGET USERS: ${(seedAnalysis.target_users || []).join(', ')} -DOMAIN: ${seedAnalysis.domain || ''} -CONSTRAINTS: ${(seedAnalysis.constraints || []).join(', ')} -FOCUS AREAS: ${(specConfig?.focus_areas || []).join(', ')} -${priorDocs.discoveryContext ? ` -CODEBASE CONTEXT: -- Existing patterns: ${JSON.parse(priorDocs.discoveryContext).existing_patterns?.slice(0,5).join(', ') || 'none'} -- Tech stack: ${JSON.stringify(JSON.parse(priorDocs.discoveryContext).tech_stack || {})} -` : ''}` - -// 4. Route to specific document type -``` - -## DRAFT-001: Product Brief - -3-way parallel CLI analysis (product/technical/user perspectives), then synthesize. - -```javascript -if (docType === 'product-brief') { - // === Parallel CLI Analysis === - - // Product Perspective (Gemini) - Bash({ - command: `ccw cli -p "PURPOSE: Product analysis for specification - identify market fit, user value, and success criteria. -Success: Clear vision, measurable goals, competitive positioning. - -${sharedContext} - -TASK: -- Define product vision (1-3 sentences, aspirational) -- Analyze market/competitive landscape -- Define 3-5 measurable success metrics -- Identify scope boundaries (in-scope vs out-of-scope) -- Assess user value proposition -- List assumptions that need validation - -MODE: analysis -EXPECTED: Structured product analysis with: vision, goals with metrics, scope, competitive positioning, assumptions -CONSTRAINTS: Focus on 'what' and 'why', not 'how' -" --tool gemini --mode analysis`, - run_in_background: true - }) - - // Technical Perspective (Codex) - Bash({ - command: `ccw cli -p "PURPOSE: Technical feasibility analysis for specification - assess implementation viability and constraints. -Success: Clear technical constraints, integration complexity, technology recommendations. - -${sharedContext} - -TASK: -- Assess technical feasibility of the core concept -- Identify technical constraints and blockers -- Evaluate integration complexity with existing systems -- Recommend technology approach (high-level) -- Identify technical risks and dependencies -- Estimate complexity: simple/moderate/complex - -MODE: analysis -EXPECTED: Technical analysis with: feasibility assessment, constraints, integration complexity, tech recommendations, risks -CONSTRAINTS: Focus on feasibility and constraints, not detailed architecture -" --tool codex --mode analysis`, - run_in_background: true - }) - - // User Perspective (Claude) - Bash({ - command: `ccw cli -p "PURPOSE: User experience analysis for specification - understand user journeys, pain points, and UX considerations. -Success: Clear user personas, journey maps, UX requirements. - -${sharedContext} - -TASK: -- Elaborate user personas with goals and frustrations -- Map primary user journey (happy path) -- Identify key pain points in current experience -- Define UX success criteria -- List accessibility and usability considerations -- Suggest interaction patterns - -MODE: analysis -EXPECTED: User analysis with: personas, journey map, pain points, UX criteria, interaction recommendations -CONSTRAINTS: Focus on user needs and experience, not implementation -" --tool claude --mode analysis`, - run_in_background: true - }) - - // STOP: Wait for all 3 CLI results - - // === Synthesize Three Perspectives === - const synthesis = { - convergent_themes: [], // Themes consistent across all three perspectives - conflicts: [], // Conflicting viewpoints - product_insights: [], // Unique product perspective insights - technical_insights: [], // Unique technical perspective insights - user_insights: [] // Unique user perspective insights - } - - // Parse CLI outputs and identify: - // - Common themes mentioned by 2+ perspectives - // - Conflicts (e.g., product wants feature X, technical says infeasible) - // - Unique insights from each perspective - - // === Integrate Discussion Feedback === - if (discussionFeedback) { - // Extract consensus and adjustments from discuss-001-scope.md - // Merge discussion conclusions into synthesis - } - - // === Generate Document from Template === - const frontmatter = `--- -session_id: ${specConfig?.session_id || 'unknown'} -phase: 2 -document_type: product-brief -status: draft -generated_at: ${new Date().toISOString()} -version: 1 -dependencies: - - spec-config.json - - discovery-context.json ----` - - // Fill template sections: - // - Vision (from product perspective + synthesis) - // - Problem Statement (from seed analysis + user perspective) - // - Target Users (from user perspective + personas) - // - Goals (from product perspective + metrics) - // - Scope (from product perspective + technical constraints) - // - Success Criteria (from all three perspectives) - // - Assumptions (from product + technical perspectives) - - const filledContent = fillTemplate(template, { - vision: productPerspective.vision, - problem: seedAnalysis.problem_statement, - users: userPerspective.personas, - goals: productPerspective.goals, - scope: synthesis.scope_boundaries, - success_criteria: synthesis.convergent_themes, - assumptions: [...productPerspective.assumptions, ...technicalPerspective.assumptions] - }) - - Write(`${sessionFolder}/spec/product-brief.md`, `${frontmatter}\n\n${filledContent}`) - - return { - outputPath: 'spec/product-brief.md', - documentSummary: `Product Brief generated with ${synthesis.convergent_themes.length} convergent themes, ${synthesis.conflicts.length} conflicts resolved` - } -} -``` - -## DRAFT-002: Requirements/PRD - -Gemini CLI expansion to generate REQ-NNN and NFR-{type}-NNN files. - -```javascript -if (docType === 'requirements') { - // === Requirements Expansion CLI === - Bash({ - command: `ccw cli -p "PURPOSE: Generate detailed functional and non-functional requirements from product brief. -Success: Complete PRD with testable acceptance criteria for every requirement. - -PRODUCT BRIEF CONTEXT: -${priorDocs.productBrief?.slice(0, 3000) || ''} - -${sharedContext} - -TASK: -- For each goal in the product brief, generate 3-7 functional requirements -- Each requirement must have: - - Unique ID: REQ-NNN (zero-padded) - - Clear title - - Detailed description - - User story: As a [persona], I want [action] so that [benefit] - - 2-4 specific, testable acceptance criteria -- Generate non-functional requirements: - - Performance (response times, throughput) - - Security (authentication, authorization, data protection) - - Scalability (user load, data volume) - - Usability (accessibility, learnability) -- Assign MoSCoW priority: Must/Should/Could/Won't -- Output structure per requirement: ID, title, description, user_story, acceptance_criteria[], priority, traces - -MODE: analysis -EXPECTED: Structured requirements with: ID, title, description, user story, acceptance criteria, priority, traceability to goals -CONSTRAINTS: Every requirement must be specific enough to estimate and test. No vague requirements. -" --tool gemini --mode analysis`, - run_in_background: true - }) - - // Wait for CLI result - - // === Integrate Discussion Feedback === - if (discussionFeedback) { - // Extract requirement adjustments from discuss-002-brief.md - // Merge new/modified/deleted requirements - } - - // === Generate requirements/ Directory === - Bash(`mkdir -p "${sessionFolder}/spec/requirements"`) - - const timestamp = new Date().toISOString() - - // Parse CLI output → funcReqs[], nfReqs[] - const funcReqs = parseFunctionalRequirements(cliOutput) - const nfReqs = parseNonFunctionalRequirements(cliOutput) - - // Write individual REQ-*.md files (one per functional requirement) - funcReqs.forEach(req => { - const reqFrontmatter = `--- -id: REQ-${req.id} -title: "${req.title}" -priority: ${req.priority} -status: draft -traces: - - product-brief.md ----` - const reqContent = `${reqFrontmatter} - -# REQ-${req.id}: ${req.title} - -## Description -${req.description} - -## User Story -${req.user_story} - -## Acceptance Criteria -${req.acceptance_criteria.map((ac, i) => `${i+1}. ${ac}`).join('\n')} -` - Write(`${sessionFolder}/spec/requirements/REQ-${req.id}-${req.slug}.md`, reqContent) - }) - - // Write individual NFR-*.md files - nfReqs.forEach(nfr => { - const nfrFrontmatter = `--- -id: NFR-${nfr.type}-${nfr.id} -type: ${nfr.type} -title: "${nfr.title}" -status: draft -traces: - - product-brief.md ----` - const nfrContent = `${nfrFrontmatter} - -# NFR-${nfr.type}-${nfr.id}: ${nfr.title} - -## Requirement -${nfr.requirement} - -## Metric & Target -${nfr.metric} — Target: ${nfr.target} -` - Write(`${sessionFolder}/spec/requirements/NFR-${nfr.type}-${nfr.id}-${nfr.slug}.md`, nfrContent) - }) - - // Write _index.md (summary + links) - const indexFrontmatter = `--- -session_id: ${specConfig?.session_id || 'unknown'} -phase: 3 -document_type: requirements-index -status: draft -generated_at: ${timestamp} -version: 1 -dependencies: - - product-brief.md ----` - const indexContent = `${indexFrontmatter} - -# Requirements (PRD) - -## Summary -Total: ${funcReqs.length} functional + ${nfReqs.length} non-functional requirements - -## Functional Requirements -| ID | Title | Priority | Status | -|----|-------|----------|--------| -${funcReqs.map(r => `| [REQ-${r.id}](REQ-${r.id}-${r.slug}.md) | ${r.title} | ${r.priority} | draft |`).join('\n')} - -## Non-Functional Requirements -| ID | Type | Title | -|----|------|-------| -${nfReqs.map(n => `| [NFR-${n.type}-${n.id}](NFR-${n.type}-${n.id}-${n.slug}.md) | ${n.type} | ${n.title} |`).join('\n')} - -## MoSCoW Summary -- **Must**: ${funcReqs.filter(r => r.priority === 'Must').length} -- **Should**: ${funcReqs.filter(r => r.priority === 'Should').length} -- **Could**: ${funcReqs.filter(r => r.priority === 'Could').length} -- **Won't**: ${funcReqs.filter(r => r.priority === "Won't").length} -` - Write(`${sessionFolder}/spec/requirements/_index.md`, indexContent) - - return { - outputPath: 'spec/requirements/_index.md', - documentSummary: `Requirements generated: ${funcReqs.length} functional, ${nfReqs.length} non-functional` - } -} -``` - -## DRAFT-003: Architecture - -Two-stage CLI: Gemini architecture design + Codex architecture review. - -```javascript -if (docType === 'architecture') { - // === Stage 1: Architecture Design (Gemini) === - Bash({ - command: `ccw cli -p "PURPOSE: Generate technical architecture for the specified requirements. -Success: Complete component architecture, tech stack, and ADRs with justified decisions. - -PRODUCT BRIEF (summary): -${priorDocs.productBrief?.slice(0, 3000) || ''} - -REQUIREMENTS: -${priorDocs.requirementsIndex?.slice(0, 5000) || ''} - -${sharedContext} - -TASK: -- Define system architecture style (monolith, microservices, serverless, etc.) with justification -- Identify core components and their responsibilities -- Create component interaction diagram (Mermaid graph TD format) -- Specify technology stack: languages, frameworks, databases, infrastructure -- Generate 2-4 Architecture Decision Records (ADRs): - - Each ADR: context, decision, 2-3 alternatives with pros/cons, consequences - - Focus on: data storage, API design, authentication, key technical choices -- Define data model: key entities and relationships (Mermaid erDiagram format) -- Identify security architecture: auth, authorization, data protection -- List API endpoints (high-level) - -MODE: analysis -EXPECTED: Complete architecture with: style justification, component diagram, tech stack table, ADRs, data model, security controls, API overview -CONSTRAINTS: Architecture must support all Must-have requirements. Prefer proven technologies. -" --tool gemini --mode analysis`, - run_in_background: true - }) - - // Wait for Gemini result - - // === Stage 2: Architecture Review (Codex) === - Bash({ - command: `ccw cli -p "PURPOSE: Critical review of proposed architecture - identify weaknesses and risks. -Success: Actionable feedback with specific concerns and improvement suggestions. - -PROPOSED ARCHITECTURE: -${geminiArchitectureOutput.slice(0, 5000)} - -REQUIREMENTS CONTEXT: -${priorDocs.requirementsIndex?.slice(0, 2000) || ''} - -TASK: -- Challenge each ADR: are the alternatives truly the best options? -- Identify scalability bottlenecks in the component design -- Assess security gaps: authentication, authorization, data protection -- Evaluate technology choices: maturity, community support, fit -- Check for over-engineering or under-engineering -- Verify architecture covers all Must-have requirements -- Rate overall architecture quality: 1-5 with justification - -MODE: analysis -EXPECTED: Architecture review with: per-ADR feedback, scalability concerns, security gaps, technology risks, quality rating -CONSTRAINTS: Be genuinely critical, not just validating. Focus on actionable improvements. -" --tool codex --mode analysis`, - run_in_background: true - }) - - // Wait for Codex result - - // === Integrate Discussion Feedback === - if (discussionFeedback) { - // Extract architecture feedback from discuss-003-requirements.md - // Merge into architecture design - } - - // === Codebase Integration Mapping (conditional) === - let integrationMapping = null - if (priorDocs.discoveryContext) { - const dc = JSON.parse(priorDocs.discoveryContext) - if (dc.relevant_files) { - integrationMapping = dc.relevant_files.map(f => ({ - new_component: '...', - existing_module: f.path, - integration_type: 'Extend|Replace|New', - notes: f.rationale - })) - } - } - - // === Generate architecture/ Directory === - Bash(`mkdir -p "${sessionFolder}/spec/architecture"`) - - const timestamp = new Date().toISOString() - const adrs = parseADRs(geminiArchitectureOutput, codexReviewOutput) - - // Write individual ADR-*.md files - adrs.forEach(adr => { - const adrFrontmatter = `--- -id: ADR-${adr.id} -title: "${adr.title}" -status: draft -traces: - - ../requirements/_index.md ----` - const adrContent = `${adrFrontmatter} - -# ADR-${adr.id}: ${adr.title} - -## Context -${adr.context} - -## Decision -${adr.decision} - -## Alternatives -${adr.alternatives.map((alt, i) => `### Option ${i+1}: ${alt.name}\n- **Pros**: ${alt.pros.join(', ')}\n- **Cons**: ${alt.cons.join(', ')}`).join('\n\n')} - -## Consequences -${adr.consequences} - -## Review Feedback -${adr.reviewFeedback || 'N/A'} -` - Write(`${sessionFolder}/spec/architecture/ADR-${adr.id}-${adr.slug}.md`, adrContent) - }) - - // Write _index.md (with Mermaid component diagram + ER diagram + links) - const archIndexFrontmatter = `--- -session_id: ${specConfig?.session_id || 'unknown'} -phase: 4 -document_type: architecture-index -status: draft -generated_at: ${timestamp} -version: 1 -dependencies: - - ../product-brief.md - - ../requirements/_index.md ----` - - const archIndexContent = `${archIndexFrontmatter} - -# Architecture Document - -## System Overview -${geminiArchitectureOutput.system_overview} - -## Component Diagram -\`\`\`mermaid -${geminiArchitectureOutput.component_diagram} -\`\`\` - -## Technology Stack -${geminiArchitectureOutput.tech_stack_table} - -## Architecture Decision Records -| ID | Title | Status | -|----|-------|--------| -${adrs.map(a => `| [ADR-${a.id}](ADR-${a.id}-${a.slug}.md) | ${a.title} | draft |`).join('\n')} - -## Data Model -\`\`\`mermaid -${geminiArchitectureOutput.data_model_diagram} -\`\`\` - -## API Design -${geminiArchitectureOutput.api_overview} - -## Security Controls -${geminiArchitectureOutput.security_controls} - -## Review Summary -${codexReviewOutput.summary} -Quality Rating: ${codexReviewOutput.quality_rating}/5 -` - - Write(`${sessionFolder}/spec/architecture/_index.md`, archIndexContent) - - return { - outputPath: 'spec/architecture/_index.md', - documentSummary: `Architecture generated with ${adrs.length} ADRs, quality rating ${codexReviewOutput.quality_rating}/5` - } -} -``` - -## DRAFT-004: Epics & Stories - -Gemini CLI decomposition to generate EPIC-*.md files. - -```javascript -if (docType === 'epics') { - // === Epic Decomposition CLI === - Bash({ - command: `ccw cli -p "PURPOSE: Decompose requirements into executable Epics and Stories for implementation planning. -Success: 3-7 Epics with prioritized Stories, dependency map, and MVP subset clearly defined. - -PRODUCT BRIEF (summary): -${priorDocs.productBrief?.slice(0, 2000) || ''} - -REQUIREMENTS: -${priorDocs.requirementsIndex?.slice(0, 5000) || ''} - -ARCHITECTURE (summary): -${priorDocs.architectureIndex?.slice(0, 3000) || ''} - -TASK: -- Group requirements into 3-7 logical Epics: - - Each Epic: EPIC-NNN ID, title, description, priority (Must/Should/Could) - - Group by functional domain or user journey stage - - Tag MVP Epics (minimum set for initial release) -- For each Epic, generate 2-5 Stories: - - Each Story: STORY-{EPIC}-NNN ID, title - - User story format: As a [persona], I want [action] so that [benefit] - - 2-4 acceptance criteria per story (testable) - - Relative size estimate: S/M/L/XL - - Trace to source requirement(s): REQ-NNN -- Create dependency map: - - Cross-Epic dependencies (which Epics block others) - - Mermaid graph LR format - - Recommended execution order with rationale -- Define MVP: - - Which Epics are in MVP - - MVP definition of done (3-5 criteria) - - What is explicitly deferred post-MVP - -MODE: analysis -EXPECTED: Structured output with: Epic list (ID, title, priority, MVP flag), Stories per Epic (ID, user story, AC, size, trace), dependency Mermaid diagram, execution order, MVP definition -CONSTRAINTS: Every Must-have requirement must appear in at least one Story. Stories must be small enough to implement independently. Dependencies should be minimized across Epics. -" --tool gemini --mode analysis`, - run_in_background: true - }) - - // Wait for CLI result - - // === Integrate Discussion Feedback === - if (discussionFeedback) { - // Extract execution feedback from discuss-004-architecture.md - // Adjust Epic granularity, MVP scope - } - - // === Generate epics/ Directory === - Bash(`mkdir -p "${sessionFolder}/spec/epics"`) - - const timestamp = new Date().toISOString() - const epicsList = parseEpics(cliOutput) - - // Write individual EPIC-*.md files (with stories) - epicsList.forEach(epic => { - const epicFrontmatter = `--- -id: EPIC-${epic.id} -title: "${epic.title}" -priority: ${epic.priority} -mvp: ${epic.mvp} -size: ${epic.size} -requirements: -${epic.reqs.map(r => ` - ${r}`).join('\n')} -architecture: -${epic.adrs.map(a => ` - ${a}`).join('\n')} -dependencies: -${epic.deps.map(d => ` - ${d}`).join('\n')} -status: draft ----` - const storiesContent = epic.stories.map(s => `### ${s.id}: ${s.title} - -**User Story**: ${s.user_story} -**Size**: ${s.size} -**Traces**: ${s.traces.join(', ')} - -**Acceptance Criteria**: -${s.acceptance_criteria.map((ac, i) => `${i+1}. ${ac}`).join('\n')} -`).join('\n') - - const epicContent = `${epicFrontmatter} - -# EPIC-${epic.id}: ${epic.title} - -## Description -${epic.description} - -## Stories -${storiesContent} - -## Requirements -${epic.reqs.map(r => `- [${r}](../requirements/${r}.md)`).join('\n')} - -## Architecture -${epic.adrs.map(a => `- [${a}](../architecture/${a}.md)`).join('\n')} -` - Write(`${sessionFolder}/spec/epics/EPIC-${epic.id}-${epic.slug}.md`, epicContent) - }) - - // Write _index.md (with Mermaid dependency diagram + MVP + links) - const epicsIndexFrontmatter = `--- -session_id: ${specConfig?.session_id || 'unknown'} -phase: 5 -document_type: epics-index -status: draft -generated_at: ${timestamp} -version: 1 -dependencies: - - ../requirements/_index.md - - ../architecture/_index.md ----` - - const epicsIndexContent = `${epicsIndexFrontmatter} - -# Epics & Stories - -## Epic Overview -| ID | Title | Priority | MVP | Size | Status | -|----|-------|----------|-----|------|--------| -${epicsList.map(e => `| [EPIC-${e.id}](EPIC-${e.id}-${e.slug}.md) | ${e.title} | ${e.priority} | ${e.mvp ? '✓' : ''} | ${e.size} | draft |`).join('\n')} - -## Dependency Map -\`\`\`mermaid -${cliOutput.dependency_diagram} -\`\`\` - -## Execution Order -${cliOutput.execution_order} - -## MVP Scope -${cliOutput.mvp_definition} - -### MVP Epics -${epicsList.filter(e => e.mvp).map(e => `- EPIC-${e.id}: ${e.title}`).join('\n')} - -### Post-MVP -${epicsList.filter(e => !e.mvp).map(e => `- EPIC-${e.id}: ${e.title}`).join('\n')} - -## Traceability Matrix -${generateTraceabilityMatrix(epicsList, funcReqs)} -` - - Write(`${sessionFolder}/spec/epics/_index.md`, epicsIndexContent) - - return { - outputPath: 'spec/epics/_index.md', - documentSummary: `Epics generated: ${epicsList.length} total, ${epicsList.filter(e => e.mvp).length} in MVP` - } -} -``` - -## Helper Functions - -```javascript -function parseFunctionalRequirements(cliOutput) { - // Parse CLI JSON output to extract functional requirements - // Returns: [{ id, title, description, user_story, acceptance_criteria[], priority, slug }] -} - -function parseNonFunctionalRequirements(cliOutput) { - // Parse CLI JSON output to extract non-functional requirements - // Returns: [{ id, type, title, requirement, metric, target, slug }] -} - -function parseADRs(geminiOutput, codexOutput) { - // Parse architecture outputs to extract ADRs with review feedback - // Returns: [{ id, title, context, decision, alternatives[], consequences, reviewFeedback, slug }] -} - -function parseEpics(cliOutput) { - // Parse CLI JSON output to extract Epics and Stories - // Returns: [{ id, title, description, priority, mvp, size, stories[], reqs[], adrs[], deps[], slug }] -} - -function fillTemplate(template, data) { - // Fill template placeholders with data - // Apply document-standards.md formatting rules -} - -function generateTraceabilityMatrix(epics, requirements) { - // Generate traceability matrix showing Epic → Requirement mappings -} -``` diff --git a/.claude/skills_lib/team-lifecycle-v2/roles/writer/role.md b/.claude/skills_lib/team-lifecycle-v2/roles/writer/role.md deleted file mode 100644 index f86cff3a..00000000 --- a/.claude/skills_lib/team-lifecycle-v2/roles/writer/role.md +++ /dev/null @@ -1,257 +0,0 @@ -# Role: writer - -Product Brief, Requirements/PRD, Architecture, and Epics & Stories document generation. Maps to spec-generator Phases 2-5. - -## Role Identity - -- **Name**: `writer` -- **Task Prefix**: `DRAFT-*` -- **Output Tag**: `[writer]` -- **Responsibility**: Load Context → Generate Document → Incorporate Feedback → Report -- **Communication**: SendMessage to coordinator only - -## Role Boundaries - -### MUST -- Only process DRAFT-* tasks -- Read templates before generating documents -- Follow document-standards.md formatting rules -- Integrate discussion feedback when available -- Generate proper frontmatter for all documents - -### MUST NOT -- Create tasks for other roles -- Contact other workers directly -- Skip template loading -- Modify discussion records -- Generate documents without loading prior dependencies - -## Message Types - -| Type | Direction | Trigger | Description | -|------|-----------|---------|-------------| -| `draft_ready` | writer → coordinator | Document writing complete | With document path and type | -| `draft_revision` | writer → coordinator | Document revised and resubmitted | Describes changes made | -| `impl_progress` | writer → coordinator | Long writing progress | Multi-document stage progress | -| `error` | writer → coordinator | Unrecoverable error | Template missing, insufficient context, etc. | - -## Message Bus - -Before every `SendMessage`, MUST call `mcp__ccw-tools__team_msg` to log: - -```javascript -// Document ready -mcp__ccw-tools__team_msg({ - operation: "log", - team: teamName, - from: "writer", - to: "coordinator", - type: "draft_ready", - summary: "[writer] Product Brief complete", - ref: `${sessionFolder}/product-brief.md` -}) - -// Document revision -mcp__ccw-tools__team_msg({ - operation: "log", - team: teamName, - from: "writer", - to: "coordinator", - type: "draft_revision", - summary: "[writer] Requirements revised per discussion feedback" -}) - -// Error report -mcp__ccw-tools__team_msg({ - operation: "log", - team: teamName, - from: "writer", - to: "coordinator", - type: "error", - summary: "[writer] Input artifact missing, cannot generate document" -}) -``` - -### CLI Fallback - -When `mcp__ccw-tools__team_msg` MCP is unavailable: - -```bash -ccw team log --team "${teamName}" --from "writer" --to "coordinator" --type "draft_ready" --summary "[writer] Brief complete" --ref "${sessionFolder}/product-brief.md" --json -``` - -## Toolbox - -### Available Commands -- `commands/generate-doc.md` - Multi-CLI document generation for 4 doc types - -### Subagent Capabilities -- None - -### CLI Capabilities -- `gemini`, `codex`, `claude` for multi-perspective analysis - -## Execution (5-Phase) - -### Phase 1: Task Discovery - -```javascript -const tasks = TaskList() -const myTasks = tasks.filter(t => - t.subject.startsWith('DRAFT-') && - t.owner === 'writer' && - t.status === 'pending' && - t.blockedBy.length === 0 -) - -if (myTasks.length === 0) return // idle - -const task = TaskGet({ taskId: myTasks[0].id }) -TaskUpdate({ taskId: task.id, status: 'in_progress' }) -``` - -### Phase 2: Context & Discussion Loading - -```javascript -// Extract session folder from task description -const sessionMatch = task.description.match(/Session:\s*(.+)/) -const sessionFolder = sessionMatch ? sessionMatch[1].trim() : '' - -// Load session config -let specConfig = null -try { specConfig = JSON.parse(Read(`${sessionFolder}/spec/spec-config.json`)) } catch {} - -// Determine document type from task subject -const docType = task.subject.includes('Product Brief') ? 'product-brief' - : task.subject.includes('Requirements') || task.subject.includes('PRD') ? 'requirements' - : task.subject.includes('Architecture') ? 'architecture' - : task.subject.includes('Epics') ? 'epics' - : 'unknown' - -// Load discussion feedback (from preceding DISCUSS task) -const discussionFiles = { - 'product-brief': 'discussions/discuss-001-scope.md', - 'requirements': 'discussions/discuss-002-brief.md', - 'architecture': 'discussions/discuss-003-requirements.md', - 'epics': 'discussions/discuss-004-architecture.md' -} -let discussionFeedback = null -try { discussionFeedback = Read(`${sessionFolder}/${discussionFiles[docType]}`) } catch {} - -// Load prior documents progressively -const priorDocs = {} -if (docType !== 'product-brief') { - try { priorDocs.discoveryContext = Read(`${sessionFolder}/spec/discovery-context.json`) } catch {} -} -if (['requirements', 'architecture', 'epics'].includes(docType)) { - try { priorDocs.productBrief = Read(`${sessionFolder}/spec/product-brief.md`) } catch {} -} -if (['architecture', 'epics'].includes(docType)) { - try { priorDocs.requirementsIndex = Read(`${sessionFolder}/spec/requirements/_index.md`) } catch {} -} -if (docType === 'epics') { - try { priorDocs.architectureIndex = Read(`${sessionFolder}/spec/architecture/_index.md`) } catch {} -} -``` - -### Phase 3: Document Generation - -**Delegate to command file**: - -```javascript -// Load and execute document generation command -const generateDocCommand = Read('commands/generate-doc.md') - -// Execute command with context: -// - docType -// - sessionFolder -// - specConfig -// - discussionFeedback -// - priorDocs -// - task - -// Command will handle: -// - Loading document standards -// - Loading appropriate template -// - Building shared context -// - Routing to type-specific generation (DRAFT-001/002/003/004) -// - Integrating discussion feedback -// - Writing output files - -// Returns: { outputPath, documentSummary } -``` - -### Phase 4: Self-Validation - -```javascript -const docContent = Read(`${sessionFolder}/${outputPath}`) - -const validationChecks = { - has_frontmatter: /^---\n[\s\S]+?\n---/.test(docContent), - sections_complete: /* verify all required sections present */, - cross_references: docContent.includes('session_id'), - discussion_integrated: !discussionFeedback || docContent.includes('Discussion') -} - -const allValid = Object.values(validationChecks).every(v => v) -``` - -### Phase 5: Report to Coordinator - -```javascript -const docTypeLabel = { - 'product-brief': 'Product Brief', - 'requirements': 'Requirements/PRD', - 'architecture': 'Architecture Document', - 'epics': 'Epics & Stories' -} - -mcp__ccw-tools__team_msg({ - operation: "log", team: teamName, - from: "writer", to: "coordinator", - type: "draft_ready", - summary: `[writer] ${docTypeLabel[docType]} 完成: ${allValid ? '验证通过' : '部分验证失败'}`, - ref: `${sessionFolder}/${outputPath}` -}) - -SendMessage({ - type: "message", - recipient: "coordinator", - content: `[writer] ## 文档撰写结果 - -**Task**: ${task.subject} -**文档类型**: ${docTypeLabel[docType]} -**验证状态**: ${allValid ? 'PASS' : 'PARTIAL'} - -### 文档摘要 -${documentSummary} - -### 讨论反馈整合 -${discussionFeedback ? '已整合前序讨论反馈' : '首次撰写'} - -### 自验证结果 -${Object.entries(validationChecks).map(([k, v]) => '- ' + k + ': ' + (v ? 'PASS' : 'FAIL')).join('\n')} - -### 输出位置 -${sessionFolder}/${outputPath} - -文档已就绪，可进入讨论轮次。`, - summary: `[writer] ${docTypeLabel[docType]} 就绪` -}) - -TaskUpdate({ taskId: task.id, status: 'completed' }) - -// Check for next DRAFT task → back to Phase 1 -``` - -## Error Handling - -| Scenario | Resolution | -|----------|------------| -| No DRAFT-* tasks available | Idle, wait for coordinator assignment | -| Prior document not found | Notify coordinator, request prerequisite | -| CLI analysis failure | Retry with fallback tool, then direct generation | -| Template sections incomplete | Generate best-effort, note gaps in report | -| Discussion feedback contradicts prior docs | Note conflict in document, flag for next discussion | -| Session folder missing | Notify coordinator, request session path | -| Unexpected error | Log error via team_msg, report to coordinator | diff --git a/.claude/skills_lib/team-lifecycle-v2/specs/document-standards.md b/.claude/skills_lib/team-lifecycle-v2/specs/document-standards.md deleted file mode 100644 index 2820cd98..00000000 --- a/.claude/skills_lib/team-lifecycle-v2/specs/document-standards.md +++ /dev/null @@ -1,192 +0,0 @@ -# Document Standards - -Defines format conventions, YAML frontmatter schema, naming rules, and content structure for all spec-generator outputs. - -## When to Use - -| Phase | Usage | Section | -|-------|-------|---------| -| All Phases | Frontmatter format | YAML Frontmatter Schema | -| All Phases | File naming | Naming Conventions | -| Phase 2-5 | Document structure | Content Structure | -| Phase 6 | Validation reference | All sections | - ---- - -## YAML Frontmatter Schema - -Every generated document MUST begin with YAML frontmatter: - -```yaml ---- -session_id: SPEC-{slug}-{YYYY-MM-DD} -phase: {1-6} -document_type: {product-brief|requirements|architecture|epics|readiness-report|spec-summary} -status: draft|review|complete -generated_at: {ISO8601 timestamp} -stepsCompleted: [] -version: 1 -dependencies: - - {list of input documents used} ---- -``` - -### Field Definitions - -| Field | Type | Required | Description | -|-------|------|----------|-------------| -| `session_id` | string | Yes | Session identifier matching spec-config.json | -| `phase` | number | Yes | Phase number that generated this document (1-6) | -| `document_type` | string | Yes | One of: product-brief, requirements, architecture, epics, readiness-report, spec-summary | -| `status` | enum | Yes | draft (initial), review (user reviewed), complete (finalized) | -| `generated_at` | string | Yes | ISO8601 timestamp of generation | -| `stepsCompleted` | array | Yes | List of step IDs completed during generation | -| `version` | number | Yes | Document version, incremented on re-generation | -| `dependencies` | array | No | List of input files this document depends on | - -### Status Transitions - -``` -draft -> review -> complete - | ^ - +-------------------+ (direct promotion in auto mode) -``` - -- **draft**: Initial generation, not yet user-reviewed -- **review**: User has reviewed and provided feedback -- **complete**: Finalized, ready for downstream consumption - -In auto mode (`-y`), documents are promoted directly from `draft` to `complete`. - ---- - -## Naming Conventions - -### Session ID Format - -``` -SPEC-{slug}-{YYYY-MM-DD} -``` - -- **slug**: Lowercase, alphanumeric + Chinese characters, hyphens as separators, max 40 chars -- **date**: UTC+8 date in YYYY-MM-DD format - -Examples: -- `SPEC-task-management-system-2026-02-11` -- `SPEC-user-auth-oauth-2026-02-11` - -### Output Files - -| File | Phase | Description | -|------|-------|-------------| -| `spec-config.json` | 1 | Session configuration and state | -| `discovery-context.json` | 1 | Codebase exploration results (optional) | -| `product-brief.md` | 2 | Product brief document | -| `requirements.md` | 3 | PRD document | -| `architecture.md` | 4 | Architecture decisions document | -| `epics.md` | 5 | Epic/Story breakdown document | -| `readiness-report.md` | 6 | Quality validation report | -| `spec-summary.md` | 6 | One-page executive summary | - -### Output Directory - -``` -.workflow/.spec/{session-id}/ -``` - ---- - -## Content Structure - -### Heading Hierarchy - -- `#` (H1): Document title only (one per document) -- `##` (H2): Major sections -- `###` (H3): Subsections -- `####` (H4): Detail items (use sparingly) - -Maximum depth: 4 levels. Prefer flat structures. - -### Section Ordering - -Every document follows this general pattern: - -1. **YAML Frontmatter** (mandatory) -2. **Title** (H1) -3. **Executive Summary** (2-3 sentences) -4. **Core Content Sections** (H2, document-specific) -5. **Open Questions / Risks** (if applicable) -6. **References / Traceability** (links to upstream/downstream docs) - -### Formatting Rules - -| Element | Format | Example | -|---------|--------|---------| -| Requirements | `REQ-{NNN}` prefix | REQ-001: User login | -| Acceptance criteria | Checkbox list | `- [ ] User can log in with email` | -| Architecture decisions | `ADR-{NNN}` prefix | ADR-001: Use PostgreSQL | -| Epics | `EPIC-{NNN}` prefix | EPIC-001: Authentication | -| Stories | `STORY-{EPIC}-{NNN}` prefix | STORY-001-001: Login form | -| Priority tags | MoSCoW labels | `[Must]`, `[Should]`, `[Could]`, `[Won't]` | -| Mermaid diagrams | Fenced code blocks | ````mermaid ... ``` `` | -| Code examples | Language-tagged blocks | ````typescript ... ``` `` | - -### Cross-Reference Format - -Use relative references between documents: - -```markdown -See [Product Brief](product-brief.md#section-name) for details. -Derived from [REQ-001](requirements.md#req-001). -``` - -### Language - -- Document body: Follow user's input language (Chinese or English) -- Technical identifiers: Always English (REQ-001, ADR-001, EPIC-001) -- YAML frontmatter keys: Always English - ---- - -## spec-config.json Schema - -```json -{ - "session_id": "string (required)", - "seed_input": "string (required) - original user input", - "input_type": "text|file (required)", - "timestamp": "ISO8601 (required)", - "mode": "interactive|auto (required)", - "complexity": "simple|moderate|complex (required)", - "depth": "light|standard|comprehensive (required)", - "focus_areas": ["string array"], - "seed_analysis": { - "problem_statement": "string", - "target_users": ["string array"], - "domain": "string", - "constraints": ["string array"], - "dimensions": ["string array - 3-5 exploration dimensions"] - }, - "has_codebase": "boolean", - "phasesCompleted": [ - { - "phase": "number (1-6)", - "name": "string (phase name)", - "output_file": "string (primary output file)", - "completed_at": "ISO8601" - } - ] -} -``` - ---- - -## Validation Checklist - -- [ ] Every document starts with valid YAML frontmatter -- [ ] `session_id` matches across all documents in a session -- [ ] `status` field reflects current document state -- [ ] All cross-references resolve to valid targets -- [ ] Heading hierarchy is correct (no skipped levels) -- [ ] Technical identifiers use correct prefixes -- [ ] Output files are in the correct directory diff --git a/.claude/skills_lib/team-lifecycle-v2/specs/quality-gates.md b/.claude/skills_lib/team-lifecycle-v2/specs/quality-gates.md deleted file mode 100644 index ae968436..00000000 --- a/.claude/skills_lib/team-lifecycle-v2/specs/quality-gates.md +++ /dev/null @@ -1,207 +0,0 @@ -# Quality Gates - -Per-phase quality gate criteria and scoring dimensions for spec-generator outputs. - -## When to Use - -| Phase | Usage | Section | -|-------|-------|---------| -| Phase 2-5 | Post-generation self-check | Per-Phase Gates | -| Phase 6 | Cross-document validation | Cross-Document Validation | -| Phase 6 | Final scoring | Scoring Dimensions | - ---- - -## Quality Thresholds - -| Gate | Score | Action | -|------|-------|--------| -| **Pass** | >= 80% | Continue to next phase | -| **Review** | 60-79% | Log warnings, continue with caveats | -| **Fail** | < 60% | Must address issues before continuing | - -In auto mode (`-y`), Review-level issues are logged but do not block progress. - ---- - -## Scoring Dimensions - -### 1. Completeness (25%) - -All required sections present with substantive content. - -| Score | Criteria | -|-------|----------| -| 100% | All template sections filled with detailed content | -| 75% | All sections present, some lack detail | -| 50% | Major sections present but minor sections missing | -| 25% | Multiple major sections missing or empty | -| 0% | Document is a skeleton only | - -### 2. Consistency (25%) - -Terminology, formatting, and references are uniform across documents. - -| Score | Criteria | -|-------|----------| -| 100% | All terms consistent, all references valid, formatting uniform | -| 75% | Minor terminology variations, all references valid | -| 50% | Some inconsistent terms, 1-2 broken references | -| 25% | Frequent inconsistencies, multiple broken references | -| 0% | Documents contradict each other | - -### 3. Traceability (25%) - -Requirements, architecture decisions, and stories trace back to goals. - -| Score | Criteria | -|-------|----------| -| 100% | Every story traces to a requirement, every requirement traces to a goal | -| 75% | Most items traceable, few orphans | -| 50% | Partial traceability, some disconnected items | -| 25% | Weak traceability, many orphan items | -| 0% | No traceability between documents | - -### 4. Depth (25%) - -Content provides sufficient detail for execution teams. - -| Score | Criteria | -|-------|----------| -| 100% | Acceptance criteria specific and testable, architecture decisions justified, stories estimable | -| 75% | Most items detailed enough, few vague areas | -| 50% | Mix of detailed and vague content | -| 25% | Mostly high-level, lacking actionable detail | -| 0% | Too abstract for execution | - ---- - -## Per-Phase Quality Gates - -### Phase 1: Discovery - -| Check | Criteria | Severity | -|-------|----------|----------| -| Session ID valid | Matches `SPEC-{slug}-{date}` format | Error | -| Problem statement exists | Non-empty, >= 20 characters | Error | -| Target users identified | >= 1 user group | Error | -| Dimensions generated | 3-5 exploration dimensions | Warning | -| Constraints listed | >= 0 (can be empty with justification) | Info | - -### Phase 2: Product Brief - -| Check | Criteria | Severity | -|-------|----------|----------| -| Vision statement | Clear, 1-3 sentences | Error | -| Problem statement | Specific and measurable | Error | -| Target users | >= 1 persona with needs described | Error | -| Goals defined | >= 2 measurable goals | Error | -| Success metrics | >= 2 quantifiable metrics | Warning | -| Scope boundaries | In-scope and out-of-scope listed | Warning | -| Multi-perspective | >= 2 CLI perspectives synthesized | Info | - -### Phase 3: Requirements (PRD) - -| Check | Criteria | Severity | -|-------|----------|----------| -| Functional requirements | >= 3 with REQ-NNN IDs | Error | -| Acceptance criteria | Every requirement has >= 1 criterion | Error | -| MoSCoW priority | Every requirement tagged | Error | -| Non-functional requirements | >= 1 (performance, security, etc.) | Warning | -| User stories | >= 1 per Must-have requirement | Warning | -| Traceability | Requirements trace to product brief goals | Warning | - -### Phase 4: Architecture - -| Check | Criteria | Severity | -|-------|----------|----------| -| Component diagram | Present (Mermaid or ASCII) | Error | -| Tech stack specified | Languages, frameworks, key libraries | Error | -| ADR present | >= 1 Architecture Decision Record | Error | -| ADR has alternatives | Each ADR lists >= 2 options considered | Warning | -| Integration points | External systems/APIs identified | Warning | -| Data model | Key entities and relationships described | Warning | -| Codebase mapping | Mapped to existing code (if has_codebase) | Info | - -### Phase 5: Epics & Stories - -| Check | Criteria | Severity | -|-------|----------|----------| -| Epics defined | 3-7 epics with EPIC-NNN IDs | Error | -| MVP subset | >= 1 epic tagged as MVP | Error | -| Stories per epic | 2-5 stories per epic | Error | -| Story format | "As a...I want...So that..." pattern | Warning | -| Dependency map | Cross-epic dependencies documented | Warning | -| Estimation hints | Relative sizing (S/M/L/XL) per story | Info | -| Traceability | Stories trace to requirements | Warning | - -### Phase 6: Readiness Check - -| Check | Criteria | Severity | -|-------|----------|----------| -| All documents exist | product-brief, requirements, architecture, epics | Error | -| Frontmatter valid | All YAML frontmatter parseable and correct | Error | -| Cross-references valid | All document links resolve | Error | -| Overall score >= 60% | Weighted average across 4 dimensions | Error | -| No unresolved Errors | All Error-severity issues addressed | Error | -| Summary generated | spec-summary.md created | Warning | - ---- - -## Cross-Document Validation - -Checks performed during Phase 6 across all documents: - -### Completeness Matrix - -``` -Product Brief goals -> Requirements (each goal has >= 1 requirement) -Requirements -> Architecture (each Must requirement has design coverage) -Requirements -> Epics (each Must requirement appears in >= 1 story) -Architecture ADRs -> Epics (tech choices reflected in implementation stories) -``` - -### Consistency Checks - -| Check | Documents | Rule | -|-------|-----------|------| -| Terminology | All | Same term used consistently (no synonyms for same concept) | -| User personas | Brief + PRD + Epics | Same user names/roles throughout | -| Scope | Brief + PRD | PRD scope does not exceed brief scope | -| Tech stack | Architecture + Epics | Stories reference correct technologies | - -### Traceability Matrix Format - -```markdown -| Goal | Requirements | Architecture | Epics | -|------|-------------|--------------|-------| -| G-001: ... | REQ-001, REQ-002 | ADR-001 | EPIC-001 | -| G-002: ... | REQ-003 | ADR-002 | EPIC-002, EPIC-003 | -``` - ---- - -## Issue Classification - -### Error (Must Fix) - -- Missing required document or section -- Broken cross-references -- Contradictory information between documents -- Empty acceptance criteria on Must-have requirements -- No MVP subset defined in epics - -### Warning (Should Fix) - -- Vague acceptance criteria -- Missing non-functional requirements -- No success metrics defined -- Incomplete traceability -- Missing architecture review notes - -### Info (Nice to Have) - -- Could add more detailed personas -- Consider additional ADR alternatives -- Story estimation hints missing -- Mermaid diagrams could be more detailed diff --git a/.claude/skills_lib/team-lifecycle-v2/specs/team-config.json b/.claude/skills_lib/team-lifecycle-v2/specs/team-config.json deleted file mode 100644 index 306db7c0..00000000 --- a/.claude/skills_lib/team-lifecycle-v2/specs/team-config.json +++ /dev/null @@ -1,156 +0,0 @@ -{ - "team_name": "team-lifecycle", - "team_display_name": "Team Lifecycle", - "description": "Unified team skill covering spec-to-dev-to-test full lifecycle", - "version": "2.0.0", - "architecture": "folder-based", - "role_structure": "roles/{name}/role.md + roles/{name}/commands/*.md", - - "roles": { - "coordinator": { - "task_prefix": null, - "responsibility": "Pipeline orchestration, requirement clarification, task chain creation, message dispatch", - "message_types": ["plan_approved", "plan_revision", "task_unblocked", "fix_required", "error", "shutdown"] - }, - "analyst": { - "task_prefix": "RESEARCH", - "responsibility": "Seed analysis, codebase exploration, multi-dimensional context gathering", - "message_types": ["research_ready", "research_progress", "error"] - }, - "writer": { - "task_prefix": "DRAFT", - "responsibility": "Product Brief / PRD / Architecture / Epics document generation", - "message_types": ["draft_ready", "draft_revision", "impl_progress", "error"] - }, - "discussant": { - "task_prefix": "DISCUSS", - "responsibility": "Multi-perspective critique, consensus building, conflict escalation", - "message_types": ["discussion_ready", "discussion_blocked", "impl_progress", "error"] - }, - "planner": { - "task_prefix": "PLAN", - "responsibility": "Multi-angle code exploration, structured implementation planning", - "message_types": ["plan_ready", "plan_revision", "impl_progress", "error"] - }, - "executor": { - "task_prefix": "IMPL", - "responsibility": "Code implementation following approved plans", - "message_types": ["impl_complete", "impl_progress", "error"] - }, - "tester": { - "task_prefix": "TEST", - "responsibility": "Adaptive test-fix cycles, progressive testing, quality gates", - "message_types": ["test_result", "impl_progress", "fix_required", "error"] - }, - "reviewer": { - "task_prefix": "REVIEW", - "additional_prefixes": ["QUALITY"], - "responsibility": "Code review (REVIEW-*) + Spec quality validation (QUALITY-*)", - "message_types": ["review_result", "quality_result", "fix_required", "error"] - }, - "explorer": { - "task_prefix": "EXPLORE", - "responsibility": "Code search, pattern discovery, dependency tracing. Service role — on-demand by coordinator", - "role_type": "service", - "message_types": ["explore_ready", "explore_progress", "task_failed"] - }, - "architect": { - "task_prefix": "ARCH", - "responsibility": "Architecture assessment, tech feasibility, design pattern review. Consulting role — on-demand by coordinator", - "role_type": "consulting", - "consultation_modes": ["spec-review", "plan-review", "code-review", "consult", "feasibility"], - "message_types": ["arch_ready", "arch_concern", "arch_progress", "error"] - }, - "fe-developer": { - "task_prefix": "DEV-FE", - "responsibility": "Frontend component/page implementation, design token consumption, responsive UI", - "role_type": "frontend-pipeline", - "message_types": ["dev_fe_complete", "dev_fe_progress", "error"] - }, - "fe-qa": { - "task_prefix": "QA-FE", - "responsibility": "5-dimension frontend review (quality, a11y, design compliance, UX, pre-delivery), GC loop", - "role_type": "frontend-pipeline", - "message_types": ["qa_fe_passed", "qa_fe_result", "fix_required", "error"] - } - }, - - "pipelines": { - "spec-only": { - "description": "Specification pipeline: research → discuss → draft → quality", - "task_chain": [ - "RESEARCH-001", - "DISCUSS-001", "DRAFT-001", "DISCUSS-002", - "DRAFT-002", "DISCUSS-003", "DRAFT-003", "DISCUSS-004", - "DRAFT-004", "DISCUSS-005", "QUALITY-001", "DISCUSS-006" - ] - }, - "impl-only": { - "description": "Implementation pipeline: plan → implement → test + review", - "task_chain": ["PLAN-001", "IMPL-001", "TEST-001", "REVIEW-001"] - }, - "full-lifecycle": { - "description": "Full lifecycle: spec pipeline → implementation pipeline", - "task_chain": "spec-only + impl-only (PLAN-001 blockedBy DISCUSS-006)" - }, - "fe-only": { - "description": "Frontend-only pipeline: plan → frontend dev → frontend QA", - "task_chain": ["PLAN-001", "DEV-FE-001", "QA-FE-001"], - "gc_loop": { "max_rounds": 2, "convergence": "score >= 8 && critical === 0" } - }, - "fullstack": { - "description": "Fullstack pipeline: plan → backend + frontend parallel → test + QA", - "task_chain": ["PLAN-001", "IMPL-001||DEV-FE-001", "TEST-001||QA-FE-001", "REVIEW-001"], - "sync_points": ["REVIEW-001"] - }, - "full-lifecycle-fe": { - "description": "Full lifecycle with frontend: spec → plan → backend + frontend → test + QA", - "task_chain": "spec-only + fullstack (PLAN-001 blockedBy DISCUSS-006)" - } - }, - - "frontend_detection": { - "keywords": ["component", "page", "UI", "前端", "frontend", "CSS", "HTML", "React", "Vue", "Tailwind", "组件", "页面", "样式", "layout", "responsive", "Svelte", "Next.js", "Nuxt", "shadcn", "设计系统", "design system"], - "file_patterns": ["*.tsx", "*.jsx", "*.vue", "*.svelte", "*.css", "*.scss", "*.html"], - "routing_rules": { - "frontend_only": "All tasks match frontend keywords, no backend/API mentions", - "fullstack": "Mix of frontend and backend tasks", - "backend_only": "No frontend keywords detected (default impl-only)" - } - }, - - "ui_ux_pro_max": { - "skill_name": "ui-ux-pro-max", - "install_command": "/plugin install ui-ux-pro-max@ui-ux-pro-max-skill", - "invocation": "Skill(skill=\"ui-ux-pro-max\", args=\"...\")", - "domains": ["product", "style", "typography", "color", "landing", "chart", "ux", "web"], - "stacks": ["html-tailwind", "react", "nextjs", "vue", "svelte", "shadcn", "swiftui", "react-native", "flutter"], - "fallback": "llm-general-knowledge", - "design_intelligence_chain": ["analyst → design-intelligence.json", "architect → design-tokens.json", "fe-developer → tokens.css", "fe-qa → anti-pattern audit"] - }, - - "shared_memory": { - "file": "shared-memory.json", - "schema": { - "design_intelligence": "From analyst via ui-ux-pro-max", - "design_token_registry": "From architect, consumed by fe-developer/fe-qa", - "component_inventory": "From fe-developer, list of implemented components", - "style_decisions": "Accumulated design decisions", - "qa_history": "From fe-qa, audit trail", - "industry_context": "Industry + strictness config" - } - }, - - "collaboration_patterns": ["CP-1", "CP-2", "CP-4", "CP-5", "CP-6", "CP-10"], - - "session_dirs": { - "base": ".workflow/.team/TLS-{slug}-{YYYY-MM-DD}/", - "spec": "spec/", - "discussions": "discussions/", - "plan": "plan/", - "explorations": "explorations/", - "architecture": "architecture/", - "wisdom": "wisdom/", - "messages": ".workflow/.team-msg/{team-name}/" - } -} diff --git a/.claude/skills_lib/team-lifecycle-v2/templates/architecture-doc.md b/.claude/skills_lib/team-lifecycle-v2/templates/architecture-doc.md deleted file mode 100644 index 5106de03..00000000 --- a/.claude/skills_lib/team-lifecycle-v2/templates/architecture-doc.md +++ /dev/null @@ -1,254 +0,0 @@ -# Architecture Document Template (Directory Structure) - -Template for generating architecture decision documents as a directory of individual ADR files in Phase 4. - -## Usage Context - -| Phase | Usage | -|-------|-------| -| Phase 4 (Architecture) | Generate `architecture/` directory from requirements analysis | -| Output Location | `{workDir}/architecture/` | - -## Output Structure - -``` -{workDir}/architecture/ -├── _index.md # Overview, components, tech stack, data model, security -├── ADR-001-{slug}.md # Individual Architecture Decision Record -├── ADR-002-{slug}.md -└── ... -``` - ---- - -## Template: _index.md - -```markdown ---- -session_id: {session_id} -phase: 4 -document_type: architecture-index -status: draft -generated_at: {timestamp} -version: 1 -dependencies: - - ../spec-config.json - - ../product-brief.md - - ../requirements/_index.md ---- - -# Architecture: {product_name} - -{executive_summary - high-level architecture approach and key decisions} - -## System Overview - -### Architecture Style -{description of chosen architecture style: microservices, monolith, serverless, etc.} - -### System Context Diagram - -```mermaid -C4Context - title System Context Diagram - Person(user, "User", "Primary user") - System(system, "{product_name}", "Core system") - System_Ext(ext1, "{external_system}", "{description}") - Rel(user, system, "Uses") - Rel(system, ext1, "Integrates with") -``` - -## Component Architecture - -### Component Diagram - -```mermaid -graph TD - subgraph "{product_name}" - A[Component A] --> B[Component B] - B --> C[Component C] - A --> D[Component D] - end - B --> E[External Service] -``` - -### Component Descriptions - -| Component | Responsibility | Technology | Dependencies | -|-----------|---------------|------------|--------------| -| {component_name} | {what it does} | {tech stack} | {depends on} | - -## Technology Stack - -### Core Technologies - -| Layer | Technology | Version | Rationale | -|-------|-----------|---------|-----------| -| Frontend | {technology} | {version} | {why chosen} | -| Backend | {technology} | {version} | {why chosen} | -| Database | {technology} | {version} | {why chosen} | -| Infrastructure | {technology} | {version} | {why chosen} | - -### Key Libraries & Frameworks - -| Library | Purpose | License | -|---------|---------|---------| -| {library_name} | {purpose} | {license} | - -## Architecture Decision Records - -| ADR | Title | Status | Key Choice | -|-----|-------|--------|------------| -| [ADR-001](ADR-001-{slug}.md) | {title} | Accepted | {one-line summary} | -| [ADR-002](ADR-002-{slug}.md) | {title} | Accepted | {one-line summary} | -| [ADR-003](ADR-003-{slug}.md) | {title} | Proposed | {one-line summary} | - -## Data Architecture - -### Data Model - -```mermaid -erDiagram - ENTITY_A ||--o{ ENTITY_B : "has many" - ENTITY_A { - string id PK - string name - datetime created_at - } - ENTITY_B { - string id PK - string entity_a_id FK - string value - } -``` - -### Data Storage Strategy - -| Data Type | Storage | Retention | Backup | -|-----------|---------|-----------|--------| -| {type} | {storage solution} | {retention policy} | {backup strategy} | - -## API Design - -### API Overview - -| Endpoint | Method | Purpose | Auth | -|----------|--------|---------|------| -| {/api/resource} | {GET/POST/etc} | {purpose} | {auth type} | - -## Security Architecture - -### Security Controls - -| Control | Implementation | Requirement | -|---------|---------------|-------------| -| Authentication | {approach} | [NFR-S-{NNN}](../requirements/NFR-S-{NNN}-{slug}.md) | -| Authorization | {approach} | [NFR-S-{NNN}](../requirements/NFR-S-{NNN}-{slug}.md) | -| Data Protection | {approach} | [NFR-S-{NNN}](../requirements/NFR-S-{NNN}-{slug}.md) | - -## Infrastructure & Deployment - -### Deployment Architecture - -{description of deployment model: containers, serverless, VMs, etc.} - -### Environment Strategy - -| Environment | Purpose | Configuration | -|-------------|---------|---------------| -| Development | Local development | {config} | -| Staging | Pre-production testing | {config} | -| Production | Live system | {config} | - -## Codebase Integration - -{if has_codebase is true:} - -### Existing Code Mapping - -| New Component | Existing Module | Integration Type | Notes | -|--------------|----------------|------------------|-------| -| {component} | {existing module path} | Extend/Replace/New | {notes} | - -### Migration Notes -{any migration considerations for existing code} - -## Quality Attributes - -| Attribute | Target | Measurement | ADR Reference | -|-----------|--------|-------------|---------------| -| Performance | {target} | {how measured} | [ADR-{NNN}](ADR-{NNN}-{slug}.md) | -| Scalability | {target} | {how measured} | [ADR-{NNN}](ADR-{NNN}-{slug}.md) | -| Reliability | {target} | {how measured} | [ADR-{NNN}](ADR-{NNN}-{slug}.md) | - -## Risks & Mitigations - -| Risk | Impact | Probability | Mitigation | -|------|--------|-------------|------------| -| {risk} | High/Medium/Low | High/Medium/Low | {mitigation approach} | - -## Open Questions - -- [ ] {architectural question 1} -- [ ] {architectural question 2} - -## References - -- Derived from: [Requirements](../requirements/_index.md), [Product Brief](../product-brief.md) -- Next: [Epics & Stories](../epics/_index.md) -``` - ---- - -## Template: ADR-NNN-{slug}.md (Individual Architecture Decision Record) - -```markdown ---- -id: ADR-{NNN} -status: Accepted -traces_to: [{REQ-NNN}, {NFR-X-NNN}] -date: {timestamp} ---- - -# ADR-{NNN}: {decision_title} - -## Context - -{what is the situation that motivates this decision} - -## Decision - -{what is the chosen approach} - -## Alternatives Considered - -| Option | Pros | Cons | -|--------|------|------| -| {option_1 - chosen} | {pros} | {cons} | -| {option_2} | {pros} | {cons} | -| {option_3} | {pros} | {cons} | - -## Consequences - -- **Positive**: {positive outcomes} -- **Negative**: {tradeoffs accepted} -- **Risks**: {risks to monitor} - -## Traces - -- **Requirements**: [REQ-{NNN}](../requirements/REQ-{NNN}-{slug}.md), [NFR-X-{NNN}](../requirements/NFR-X-{NNN}-{slug}.md) -- **Implemented by**: [EPIC-{NNN}](../epics/EPIC-{NNN}-{slug}.md) (added in Phase 5) -``` - ---- - -## Variable Descriptions - -| Variable | Source | Description | -|----------|--------|-------------| -| `{session_id}` | spec-config.json | Session identifier | -| `{timestamp}` | Runtime | ISO8601 generation timestamp | -| `{product_name}` | product-brief.md | Product/feature name | -| `{NNN}` | Auto-increment | ADR/requirement number | -| `{slug}` | Auto-generated | Kebab-case from decision title | -| `{has_codebase}` | spec-config.json | Whether existing codebase exists | diff --git a/.claude/skills_lib/team-lifecycle-v2/templates/epics-template.md b/.claude/skills_lib/team-lifecycle-v2/templates/epics-template.md deleted file mode 100644 index 939d933c..00000000 --- a/.claude/skills_lib/team-lifecycle-v2/templates/epics-template.md +++ /dev/null @@ -1,196 +0,0 @@ -# Epics & Stories Template (Directory Structure) - -Template for generating epic/story breakdown as a directory of individual Epic files in Phase 5. - -## Usage Context - -| Phase | Usage | -|-------|-------| -| Phase 5 (Epics & Stories) | Generate `epics/` directory from requirements decomposition | -| Output Location | `{workDir}/epics/` | - -## Output Structure - -``` -{workDir}/epics/ -├── _index.md # Overview table + dependency map + MVP scope + execution order -├── EPIC-001-{slug}.md # Individual Epic with its Stories -├── EPIC-002-{slug}.md -└── ... -``` - ---- - -## Template: _index.md - -```markdown ---- -session_id: {session_id} -phase: 5 -document_type: epics-index -status: draft -generated_at: {timestamp} -version: 1 -dependencies: - - ../spec-config.json - - ../product-brief.md - - ../requirements/_index.md - - ../architecture/_index.md ---- - -# Epics & Stories: {product_name} - -{executive_summary - overview of epic structure and MVP scope} - -## Epic Overview - -| Epic ID | Title | Priority | MVP | Stories | Est. Size | -|---------|-------|----------|-----|---------|-----------| -| [EPIC-001](EPIC-001-{slug}.md) | {title} | Must | Yes | {n} | {S/M/L/XL} | -| [EPIC-002](EPIC-002-{slug}.md) | {title} | Must | Yes | {n} | {S/M/L/XL} | -| [EPIC-003](EPIC-003-{slug}.md) | {title} | Should | No | {n} | {S/M/L/XL} | - -## Dependency Map - -```mermaid -graph LR - EPIC-001 --> EPIC-002 - EPIC-001 --> EPIC-003 - EPIC-002 --> EPIC-004 - EPIC-003 --> EPIC-005 -``` - -### Dependency Notes -{explanation of why these dependencies exist and suggested execution order} - -### Recommended Execution Order -1. [EPIC-{NNN}](EPIC-{NNN}-{slug}.md): {reason - foundational} -2. [EPIC-{NNN}](EPIC-{NNN}-{slug}.md): {reason - depends on #1} -3. ... - -## MVP Scope - -### MVP Epics -{list of epics included in MVP with justification, linking to each} - -### MVP Definition of Done -- [ ] {MVP completion criterion 1} -- [ ] {MVP completion criterion 2} -- [ ] {MVP completion criterion 3} - -## Traceability Matrix - -| Requirement | Epic | Stories | Architecture | -|-------------|------|---------|--------------| -| [REQ-001](../requirements/REQ-001-{slug}.md) | [EPIC-001](EPIC-001-{slug}.md) | STORY-001-001, STORY-001-002 | [ADR-001](../architecture/ADR-001-{slug}.md) | -| [REQ-002](../requirements/REQ-002-{slug}.md) | [EPIC-001](EPIC-001-{slug}.md) | STORY-001-003 | Component B | -| [REQ-003](../requirements/REQ-003-{slug}.md) | [EPIC-002](EPIC-002-{slug}.md) | STORY-002-001 | [ADR-002](../architecture/ADR-002-{slug}.md) | - -## Estimation Summary - -| Size | Meaning | Count | -|------|---------|-------| -| S | Small - well-understood, minimal risk | {n} | -| M | Medium - some complexity, moderate risk | {n} | -| L | Large - significant complexity, should consider splitting | {n} | -| XL | Extra Large - high complexity, must split before implementation | {n} | - -## Risks & Considerations - -| Risk | Affected Epics | Mitigation | -|------|---------------|------------| -| {risk description} | [EPIC-{NNN}](EPIC-{NNN}-{slug}.md) | {mitigation} | - -## Open Questions - -- [ ] {question about scope or implementation 1} -- [ ] {question about scope or implementation 2} - -## References - -- Derived from: [Requirements](../requirements/_index.md), [Architecture](../architecture/_index.md) -- Handoff to: execution workflows (lite-plan, plan, req-plan) -``` - ---- - -## Template: EPIC-NNN-{slug}.md (Individual Epic) - -```markdown ---- -id: EPIC-{NNN} -priority: {Must|Should|Could} -mvp: {true|false} -size: {S|M|L|XL} -requirements: [REQ-{NNN}] -architecture: [ADR-{NNN}] -dependencies: [EPIC-{NNN}] -status: draft ---- - -# EPIC-{NNN}: {epic_title} - -**Priority**: {Must|Should|Could} -**MVP**: {Yes|No} -**Estimated Size**: {S|M|L|XL} - -## Description - -{detailed epic description} - -## Requirements - -- [REQ-{NNN}](../requirements/REQ-{NNN}-{slug}.md): {title} -- [REQ-{NNN}](../requirements/REQ-{NNN}-{slug}.md): {title} - -## Architecture - -- [ADR-{NNN}](../architecture/ADR-{NNN}-{slug}.md): {title} -- Component: {component_name} - -## Dependencies - -- [EPIC-{NNN}](EPIC-{NNN}-{slug}.md) (blocking): {reason} -- [EPIC-{NNN}](EPIC-{NNN}-{slug}.md) (soft): {reason} - -## Stories - -### STORY-{EPIC}-001: {story_title} - -**User Story**: As a {persona}, I want to {action} so that {benefit}. - -**Acceptance Criteria**: -- [ ] {criterion 1} -- [ ] {criterion 2} -- [ ] {criterion 3} - -**Size**: {S|M|L|XL} -**Traces to**: [REQ-{NNN}](../requirements/REQ-{NNN}-{slug}.md) - ---- - -### STORY-{EPIC}-002: {story_title} - -**User Story**: As a {persona}, I want to {action} so that {benefit}. - -**Acceptance Criteria**: -- [ ] {criterion 1} -- [ ] {criterion 2} - -**Size**: {S|M|L|XL} -**Traces to**: [REQ-{NNN}](../requirements/REQ-{NNN}-{slug}.md) -``` - ---- - -## Variable Descriptions - -| Variable | Source | Description | -|----------|--------|-------------| -| `{session_id}` | spec-config.json | Session identifier | -| `{timestamp}` | Runtime | ISO8601 generation timestamp | -| `{product_name}` | product-brief.md | Product/feature name | -| `{EPIC}` | Auto-increment | Epic number (3 digits) | -| `{NNN}` | Auto-increment | Story/requirement number | -| `{slug}` | Auto-generated | Kebab-case from epic/story title | -| `{S\|M\|L\|XL}` | CLI analysis | Relative size estimate | diff --git a/.claude/skills_lib/team-lifecycle-v2/templates/product-brief.md b/.claude/skills_lib/team-lifecycle-v2/templates/product-brief.md deleted file mode 100644 index ffbdf437..00000000 --- a/.claude/skills_lib/team-lifecycle-v2/templates/product-brief.md +++ /dev/null @@ -1,133 +0,0 @@ -# Product Brief Template - -Template for generating product brief documents in Phase 2. - -## Usage Context - -| Phase | Usage | -|-------|-------| -| Phase 2 (Product Brief) | Generate product-brief.md from multi-CLI analysis | -| Output Location | `{workDir}/product-brief.md` | - ---- - -## Template - -```markdown ---- -session_id: {session_id} -phase: 2 -document_type: product-brief -status: draft -generated_at: {timestamp} -stepsCompleted: [] -version: 1 -dependencies: - - spec-config.json ---- - -# Product Brief: {product_name} - -{executive_summary - 2-3 sentences capturing the essence of the product/feature} - -## Vision - -{vision_statement - clear, aspirational 1-3 sentence statement of what success looks like} - -## Problem Statement - -### Current Situation -{description of the current state and pain points} - -### Impact -{quantified impact of the problem - who is affected, how much, how often} - -## Target Users - -{for each user persona:} - -### {Persona Name} -- **Role**: {user's role/context} -- **Needs**: {primary needs related to this product} -- **Pain Points**: {current frustrations} -- **Success Criteria**: {what success looks like for this user} - -## Goals & Success Metrics - -| Goal ID | Goal | Success Metric | Target | -|---------|------|----------------|--------| -| G-001 | {goal description} | {measurable metric} | {specific target} | -| G-002 | {goal description} | {measurable metric} | {specific target} | - -## Scope - -### In Scope -- {feature/capability 1} -- {feature/capability 2} -- {feature/capability 3} - -### Out of Scope -- {explicitly excluded item 1} -- {explicitly excluded item 2} - -### Assumptions -- {key assumption 1} -- {key assumption 2} - -## Competitive Landscape - -| Aspect | Current State | Proposed Solution | Advantage | -|--------|--------------|-------------------|-----------| -| {aspect} | {how it's done now} | {our approach} | {differentiator} | - -## Constraints & Dependencies - -### Technical Constraints -- {constraint 1} -- {constraint 2} - -### Business Constraints -- {constraint 1} - -### Dependencies -- {external dependency 1} -- {external dependency 2} - -## Multi-Perspective Synthesis - -### Product Perspective -{summary of product/market analysis findings} - -### Technical Perspective -{summary of technical feasibility and constraints} - -### User Perspective -{summary of user journey and UX considerations} - -### Convergent Themes -{themes where all perspectives agree} - -### Conflicting Views -{areas where perspectives differ, with notes on resolution approach} - -## Open Questions - -- [ ] {unresolved question 1} -- [ ] {unresolved question 2} - -## References - -- Derived from: [spec-config.json](spec-config.json) -- Next: [Requirements PRD](requirements.md) -``` - -## Variable Descriptions - -| Variable | Source | Description | -|----------|--------|-------------| -| `{session_id}` | spec-config.json | Session identifier | -| `{timestamp}` | Runtime | ISO8601 generation timestamp | -| `{product_name}` | Seed analysis | Product/feature name | -| `{executive_summary}` | CLI synthesis | 2-3 sentence summary | -| `{vision_statement}` | CLI product perspective | Aspirational vision | -| All `{...}` fields | CLI analysis outputs | Filled from multi-perspective analysis | diff --git a/.claude/skills_lib/team-lifecycle-v2/templates/requirements-prd.md b/.claude/skills_lib/team-lifecycle-v2/templates/requirements-prd.md deleted file mode 100644 index 0b1dbf28..00000000 --- a/.claude/skills_lib/team-lifecycle-v2/templates/requirements-prd.md +++ /dev/null @@ -1,224 +0,0 @@ -# Requirements PRD Template (Directory Structure) - -Template for generating Product Requirements Document as a directory of individual requirement files in Phase 3. - -## Usage Context - -| Phase | Usage | -|-------|-------| -| Phase 3 (Requirements) | Generate `requirements/` directory from product brief expansion | -| Output Location | `{workDir}/requirements/` | - -## Output Structure - -``` -{workDir}/requirements/ -├── _index.md # Summary + MoSCoW table + traceability matrix + links -├── REQ-001-{slug}.md # Individual functional requirement -├── REQ-002-{slug}.md -├── NFR-P-001-{slug}.md # Non-functional: Performance -├── NFR-S-001-{slug}.md # Non-functional: Security -├── NFR-SC-001-{slug}.md # Non-functional: Scalability -├── NFR-U-001-{slug}.md # Non-functional: Usability -└── ... -``` - ---- - -## Template: _index.md - -```markdown ---- -session_id: {session_id} -phase: 3 -document_type: requirements-index -status: draft -generated_at: {timestamp} -version: 1 -dependencies: - - ../spec-config.json - - ../product-brief.md ---- - -# Requirements: {product_name} - -{executive_summary - brief overview of what this PRD covers and key decisions} - -## Requirement Summary - -| Priority | Count | Coverage | -|----------|-------|----------| -| Must Have | {n} | {description of must-have scope} | -| Should Have | {n} | {description of should-have scope} | -| Could Have | {n} | {description of could-have scope} | -| Won't Have | {n} | {description of explicitly excluded} | - -## Functional Requirements - -| ID | Title | Priority | Traces To | -|----|-------|----------|-----------| -| [REQ-001](REQ-001-{slug}.md) | {title} | Must | [G-001](../product-brief.md#goals--success-metrics) | -| [REQ-002](REQ-002-{slug}.md) | {title} | Must | [G-001](../product-brief.md#goals--success-metrics) | -| [REQ-003](REQ-003-{slug}.md) | {title} | Should | [G-002](../product-brief.md#goals--success-metrics) | - -## Non-Functional Requirements - -### Performance - -| ID | Title | Target | -|----|-------|--------| -| [NFR-P-001](NFR-P-001-{slug}.md) | {title} | {target value} | - -### Security - -| ID | Title | Standard | -|----|-------|----------| -| [NFR-S-001](NFR-S-001-{slug}.md) | {title} | {standard/framework} | - -### Scalability - -| ID | Title | Target | -|----|-------|--------| -| [NFR-SC-001](NFR-SC-001-{slug}.md) | {title} | {target value} | - -### Usability - -| ID | Title | Target | -|----|-------|--------| -| [NFR-U-001](NFR-U-001-{slug}.md) | {title} | {target value} | - -## Data Requirements - -### Data Entities - -| Entity | Description | Key Attributes | -|--------|-------------|----------------| -| {entity_name} | {description} | {attr1, attr2, attr3} | - -### Data Flows - -{description of key data flows, optionally with Mermaid diagram} - -## Integration Requirements - -| System | Direction | Protocol | Data Format | Notes | -|--------|-----------|----------|-------------|-------| -| {system_name} | Inbound/Outbound/Both | {REST/gRPC/etc} | {JSON/XML/etc} | {notes} | - -## Constraints & Assumptions - -### Constraints -- {technical or business constraint 1} -- {technical or business constraint 2} - -### Assumptions -- {assumption 1 - must be validated} -- {assumption 2 - must be validated} - -## Priority Rationale - -{explanation of MoSCoW prioritization decisions, especially for Should/Could boundaries} - -## Traceability Matrix - -| Goal | Requirements | -|------|-------------| -| G-001 | [REQ-001](REQ-001-{slug}.md), [REQ-002](REQ-002-{slug}.md), [NFR-P-001](NFR-P-001-{slug}.md) | -| G-002 | [REQ-003](REQ-003-{slug}.md), [NFR-S-001](NFR-S-001-{slug}.md) | - -## Open Questions - -- [ ] {unresolved question 1} -- [ ] {unresolved question 2} - -## References - -- Derived from: [Product Brief](../product-brief.md) -- Next: [Architecture](../architecture/_index.md) -``` - ---- - -## Template: REQ-NNN-{slug}.md (Individual Functional Requirement) - -```markdown ---- -id: REQ-{NNN} -type: functional -priority: {Must|Should|Could|Won't} -traces_to: [G-{NNN}] -status: draft ---- - -# REQ-{NNN}: {requirement_title} - -**Priority**: {Must|Should|Could|Won't} - -## Description - -{detailed requirement description} - -## User Story - -As a {persona}, I want to {action} so that {benefit}. - -## Acceptance Criteria - -- [ ] {specific, testable criterion 1} -- [ ] {specific, testable criterion 2} -- [ ] {specific, testable criterion 3} - -## Traces - -- **Goal**: [G-{NNN}](../product-brief.md#goals--success-metrics) -- **Architecture**: [ADR-{NNN}](../architecture/ADR-{NNN}-{slug}.md) (if applicable) -- **Implemented by**: [EPIC-{NNN}](../epics/EPIC-{NNN}-{slug}.md) (added in Phase 5) -``` - ---- - -## Template: NFR-{type}-NNN-{slug}.md (Individual Non-Functional Requirement) - -```markdown ---- -id: NFR-{type}-{NNN} -type: non-functional -category: {Performance|Security|Scalability|Usability} -priority: {Must|Should|Could} -status: draft ---- - -# NFR-{type}-{NNN}: {requirement_title} - -**Category**: {Performance|Security|Scalability|Usability} -**Priority**: {Must|Should|Could} - -## Requirement - -{detailed requirement description} - -## Metric & Target - -| Metric | Target | Measurement Method | -|--------|--------|--------------------| -| {metric} | {target value} | {how measured} | - -## Traces - -- **Goal**: [G-{NNN}](../product-brief.md#goals--success-metrics) -- **Architecture**: [ADR-{NNN}](../architecture/ADR-{NNN}-{slug}.md) (if applicable) -``` - ---- - -## Variable Descriptions - -| Variable | Source | Description | -|----------|--------|-------------| -| `{session_id}` | spec-config.json | Session identifier | -| `{timestamp}` | Runtime | ISO8601 generation timestamp | -| `{product_name}` | product-brief.md | Product/feature name | -| `{NNN}` | Auto-increment | Requirement number (zero-padded 3 digits) | -| `{slug}` | Auto-generated | Kebab-case from requirement title | -| `{type}` | Category | P (Performance), S (Security), SC (Scalability), U (Usability) | -| `{Must\|Should\|Could\|Won't}` | User input / auto | MoSCoW priority tag | diff --git a/.claude/skills_lib/team-skill-designer-v2/SKILL.md b/.claude/skills_lib/team-skill-designer-v2/SKILL.md deleted file mode 100644 index 350fa775..00000000 --- a/.claude/skills_lib/team-skill-designer-v2/SKILL.md +++ /dev/null @@ -1,274 +0,0 @@ ---- -name: team-skill-designer -description: Design and generate unified team skills with role-based routing. All team members invoke ONE skill, SKILL.md routes to role-specific execution via --role arg. Triggers on "design team skill", "create team skill", "team skill designer". -allowed-tools: Task, AskUserQuestion, Read, Write, Bash, Glob, Grep ---- - -# Team Skill Designer v2 - -Meta-skill for creating unified team skills where all team members invoke ONE skill with role-based routing. Generates a complete skill package with SKILL.md as role router and `roles/` folder for per-role execution detail. - -**v2 Style**: 生成的技能包遵循 v3 撰写规范 — text + decision tables + flow symbols, 无伪代码, `` 占位符, 显式节拍控制。 - -## Architecture Overview - -``` -┌─────────────────────────────────────────────────────────────────┐ -│ Team Skill Designer (this meta-skill) │ -│ → Collect requirements → Analyze patterns → Generate skill pkg │ -└───────────────┬─────────────────────────────────────────────────┘ - │ - ┌───────────┼───────────┬───────────┬───────────┐ - ↓ ↓ ↓ ↓ ↓ -┌─────────┐ ┌─────────┐ ┌─────────┐ ┌─────────┐ ┌─────────┐ -│ Phase 1 │ │ Phase 2 │ │ Phase 3 │ │ Phase 4 │ │ Phase 5 │ -│ Require │ │ Pattern │ │ Skill │ │ Integ │ │ Valid │ -│ Collect │ │ Analyze │ │ Gen │ │ Verify │ │ │ -└─────────┘ └─────────┘ └─────────┘ └─────────┘ └─────────┘ - ↓ ↓ ↓ ↓ ↓ - team- pattern- preview/ integ- validated - config.json analysis SKILL.md + report skill pkg - .json roles/*.md .json → delivery -``` - -## Key Innovation: Unified Skill + Role Router - -**Before** (command approach): 5 separate command files → 5 separate skill paths - -**After** (unified skill approach): - -``` -.claude/skills/team-/ -├── SKILL.md → Skill(skill="team-", args="--role=xxx") -├── roles/ -│ ├── coordinator/ -│ │ ├── role.md -│ │ └── commands/ -│ ├── / -│ │ ├── role.md -│ │ └── commands/ -│ └── / -│ ├── role.md -│ └── commands/ -└── specs/ - └── team-config.json -``` - -→ 1 skill entry point, `--role` arg routes to per-role execution - -## Core Design Patterns - -### Pattern 1: Role Router (Unified Entry Point) - -SKILL.md parses `$ARGUMENTS` to extract `--role`: - -``` -Input: Skill(skill="team-", args="--role=planner") - → Parse --role=planner - → Read roles/planner/role.md - → Execute planner-specific phases -``` - -No `--role` → Orchestration Mode (auto route to coordinator). - -### Pattern 2: SKILL.md = Orchestration-Level Only - -SKILL.md 仅包含编排级内容: - -| 包含 | 不包含 | -|------|--------| -| Role Router (parse → dispatch) | Message bus 代码 | -| Architecture 图 | Task lifecycle 代码 | -| Role Registry 表 (含 markdown links) | 工具声明/使用示例 | -| Pipeline 定义 + Cadence Control | 角色特定检测逻辑 | -| Coordinator Spawn Template | 实现级代码块 | -| Shared Infrastructure (Phase 1/5 模板) | | -| Compact Protection | | - -### Pattern 3: Role Files = Self-Contained Execution - -每个 `roles//role.md` 包含角色执行所需的一切: -- Identity, Boundaries (MUST/MUST NOT) -- Toolbox 表 (command links) -- Phase 2-4 核心逻辑 (text + decision tables, 无伪代码) -- Error Handling 表 - -**关键原则**: subagent 加载 role.md 后无需回读 SKILL.md 即可执行。 - -### Pattern 4: v3 Style Output - -生成的技能包遵循以下风格规则: - -| 规则 | 说明 | -|------|------| -| 无伪代码 | 流程用 text + decision tables + flow symbols (→ ├─ └─) | -| 代码块仅限工具调用 | 只有 Task(), TaskCreate(), Bash(), Read() 等实际执行的调用 | -| `` 占位符 | 不使用 `${variable}` 或 `{{handlebars}}` | -| Decision tables | 所有分支逻辑用 `\| Condition \| Action \|` 表格 | -| Phase 1/5 共享 | SKILL.md 定义 Shared Infrastructure, role.md 只写 Phase 2-4 | -| Cadence Control | SKILL.md 包含节拍图和检查点定义 | -| Compact Protection | Phase Reference 表含 Compact 列, 关键 phase 标记重读 | - -### Pattern 5: Batch Role Generation - -Phase 1 一次性收集所有角色 (非逐个): -- Team name + all role definitions in one pass -- Coordinator always generated -- Worker roles collected as batch - -### Pattern 6: Coordinator Commands Alignment - -**dispatch.md 约束**: owner 值匹配 Role Registry | 任务 ID 匹配 Pipeline 图 | 无幽灵角色名 - -**monitor.md 约束**: spawn prompt 含完整 `Skill(skill="...", args="--role=...")` | Task() 含 description + team_name + name | Message Routing 角色名匹配 Registry - -**验证时机**: Phase 4 自动检查。 - ---- - -## Mandatory Prerequisites - -> **Do NOT skip**: Read these before any execution. - -### Specification Documents - -| Document | Purpose | When | -|----------|---------|------| -| [specs/team-design-patterns.md](specs/team-design-patterns.md) | Infrastructure patterns (9) + collaboration index | Phase 0 必读 | -| [specs/collaboration-patterns.md](specs/collaboration-patterns.md) | 11 collaboration patterns with convergence control | Phase 0 必读 | -| [specs/quality-standards.md](specs/quality-standards.md) | Quality criteria (4 dimensions + command standards) | Phase 3 前必读 | - -### Template Files - -| Document | Purpose | -|----------|---------| -| [templates/skill-router-template.md](templates/skill-router-template.md) | 生成 SKILL.md 模板 (v3 style) | -| [templates/role-template.md](templates/role-template.md) | 生成 role.md 模板 (v3 style) | -| [templates/role-command-template.md](templates/role-command-template.md) | 生成 command 文件模板 (v3 style) | - ---- - -## Cadence Control - -**节拍模型**: 串行 5-Phase, 每个 Phase 产出一个 artifact 作为下一 Phase 的输入。 - -``` -Phase Cadence (设计生成节拍) -═══════════════════════════════════════════════════════════════════ -Phase 0 1 2 3 4 5 - │ │ │ │ │ │ - 读规格 → 收集需求 → 模式分析 → 技能生成 → 集成验证 → 质量交付 - │ │ │ │ │ │ - [memory] config analysis preview/ report delivery - .json .json SKILL.md .json → skills/ - roles/ - commands/ -═══════════════════════════════════════════════════════════════════ - -Phase 产物链: - Phase 0 → [in-memory] specs + templates 内化 - Phase 1 → team-config.json (角色定义 + pipeline) - Phase 2 → pattern-analysis.json (模式映射 + 协作模式) - Phase 3 → preview/ 完整技能包 - Phase 4 → integration-report.json (一致性报告) - Phase 5 → validation-report.json + delivery → .claude/skills/team-/ - -检查点: - Phase 3 完成 → ⏸ 向用户展示 preview 结构，确认后进入 Phase 4 - Phase 5 评分 → ⏸ 评分 < 60% 则回退 Phase 3 重新生成 -``` - -**Phase 间衔接**: - -| 当前 Phase | 完成条件 | 产物 | 下一步 | -|------------|----------|------|--------| -| Phase 0 | 3 个 spec + 3 个 template 已读取 | in-memory | → Phase 1 | -| Phase 1 | team-config.json 写入成功 | team-config.json | → Phase 2 | -| Phase 2 | pattern-analysis.json 写入成功 | pattern-analysis.json | → Phase 3 | -| Phase 3 | preview/ 目录下所有文件生成 | preview/* | → ⏸ 用户确认 → Phase 4 | -| Phase 4 | integration-report.json 无 FAIL 项 | integration-report.json | → Phase 5 | -| Phase 5 | score ≥ 80% | delivery to skills/ | → 完成 | - -**回退机制**: - -| 条件 | 回退到 | 动作 | -|------|--------|------| -| Phase 4 发现 FAIL | Phase 3 | 修复后重新生成 | -| Phase 5 score < 60% | Phase 3 | 重大返工 | -| Phase 5 score 60-79% | Phase 4 | 修复建议后重验 | - ---- - -## Execution Flow - -### Phase Reference Documents - -| Phase | Document | Purpose | Compact | -|-------|----------|---------|---------| -| 0 | (inline) | Read specs + templates | N/A | -| 1 | [phases/01-requirements-collection.md](phases/01-requirements-collection.md) | Batch collect team + all role definitions | 完成后可压缩 | -| 2 | [phases/02-pattern-analysis.md](phases/02-pattern-analysis.md) | Per-role pattern matching and phase mapping | 完成后可压缩 | -| 3 | [phases/03-skill-generation.md](phases/03-skill-generation.md) | Generate unified skill package | **⚠️ 压缩后必须重读** | -| 4 | [phases/04-integration-verification.md](phases/04-integration-verification.md) | Verify internal consistency | 压缩后必须重读 | -| 5 | [phases/05-validation.md](phases/05-validation.md) | Quality gate and delivery | 压缩后必须重读 | - -> **⚠️ COMPACT PROTECTION**: Phase 文件是执行文档。当 context compression 发生后，Phase 指令仅剩摘要时，**必须立即 `Read` 对应 phase 文件重新加载后再继续执行**。不得基于摘要执行任何 Step。 - -### Phase 0: Specification Study (Inline) - -**必须在生成前读取以下文件**: - -1. Read `specs/team-design-patterns.md` → 9 基础设施模式 -2. Read `specs/collaboration-patterns.md` → 11 协作模式 -3. Read `specs/quality-standards.md` → 质量标准 -4. Read `templates/skill-router-template.md` → SKILL.md 生成模板 -5. Read `templates/role-template.md` → role.md 生成模板 -6. Read `templates/role-command-template.md` → command 文件模板 - -### Phase 1-5: Delegated - -各 Phase 读取对应 phase 文件执行。See Phase Reference Documents table above. - ---- - -## Directory Setup - -工作目录: `.workflow/.scratchpad/team-skill-/` - -```bash -Bash("mkdir -p .workflow/.scratchpad/team-skill-$(date +%Y%m%d%H%M%S)") -``` - -## Output Structure - -``` -.workflow/.scratchpad/team-skill-/ -├── team-config.json # Phase 1 output -├── pattern-analysis.json # Phase 2 output -├── integration-report.json # Phase 4 output -├── validation-report.json # Phase 5 output -└── preview/ # Phase 3 output (preview before delivery) - ├── SKILL.md - ├── roles/ - │ ├── coordinator/ - │ │ ├── role.md - │ │ └── commands/ - │ └── / - │ ├── role.md - │ └── commands/ - └── specs/ - └── team-config.json - -Final delivery → .claude/skills/team-/ -``` - -## Error Handling - -| Scenario | Resolution | -|----------|------------| -| Specs not found | Fall back to inline pattern knowledge | -| Role name conflicts | AskUserQuestion for rename | -| Task prefix conflicts | Suggest alternative prefix | -| Template variable unresolved | FAIL with specific variable name | -| Quality score < 60% | Re-run Phase 3 with additional context | -| Phase file compressed | Re-read phase file before continuing | diff --git a/.claude/skills_lib/team-skill-designer-v2/phases/01-requirements-collection.md b/.claude/skills_lib/team-skill-designer-v2/phases/01-requirements-collection.md deleted file mode 100644 index 78463cb0..00000000 --- a/.claude/skills_lib/team-skill-designer-v2/phases/01-requirements-collection.md +++ /dev/null @@ -1,200 +0,0 @@ -# Phase 1: Requirements Collection (Task-Driven Inference) - -Analyze task requirements, infer appropriate roles, and generate team configuration. - -## Objective - -- Determine team name and display name -- Analyze task description to infer needed roles (coordinator always included) -- For each role: name, responsibility type, task prefix, capabilities -- Build pipeline from inferred roles -- Generate `team-config.json` - -## Input - -| Source | Description | -|--------|-------------| -| User request | `$ARGUMENTS` or interactive input | -| Specification | `specs/team-design-patterns.md` (read in Phase 0) | - -## Execution Steps - -### Step 1: Team Name + Task Description - -Prompt the user for team name and core task description. - -``` -AskUserQuestion({ - questions: [ - { question: "Team name (lowercase, used as .claude/skills/team-{name}/)", - header: "Team Name", - options: ["custom", "dev", "spec", "security"] }, - { question: "Core task of this team? (system will infer roles automatically)", - header: "Task Desc", - options: ["custom", "fullstack dev", "code review + refactor", "doc writing"] } - ] -}) -``` - -### Step 2: Role Inference (Task-Driven) - -Coordinator is **always** included. Scan the task description for intent signals to infer worker roles. - -#### Role Signal Detection Table - -| Role | Keywords (CN/EN) | Responsibility Type | Task Prefix | -|------|-------------------|---------------------|-------------| -| planner | plan, design, architect, explore, analyze requirements | Orchestration | PLAN | -| executor | implement, develop, build, code, create, refactor, migrate | Code generation | IMPL | -| tester | test, verify, validate, QA, regression, fix, bug | Validation | TEST | -| reviewer | review, audit, inspect, code quality | Read-only analysis | REVIEW | -| analyst | research, analyze, investigate, diagnose | Orchestration | RESEARCH | -| writer | document, write doc, generate report | Code generation | DRAFT | -| debugger | debug, troubleshoot, root cause | Orchestration | DEBUG | -| security | security, vulnerability, OWASP, compliance | Read-only analysis | SEC | - -**Inference**: For each role, check if task description matches any keyword. Add matched roles to the inferred list. - -#### Implicit Role Completion Table - -| Condition | Add Role | Reason | -|-----------|----------|--------| -| Has executor, missing planner | Add planner (before executor) | Code needs planning first | -| Has executor, missing tester | Add tester (after executor) | Code needs validation | -| Has debugger, missing tester | Add tester | Bug fixes need verification | -| Has writer, missing reviewer | Add reviewer | Documents need review | - -**Minimum guarantee**: If fewer than 2 worker roles inferred, fall back to standard set: planner + executor + tester + reviewer. - -**Pipeline type tag** (for Step 5): - -| Condition | Pipeline Type | -|-----------|---------------| -| Has writer role | Document | -| Has debugger role | Debug | -| Default | Standard | - -### Step 3: Role Confirmation (Interactive) - -Present the inferred roles to the user for confirmation. - -``` -AskUserQuestion({ - questions: [ - { question: "Inferred roles: . Adjust?", - header: "Confirm", - options: ["Confirm (Recommended)", "Add role", "Remove role", "Re-describe"] } - ] -}) -``` - -| User Choice | Action | -|-------------|--------| -| Confirm | Proceed with inferred roles | -| Add role | AskUserQuestion for new role name + responsibility type | -| Remove role | AskUserQuestion for which role to remove | -| Re-describe | Return to Step 1, re-enter task description | - -### Step 4: Capability Assignment (Per Role) - -For each worker role, assign capabilities based on responsibility type. - -#### Tool Assignment Table - -| Responsibility Type | Extra Tools (beyond base set) | Adaptive Routing | -|---------------------|-------------------------------|------------------| -| Read-only analysis | Task(*) | No | -| Code generation | Write(*), Edit(*), Task(*) | Yes | -| Orchestration | Write(*), Task(*) | Yes | -| Validation | Write(*), Edit(*), Task(*) | No | - -> **Base tools** (all roles): SendMessage, TaskUpdate, TaskList, TaskGet, TodoWrite, Read, Bash, Glob, Grep - -#### Message Type Assignment Table - -| Responsibility Type | Message Types | -|---------------------|---------------| -| Read-only analysis | `_result` (analysis complete), `error` | -| Code generation | `_complete`, `_progress`, `error` | -| Orchestration | `_ready`, `_progress`, `error` | -| Validation | `_result`, `fix_required`, `error` | - -**Coordinator** gets special tools: TeamCreate, TeamDelete, AskUserQuestion, TaskCreate + all base tools. -**Coordinator** message types: `plan_approved`, `plan_revision`, `task_unblocked`, `shutdown`, `error`. - -#### Toolbox Assignment Table - -| Responsibility Type | Commands | Subagents | CLI Tools | -|---------------------|----------|-----------|-----------| -| Read-only analysis | review, analyze | (none) | gemini (analysis), codex (review) | -| Code generation | implement, validate | code-developer | (none) | -| Orchestration | explore, plan | cli-explore-agent, cli-lite-planning-agent | gemini (analysis) | -| Validation | validate | code-developer | (none) | - -**Coordinator** always gets: commands=[dispatch, monitor], no subagents, no CLI tools. - -### Step 5: Pipeline Definition - -Sort roles into execution stages by weight, then build dependency chain. - -#### Stage Weight Table - -| Role | Weight | Stage Position | -|------|--------|----------------| -| analyst, debugger, security | 1 | Analysis/Exploration | -| planner | 2 | Planning | -| executor, writer | 3 | Implementation | -| tester, reviewer | 4 | Validation/Review | - -**Pipeline construction flow**: - -1. Group worker roles by weight -2. Sort groups by weight ascending (1 → 2 → 3 → 4) -3. Within same weight → parallel (same stage) -4. Each stage `blockedBy` all roles in previous stage -5. Generate diagram: `Requirements → [Stage1] → [Stage2] → ... → Report` - -### Step 6: Generate Configuration - -Assemble all collected data into `team-config.json`. - -#### Config Schema - -| Field | Source | Example | -|-------|--------|---------| -| `team_name` | Step 1 | `"lifecycle"` | -| `team_display_name` | Capitalized team_name | `"Lifecycle"` | -| `skill_name` | `team-` | `"team-lifecycle"` | -| `skill_path` | `.claude/skills/team-/` | | -| `pipeline_type` | Step 2 tag | `"Standard"` | -| `pipeline` | Step 5 output | `{ stages: [...], diagram: "..." }` | -| `roles` | All roles with full metadata | Array | -| `worker_roles` | Roles excluding coordinator | Array | -| `all_roles_tools_union` | Union of all roles' allowed_tools | Comma-separated string | -| `role_list` | All role names | Comma-separated string | - -``` -Write("/team-config.json", ) -``` - -## Output - -| Item | Value | -|------|-------| -| File | `team-config.json` | -| Format | JSON | -| Location | `/team-config.json` | - -## Quality Checklist - -- [ ] Team name is lowercase, valid as folder/skill name -- [ ] Coordinator always included -- [ ] At least 2 worker roles defined -- [ ] Task prefixes are UPPERCASE and unique across roles -- [ ] Pipeline stages reference valid roles -- [ ] All roles have message types defined -- [ ] Allowed tools include minimum set per responsibility type - -## Next Phase - --> [Phase 2: Pattern Analysis](02-pattern-analysis.md) diff --git a/.claude/skills_lib/team-skill-designer-v2/phases/02-pattern-analysis.md b/.claude/skills_lib/team-skill-designer-v2/phases/02-pattern-analysis.md deleted file mode 100644 index ac852049..00000000 --- a/.claude/skills_lib/team-skill-designer-v2/phases/02-pattern-analysis.md +++ /dev/null @@ -1,180 +0,0 @@ -# Phase 2: Pattern Analysis - -Analyze applicable patterns for each role in the team. - -## Objective - -- Per-role: find most similar existing command reference -- Per-role: select infrastructure + collaboration patterns -- Per-role: map 5-phase structure to role responsibilities -- Generate `pattern-analysis.json` - -## Input - -| Source | Description | -|--------|-------------| -| `team-config.json` | Phase 1 output | -| `specs/team-design-patterns.md` | Infrastructure patterns (read in Phase 0) | -| `specs/collaboration-patterns.md` | Collaboration patterns (read in Phase 0) | - -## Execution Steps - -### Step 1: Load Configuration - -``` -Read("/team-config.json") -``` - -### Step 2: Per-Role Similarity Mapping - -For each worker role, find the most similar existing command based on responsibility type. - -#### Similarity Mapping Table - -| Responsibility Type | Primary Reference | Secondary Reference | Reason | -|---------------------|-------------------|---------------------|--------| -| Read-only analysis | review | plan | Both analyze code and report findings with severity classification | -| Code generation | execute | test | Both write/modify code and self-validate | -| Orchestration | plan | coordinate | Both coordinate sub-tasks and produce structured output | -| Validation | test | review | Both validate quality with structured criteria | - -For each worker role: -1. Look up responsibility type in table above -2. Record `similar_to.primary` and `similar_to.secondary` -3. Set `reference_command` = `.claude/commands/team/.md` - -### Step 3: Per-Role Phase Mapping - -Map the generic 5-phase structure to role-specific phase names. - -#### Phase Structure Mapping Table - -| Responsibility Type | Phase 2 | Phase 3 | Phase 4 | -|---------------------|---------|---------|---------| -| Read-only analysis | Context Loading | Analysis Execution | Finding Summary | -| Code generation | Task & Plan Loading | Code Implementation | Self-Validation | -| Orchestration | Context & Complexity Assessment | Orchestrated Execution | Result Aggregation | -| Validation | Environment Detection | Execution & Fix Cycle | Result Analysis | - -> Phase 1 is always "Task Discovery" and Phase 5 is always "Report to Coordinator" for all roles. - -### Step 4: Per-Role Infrastructure Patterns - -#### Core Patterns (mandatory for all roles) - -| Pattern | Name | -|---------|------| -| pattern-1 | Message Bus | -| pattern-2 | YAML Front Matter (adapted: no YAML in skill role files) | -| pattern-3 | Task Lifecycle | -| pattern-4 | Five Phase | -| pattern-6 | Coordinator Spawn | -| pattern-7 | Error Handling | - -#### Conditional Pattern Selection Table - -| Condition | Add Pattern | -|-----------|-------------| -| Role has `adaptive_routing = true` | pattern-5 (Complexity Adaptive) | -| Responsibility type is Code generation or Orchestration | pattern-8 (Session Files) | - -#### Pattern 9 Selection - -| Condition | Uses Pattern 9 | -|-----------|----------------| -| Role has subagents defined (length > 0) | Yes | -| Role has CLI tools defined (length > 0) | Yes | -| Neither | No | - -### Step 5: Command-to-Phase Mapping - -For each worker role, map commands to phases and determine extraction reasons. - -**Per-command extraction reasons**: - -| Condition | Extraction Reason | -|-----------|-------------------| -| Role has subagents | `subagent-delegation` | -| Role has CLI tools | `cli-fan-out` | -| Role has adaptive routing | `complexity-adaptive` | - -Record `phase_commands` mapping (from config): which command runs in which phase. - -### Step 6: Collaboration Pattern Selection - -Select team-level collaboration patterns based on team composition. - -#### Collaboration Pattern Selection Decision Table - -| Condition | Pattern | Name | -|-----------|---------|------| -| Always | CP-1 | Linear Pipeline (base) | -| Any role has Validation or Read-only analysis type | CP-2 | Review-Fix Cycle | -| Any role has Orchestration type | CP-3 | Fan-out/Fan-in | -| Worker roles >= 4 | CP-6 | Incremental Delivery | -| Always | CP-5 | Escalation Chain | -| Always | CP-10 | Post-Mortem | - -#### Convergence Defaults Table - -| Pattern | Max Iterations | Success Gate | -|---------|----------------|--------------| -| CP-1 | 1 | all_stages_completed | -| CP-2 | 5 | verdict_approve_or_conditional | -| CP-3 | 1 | quorum_100_percent | -| CP-5 | null | issue_resolved_at_any_level | -| CP-6 | 3 | all_increments_validated | -| CP-10 | 1 | report_generated | - -### Step 7: Read Reference Commands - -For each unique `similar_to.primary` across all roles: - -``` -Read(".claude/commands/team/.md") -``` - -Store content for Phase 3 reference. Skip silently if file not found. - -### Step 8: Generate Analysis Document - -Assemble all analysis results into `pattern-analysis.json`. - -#### Output Schema - -| Field | Source | -|-------|--------| -| `team_name` | config | -| `role_count` / `worker_count` | config | -| `role_analysis[]` | Steps 2-5 (per-role: similarity, phases, patterns, commands) | -| `collaboration_patterns[]` | Step 6 | -| `convergence_config[]` | Step 6 | -| `referenced_commands[]` | Step 7 | -| `pipeline` | config | -| `skill_patterns` | Fixed: role_router, shared_infrastructure, progressive_loading | -| `command_architecture` | Per-role command mapping + pattern-9 flag | - -``` -Write("/pattern-analysis.json", ) -``` - -## Output - -| Item | Value | -|------|-------| -| File | `pattern-analysis.json` | -| Format | JSON | -| Location | `/pattern-analysis.json` | - -## Quality Checklist - -- [ ] Every worker role has similarity mapping -- [ ] Every worker role has 5-phase structure -- [ ] Infrastructure patterns include all mandatory patterns -- [ ] Collaboration patterns selected at team level -- [ ] Referenced commands are readable -- [ ] Skill-specific patterns documented - -## Next Phase - --> [Phase 3: Skill Package Generation](03-skill-generation.md) diff --git a/.claude/skills_lib/team-skill-designer-v2/phases/03-skill-generation.md b/.claude/skills_lib/team-skill-designer-v2/phases/03-skill-generation.md deleted file mode 100644 index e38322be..00000000 --- a/.claude/skills_lib/team-skill-designer-v2/phases/03-skill-generation.md +++ /dev/null @@ -1,239 +0,0 @@ -# Phase 3: Skill Package Generation - -> **COMPACT PROTECTION**: This is the core generation phase. If context compression has occurred and this file is only a summary, **MUST `Read` this file again before executing any Step**. Do not generate from memory. - -Generate the unified team skill package: SKILL.md (role router) + per-role `role.md` + per-role `commands/*.md`. - -## Objective - -- Generate `SKILL.md` with role router and shared infrastructure -- Generate `roles/coordinator/role.md` + `commands/` -- Generate `roles//role.md` + `commands/` for each worker role -- Generate `specs/team-config.json` -- All files written to `preview/` directory first - -## Input - -| Source | Description | -|--------|-------------| -| `team-config.json` | Phase 1 output (roles, pipeline, capabilities) | -| `pattern-analysis.json` | Phase 2 output (patterns, phase mapping, similarity) | -| `templates/skill-router-template.md` | SKILL.md generation template | -| `templates/role-template.md` | role.md generation template | -| `templates/role-command-template.md` | command file generation template | - -## Execution Steps - -### Step 1: Load Inputs + Create Preview Directory - -1. Read `/team-config.json` and `/pattern-analysis.json` -2. Read all 3 template files from `templates/` -3. Create directory structure: - -``` -Bash("mkdir -p /roles//commands /specs") -``` - -Repeat for every role in config. - -### Step 2: Generate SKILL.md (Role Router) - -Use `templates/skill-router-template.md` as the base. Fill the template using config values. - -#### Template Variable Mapping - -| Template Variable | Config Source | -|-------------------|--------------| -| `` | `config.skill_name` | -| `` | `config.team_name` | -| `` | `config.team_display_name` | -| `` | `config.all_roles_tools_union` | -| `` | Generated from `config.roles[]` (see Roles Table below) | -| `` | Per-role: `"": { file, prefix }` | -| `` | Per worker role: name + message types | -| `` | Per worker role: Task() spawn block | -| `` | `config.pipeline.diagram` | -| `` | Generated from role names | - -#### Roles Table Generation - -For each role in `config.roles[]`, produce one row: - -``` -| | | | [roles//role.md](roles//role.md) | -``` - -#### Spawn Block Generation - -For each worker role, generate a `Task()` spawn block containing: -- `subagent_type: "general-purpose"` -- `team_name: ` -- `name: ""` -- Prompt with: primary directive (MUST call Skill), role constraints, message bus requirement, workflow steps - -**Spawn prompt must include**: -1. Primary directive: `Skill(skill="", args="--role=")` -2. Task prefix constraint: only handle `-*` tasks -3. Output tag: all messages tagged `[]` -4. Communication rule: only talk to coordinator -5. Message bus: call `team_msg` before every `SendMessage` - -``` -Write("/SKILL.md", ) -``` - -### Step 3: Generate Coordinator Role File - -Build coordinator `role.md` with these sections: - -| Section | Content Source | -|---------|---------------| -| Role Identity | Fixed: name=coordinator, prefix=N/A, type=Orchestration | -| Message Types | Fixed 5 types: plan_approved, plan_revision, task_unblocked, shutdown, error | -| Execution Phase 1 | Requirement clarification via AskUserQuestion | -| Execution Phase 2 | TeamCreate + spawn blocks (same as SKILL.md Step 2) | -| Execution Phase 3 | Task chain creation from `config.pipeline.stages` | -| Execution Phase 4 | Message-driven coordination loop | -| Execution Phase 5 | Report + next steps (new requirement or shutdown) | -| Error Handling | Fixed table: unresponsive, rejected plan, stuck tests, critical review | - -#### Task Chain Generation - -For each stage in `config.pipeline.stages[]`: -1. Create task: `TaskCreate({ subject: "-001: work" })` -2. Set owner: `TaskUpdate({ owner: "" })` -3. Set dependencies: `addBlockedBy` = all prefixes from the previous stage - -#### Coordination Handler Table - -For each worker role, generate one row: - -``` -| : | team_msg log -> TaskUpdate completed -> check next | -``` - -``` -Write("/roles/coordinator/role.md", ) -``` - -Generate coordinator command files (dispatch.md, monitor.md) using `templates/role-command-template.md`. - -### Step 4: Generate Worker Role Files - -**For each worker role**, generate `role.md` using `templates/role-template.md`. - -#### Per-Role Template Variable Mapping - -| Template Variable | Source | -|-------------------|--------| -| `` | `role.name` | -| `` | `role.task_prefix` | -| `` | `role.responsibility_type` | -| `` | `role.description` | -| `` | From `role.message_types[]` | -| `` | First non-error, non-progress message type | -| `` | From `pattern-analysis.phase_structure.phase2` | -| `` | From `pattern-analysis.phase_structure.phase3` | -| `` | From `pattern-analysis.phase_structure.phase4` | -| `` | From `role.commands[]` with phase mapping | -| `` | From `role.subagents[]` | -| `` | From `role.cli_tools[]` | - -#### Role File Sections (v3 style) - -Each generated `role.md` must contain: - -1. **Role Identity**: name, prefix, output tag, responsibility, communication rule -2. **Role Boundaries**: MUST / MUST NOT lists -3. **Message Types**: table with type, direction, trigger -4. **Message Bus**: `team_msg` call pattern + CLI fallback -5. **Toolbox**: commands table, subagents table, CLI tools table -6. **Execution (5-Phase)**: - - Phase 1: Task Discovery (TaskList -> filter by prefix -> TaskGet -> TaskUpdate in_progress) - - Phase 2-4: Content varies by responsibility type (see Phase Content Table below) - - Phase 5: Report to Coordinator (team_msg + SendMessage + TaskUpdate completed + check next) -7. **Error Handling**: table with scenario/resolution - -#### Phase Content by Responsibility Type - -| Type | Phase 2 | Phase 3 | Phase 4 | -|------|---------|---------|---------| -| Read-only analysis | Load plan + get changed files + read contents | Domain-specific analysis per file | Classify findings by severity | -| Code generation | Extract plan path + load plan tasks | Implement tasks (adaptive: direct edit or delegate to code-developer) | Self-validation (syntax check + auto-fix) | -| Orchestration | Assess complexity (Low/Medium/High) | Execute (adaptive: direct search or delegate to sub-agent) | Aggregate results | -| Validation | Detect changed files for scope | Iterative test-fix cycle (max 5 iterations) | Analyze results (iterations, pass rate) | - -``` -Write("/roles//role.md", ) -``` - -### Step 5: Generate Command Files - -#### Command Extraction Decision Table - -| Condition | Extract to command file? | -|-----------|--------------------------| -| Role has subagents (delegation needed) | Yes | -| Role has CLI tools (fan-out needed) | Yes | -| Role has adaptive routing (complexity branching) | Yes | -| None of the above | No (all phases execute inline in role.md) | - -For each role that needs command files, generate from `templates/role-command-template.md`. - -#### Pre-built Command Patterns - -| Command | Description | Delegation Mode | Used By Phase | -|---------|-------------|-----------------|---------------| -| explore | Multi-angle codebase exploration | Subagent Fan-out | Phase 2 | -| analyze | Multi-perspective code analysis | CLI Fan-out | Phase 3 | -| implement | Code implementation via delegation | Sequential Delegation | Phase 3 | -| validate | Iterative test-fix cycle | Sequential Delegation | Phase 3 | -| review | 4-dimensional code review | CLI Fan-out | Phase 3 | -| dispatch | Task chain creation (coordinator) | Direct | Phase 3 | -| monitor | Message-driven coordination (coordinator) | Message-Driven | Phase 4 | - -If command name not in pre-built list, generate a skeleton with TODO placeholders. - -``` -Write("/roles//commands/.md", ) -``` - -### Step 6: Copy Team Config - -``` -Write("/specs/team-config.json", ) -``` - -### Step 7: Preview Checkpoint - -**PAUSE**: Present the generated preview structure to the user for confirmation before proceeding to Phase 4. - -Display: -- File tree of `/` -- Role count and names -- Pipeline diagram -- Total file count - -Wait for user confirmation before advancing. - -## Output - -| Item | Value | -|------|-------| -| Directory | `/preview/` | -| Files | SKILL.md + roles/*/role.md + roles/*/commands/*.md + specs/team-config.json | - -## Quality Checklist - -- [ ] SKILL.md has frontmatter, architecture diagram, role router, role dispatch, shared infrastructure -- [ ] Every role has `role.md` with all 7 required sections -- [ ] Coordinator has dispatch.md and monitor.md command files -- [ ] Worker roles with delegation have command files -- [ ] All generated files use v3 style: text + decision tables + flow symbols, no pseudocode -- [ ] Spawn blocks include complete prompt with primary directive + constraints -- [ ] All `` variables resolved (no `${variable}` syntax in output) -- [ ] Pipeline diagram matches actual role stages - -## Next Phase - --> [Phase 4: Integration Verification](04-integration-verification.md) diff --git a/.claude/skills_lib/team-skill-designer-v2/phases/04-integration-verification.md b/.claude/skills_lib/team-skill-designer-v2/phases/04-integration-verification.md deleted file mode 100644 index 8b9a155e..00000000 --- a/.claude/skills_lib/team-skill-designer-v2/phases/04-integration-verification.md +++ /dev/null @@ -1,183 +0,0 @@ -# Phase 4: Integration Verification - -Verify the generated skill package is internally consistent. - -## Objective - -- Verify SKILL.md role router references match actual role files -- Verify task prefixes are unique across all roles -- Verify message types are consistent between config and generated files -- Verify coordinator spawn template uses correct skill invocation -- Verify role file structural compliance -- Verify coordinator commands alignment -- Generate `integration-report.json` - -## Input - -| Source | Description | -|--------|-------------| -| `/preview/` | Phase 3 generated skill package | -| `team-config.json` | Phase 1 configuration | - -## Execution Steps - -### Step 1: Load Generated Files - -1. Read `/team-config.json` -2. Read `/SKILL.md` -3. Read each `/roles//role.md` -4. Read each `/roles//commands/*.md` - -### Step 2: Run 6 Integration Checks - -#### Check 1: Router Consistency - -For each role in config, verify 3 conditions in SKILL.md: - -| Item | Method | Pass Criteria | -|------|--------|---------------| -| Router entry | SKILL.md contains `""` | Found | -| Role file exists | `roles//role.md` is readable | File exists | -| Role link valid | SKILL.md contains `roles//role.md` | Found | - -**Status**: PASS if all 3 conditions met for every role, FAIL otherwise. - -#### Check 2: Prefix Uniqueness - -| Item | Method | Pass Criteria | -|------|--------|---------------| -| All task prefixes | Collect `task_prefix` from each worker role | No duplicates | - -**Status**: PASS if all prefixes unique, FAIL if any duplicate found. - -#### Check 3: Message Type Consistency - -For each worker role: - -| Item | Method | Pass Criteria | -|------|--------|---------------| -| Config message types | List types from `role.message_types[]` | Baseline | -| Types in role file | Search role.md for each type string | All present | - -**Status**: PASS if all configured types found in role file, WARN if any missing. - -#### Check 4: Spawn Template Verification - -For each worker role, verify in SKILL.md: - -| Item | Method | Pass Criteria | -|------|--------|---------------| -| Spawn present | SKILL.md contains `name: ""` | Found | -| Skill call correct | Contains `Skill(skill="", args="--role=")` | Found | -| Prefix in prompt | Contains `-*` | Found | - -**Status**: PASS if all 3 conditions met, FAIL otherwise. - -#### Check 5: Role File Pattern Compliance - -For each role file, check structural elements: - -| Item | Search Pattern | Required | -|------|---------------|----------| -| Role Identity section | `## Role Identity` | Yes | -| 5-Phase structure | `Phase 1` and `Phase 5` both present | Yes | -| Task lifecycle | `TaskList`, `TaskGet`, `TaskUpdate` all present | Yes | -| Message bus | `team_msg` present | Yes | -| SendMessage | `SendMessage` present | Yes | -| Error Handling | `## Error Handling` | Yes | - -**Status**: PASS if all 6 items found, PARTIAL if some missing, MISSING if file not found. - -#### Check 5b: Command File Verification - -For each role's command files: - -| Item | Search Pattern | Required | -|------|---------------|----------| -| Strategy section | `## Strategy` | Yes | -| Execution Steps | `## Execution Steps` | Yes | -| Error Handling | `## Error Handling` | Yes | -| When to Use | `## When to Use` | Yes | -| Self-contained | No `Read("../` cross-command references | Yes | - -**Status**: PASS if all items found, PARTIAL if some missing, MISSING if file not found. - -#### Check 6: Coordinator Commands Alignment - -> **Critical**: dispatch.md and monitor.md are the most common source of integration failures. - -**6a: dispatch.md role names** - -| Item | Method | Pass Criteria | -|------|--------|---------------| -| Owner values | Extract all `owner: ""` from dispatch.md | Every name exists in config roles | -| No ghost roles | Compare dispatch roles vs config roles | No invalid role names | - -**6b: monitor.md spawn completeness** - -| Item | Method | Pass Criteria | -|------|--------|---------------| -| Has `description:` | Search for `description:` | Found | -| Has `team_name:` | Search for `team_name:` | Found | -| Has `name:` param | Search for `name:` | Found | -| Has Skill callback | Search for `Skill(skill=` | Found | -| Has role boundaries | Search for role constraint / MUST keywords | Found | -| Not minimal prompt | No `prompt: \`Execute task` anti-pattern | Confirmed | - -**6c: Pipeline alignment** - -| Item | Method | Pass Criteria | -|------|--------|---------------| -| Pipeline task IDs | From `config.pipeline_tasks` (if defined) | Baseline | -| Dispatch task IDs | Extract `subject: ""` from dispatch.md | Match pipeline | - -**Status**: PASS if no mismatches, WARN if pipeline_tasks not defined, FAIL if mismatches found. - -### Step 3: Generate Report - -Compute overall status: PASS if all checks pass (excluding SKIP), NEEDS_ATTENTION otherwise. - -#### Report Schema - -| Field | Content | -|-------|---------| -| `team_name` | Config team name | -| `skill_name` | Config skill name | -| `checks.router_consistency` | Check 1 results per role | -| `checks.prefix_uniqueness` | Check 2 result | -| `checks.message_types` | Check 3 results per role | -| `checks.spawn_template` | Check 4 results per role | -| `checks.pattern_compliance` | Check 5 results per role | -| `checks.command_files` | Check 5b results per role | -| `checks.coordinator_commands` | Check 6a/6b/6c results | -| `overall` | PASS or NEEDS_ATTENTION | -| `file_count` | skill_md: 1, role_files: N, total: N+2 | - -``` -Write("/integration-report.json", ) -``` - -## Output - -| Item | Value | -|------|-------| -| File | `integration-report.json` | -| Format | JSON | -| Location | `/integration-report.json` | - -## Quality Checklist - -- [ ] Every role in config has a router entry in SKILL.md -- [ ] Every role has a file in `roles/` -- [ ] Task prefixes are unique -- [ ] Spawn template uses correct `Skill(skill="...", args="--role=...")` -- [ ] Spawn template includes `description`, `team_name`, `name` parameters -- [ ] All role files have 5-phase structure -- [ ] All role files have message bus integration -- [ ] dispatch.md `owner` values all exist in config roles (no ghost roles) -- [ ] monitor.md spawn prompt contains full Skill callback (not minimal) -- [ ] Task IDs in dispatch.md match pipeline diagram in SKILL.md - -## Next Phase - --> [Phase 5: Validation](05-validation.md) diff --git a/.claude/skills_lib/team-skill-designer-v2/phases/05-validation.md b/.claude/skills_lib/team-skill-designer-v2/phases/05-validation.md deleted file mode 100644 index 58873673..00000000 --- a/.claude/skills_lib/team-skill-designer-v2/phases/05-validation.md +++ /dev/null @@ -1,209 +0,0 @@ -# Phase 5: Validation - -Verify quality and deliver the final skill package. - -## Objective - -- SKILL.md structural completeness check -- Per-role structural completeness check -- Per-role command file quality check -- Quality scoring across 5 dimensions -- Deliver final skill package to `.claude/skills/team-/` - -## Input - -| Source | Description | -|--------|-------------| -| `/preview/` | Phase 3 generated skill package | -| `integration-report.json` | Phase 4 integration check results | -| `specs/quality-standards.md` | Quality criteria (read in Phase 0) | - -## Execution Steps - -### Step 1: Load Files - -1. Read `/team-config.json` -2. Read `/integration-report.json` -3. Read `/SKILL.md` -4. Read each `/roles//role.md` -5. Read each `/roles//commands/*.md` - -### Step 2: SKILL.md Structural Check - -#### SKILL.md Structure Checklist - -| # | Check Item | Search For | -|---|------------|------------| -| 1 | Frontmatter | `---` block at file start | -| 2 | Architecture Overview | `## Architecture Overview` | -| 3 | Role Router | `## Role Router` | -| 4 | Role Dispatch Code | `VALID_ROLES` | -| 5 | Orchestration Mode | `Orchestration Mode` | -| 6 | Available Roles Table | `| Role | Task Prefix` | -| 7 | Shared Infrastructure | `## Shared Infrastructure` | -| 8 | Role Isolation Rules | `Role Isolation` | -| 9 | Pipeline Diagram | `## Pipeline` | -| 10 | Coordinator Spawn Template | `Coordinator Spawn` | -| 11 | Spawn Skill Directive | `MUST` + primary directive | -| 12 | Spawn Description Param | `description:` in spawn block | -| 13 | Error Handling | `## Error Handling` | - -**SKILL.md score** = (passed items / 13) * 100 - -### Step 3: Per-Role Structural Check - -#### Role Structure Checklist - -| # | Check Item | Search For | -|---|------------|------------| -| 1 | Role Identity | `## Role Identity` | -| 2 | Role Boundaries | `## Role Boundaries` | -| 3 | Output Tag | `Output Tag` | -| 4 | Message Types Table | `## Message Types` | -| 5 | Message Bus | `## Message Bus` | -| 6 | CLI Fallback | `CLI` fallback section | -| 7 | Toolbox Section | `## Toolbox` | -| 8 | 5-Phase Execution | `## Execution` | -| 9 | Phase 1 Task Discovery | `Phase 1` + `Task Discovery` | -| 10 | TaskList Usage | `TaskList` | -| 11 | TaskGet Usage | `TaskGet` | -| 12 | TaskUpdate Usage | `TaskUpdate` | -| 13 | team_msg Before SendMessage | `team_msg` | -| 14 | SendMessage to Coordinator | `SendMessage` | -| 15 | Error Handling | `## Error Handling` | - -**Per-role score** = (passed items / 15) * 100 - -| Score | Status | -|-------|--------| -| >= 80% | PASS | -| < 80% | PARTIAL | -| File missing | MISSING (score = 0) | - -### Step 3b: Command File Quality Check - -For each role's command files: - -#### Command Quality Checklist - -| # | Check Item | Search For | -|---|------------|------------| -| 1 | When to Use section | `## When to Use` | -| 2 | Strategy section | `## Strategy` | -| 3 | Delegation mode declared | `Delegation Mode` | -| 4 | Execution Steps section | `## Execution Steps` | -| 5 | Error Handling section | `## Error Handling` | -| 6 | Output Format section | `## Output Format` | -| 7 | Self-contained (no cross-ref) | No `Read("../` patterns | - -**Per-command score** = (passed items / 7) * 100. Role command score = average of all commands. - -### Step 4: Quality Scoring - -#### Quality Scoring Table - -| Dimension | Weight | Source | Calculation | -|-----------|--------|--------|-------------| -| `skill_md` | Equal | Step 2 | SKILL.md checklist score | -| `roles_avg` | Equal | Step 3 | Average of all role scores | -| `integration` | Equal | Phase 4 report | PASS=100, otherwise=50 | -| `consistency` | Equal | Cross-check | Start at 100, -20 per mismatch (see below) | -| `command_quality` | Equal | Step 3b | Average of all command scores | - -**Consistency deductions**: - -| Mismatch | Deduction | -|----------|-----------| -| Skill name not in SKILL.md | -20 | -| Team name not in SKILL.md | -20 | -| Any role name not in SKILL.md | -10 per role | - -**Overall score** = average of all 5 dimension scores. - -#### Delivery Decision Table - -| Score Range | Gate | Action | -|-------------|------|--------| -| >= 80% | PASS | Deliver to `.claude/skills/team-/` | -| 60-79% | REVIEW | Deliver with warnings, suggest fixes | -| < 60% | FAIL | Do not deliver, return to Phase 3 for rework | - -### Step 5: Generate Validation Report - -#### Report Schema - -| Field | Content | -|-------|---------| -| `team_name` | Config team name | -| `skill_name` | Config skill name | -| `timestamp` | ISO timestamp | -| `scores` | All 5 dimension scores | -| `overall_score` | Average score | -| `quality_gate` | PASS / REVIEW / FAIL | -| `skill_md_checks` | Step 2 results | -| `role_results` | Step 3 results per role | -| `integration_status` | Phase 4 overall status | -| `delivery.source` | Preview directory | -| `delivery.destination` | `.claude/skills//` | -| `delivery.ready` | true if gate is not FAIL | - -``` -Write("/validation-report.json", ) -``` - -### Step 6: Deliver Final Package - -**Only execute if `quality_gate` is not FAIL.** - -1. Create destination directory structure: - -``` -Bash("mkdir -p .claude/skills//roles//commands .claude/skills//specs") -``` - -2. Copy files from preview to destination: - -| Source | Destination | -|--------|-------------| -| `/SKILL.md` | `.claude/skills//SKILL.md` | -| `/roles//role.md` | `.claude/skills//roles//role.md` | -| `/roles//commands/*.md` | `.claude/skills//roles//commands/*.md` | -| `/specs/team-config.json` | `.claude/skills//specs/team-config.json` | - -3. Report delivery summary: - - Destination path - - Skill name - - Quality score and gate - - Role list - - Usage examples: `Skill(skill="", args="--role=")` - -4. List delivered files: - -``` -Bash("find .claude/skills/ -type f | sort") -``` - -**If gate is FAIL**: Report failure with score, suggest returning to Phase 3 for rework. - -## Output - -| Item | Value | -|------|-------| -| File | `validation-report.json` | -| Format | JSON | -| Location | `/validation-report.json` | -| Delivery | `.claude/skills/team-/` (if gate passes) | - -## Quality Checklist - -- [ ] SKILL.md passes all 13 routing-level structural checks -- [ ] All role files pass structural checks (>= 80%) -- [ ] All command files pass quality checks (>= 80%) -- [ ] Integration report is PASS -- [ ] Overall score >= 80% -- [ ] Final package delivered to `.claude/skills/team-/` -- [ ] Usage instructions provided to user - -## Completion - -This is the final phase. The unified team skill is ready for use. diff --git a/.claude/skills_lib/team-skill-designer-v2/specs/collaboration-patterns.md b/.claude/skills_lib/team-skill-designer-v2/specs/collaboration-patterns.md deleted file mode 100644 index 700165b0..00000000 --- a/.claude/skills_lib/team-skill-designer-v2/specs/collaboration-patterns.md +++ /dev/null @@ -1,1555 +0,0 @@ -# Collaboration Patterns Specification - -> 11 种团队协作模式，每种具备：收敛性、完整流程、反馈控制 - ---- - -## Pattern Standard Structure - -每种协作模式遵循统一规范： - -``` -┌─────────────────────────────────────────┐ -│ Entry Condition (何时启用) │ -├─────────────────────────────────────────┤ -│ Roles Required (需要哪些角色) │ -├─────────────────────────────────────────┤ -│ Workflow (完整执行流程) │ -├─────────────────────────────────────────┤ -│ Convergence (收敛条件) │ -│ ├─ Success Gate (成功判定) │ -│ ├─ Max Iterations (最大迭代) │ -│ └─ Timeout (超时处理) │ -├─────────────────────────────────────────┤ -│ Feedback Loop (反馈控制) │ -│ ├─ Signal (反馈信号) │ -│ ├─ Handler (处理逻辑) │ -│ └─ Correction (纠正动作) │ -├─────────────────────────────────────────┤ -│ Fallback (降级策略) │ -└─────────────────────────────────────────┘ -``` - ---- - -## CP-1: Linear Pipeline (线性流水线) - -### Description - -最基础的协作模式。任务沿固定顺序在角色间传递，每个阶段有明确的入口和出口条件。上一阶段的输出是下一阶段的输入。 - -### Entry Condition - -- 任务具有清晰的阶段划分（规划 → 实现 → 验证） -- 各阶段之间有天然的依赖关系 -- 适用于大多数标准特性开发 - -### Roles Required - -`coordinator` → `planner` → `executor` → `tester` - -### Workflow - -``` - ┌──────────┐ ┌──────────┐ ┌───────────┐ ┌──────────┐ -需求 ──→ │ PLAN │──→ │ IMPL │──→ │ TEST │──→ │ REPORT │ - │ planner │ │ executor │ │ + REVIEW │ │ coord. │ - └────┬─────┘ └────┬─────┘ └─────┬─────┘ └──────────┘ - │ │ │ - ▼ ▼ ▼ - plan.json code changes test results - review findings -``` - -```javascript -// Coordinator creates task chain -TaskCreate({ subject: "PLAN-001", owner: "planner" }) -TaskCreate({ subject: "IMPL-001", owner: "executor", addBlockedBy: [planId] }) -TaskCreate({ subject: "TEST-001", owner: "tester", addBlockedBy: [implId] }) -TaskCreate({ subject: "REVIEW-001", owner: "tester", addBlockedBy: [implId] }) -``` - -### Convergence - -| Element | Value | -|---------|-------| -| **Success Gate** | 所有阶段任务状态 = `completed` | -| **Max Iterations** | 每阶段 1 次（若失败触发 Review-Fix Cycle） | -| **Timeout** | 无显式超时，每阶段内部有各自收敛机制 | - -### Feedback Loop - -``` -┌─ Stage Transition Feedback ─────────────────────────┐ -│ │ -│ Plan rejected? → planner revises → resubmit │ -│ Impl has errors? → executor self-validates → fix │ -│ Tests fail? → tester fix cycle → retry │ -│ Review blocks? → create IMPL-fix → executor fixes │ -│ │ -└──────────────────────────────────────────────────────┘ -``` - -**Signal**: 下一阶段的 reject/fail message -**Handler**: Coordinator 路由消息回上一阶段 -**Correction**: 上一阶段 agent 修订并重新提交 - -### Fallback - -- Plan 拒绝 3+ 次 → Coordinator 自行规划 -- Test 达不到 95% 超过 5 次迭代 → 上报用户 -- Review 发现 critical → 创建 IMPL-fix 任务 - -### Implementation Reference - -当前 `coordinate.md` 即采用此模式。 - ---- - -## CP-2: Review-Fix Cycle (审查修复循环) - -### Description - -两个角色之间的迭代改进循环。一个角色产出工作成果，另一个角色审查，发现问题后退回修复，直到达到质量门控。这是软件开发中 code review 的自然映射。 - -### Entry Condition - -- 工作产出需要质量验证（代码实现、计划、文档） -- 存在明确的质量标准（pass rate、severity threshold、acceptance criteria） -- 需要多轮迭代才能达到质量要求 - -### Roles Required - -`producer` (executor/planner) ↔ `reviewer` (tester/reviewer) - -### Workflow - -``` - ┌─────────┐ ┌──────────┐ - │Producer │ │Reviewer │ - │ │──(1)产出───→│ │ - │ │ │ │ - │ │←─(2)反馈────│ │ - │ │ │ │ - │ │──(3)修订───→│ │ - │ │ │ │ - │ ... │ ...循环 │ ... │ - │ │ │ │ - └─────────┘ └──────────┘ - │ │ - ▼ ▼ - final artifact APPROVE verdict -``` - -```javascript -// Coordinator orchestrates review-fix cycle -function reviewFixCycle(producerRole, reviewerRole, maxIterations) { - let iteration = 0 - let verdict = 'PENDING' - - while (iteration < maxIterations && verdict !== 'APPROVE') { - iteration++ - - // Step 1: Producer delivers (or revises) - if (iteration === 1) { - // Wait for initial delivery - // msg type: impl_complete / plan_ready - } else { - // Wait for revision - // msg type: impl_complete (revision) - } - - // Step 2: Reviewer examines - // Creates REVIEW task, waits for review_result - - // Step 3: Check verdict - verdict = reviewResult.data.verdict // APPROVE | CONDITIONAL | BLOCK - - if (verdict === 'BLOCK') { - // Step 4: Create fix task for producer - TaskCreate({ - subject: `IMPL-fix-${iteration}`, - description: `Fix issues: ${reviewResult.data.findings}`, - owner: producerRole - }) - // Send feedback to producer - team_msg({ type: "fix_required", data: { iteration, findings: reviewResult.data.findings } }) - } - } - - return { verdict, iterations: iteration } -} -``` - -### Convergence - -| Element | Value | -|---------|-------| -| **Success Gate** | Reviewer verdict = `APPROVE` 或 `CONDITIONAL`（无 critical findings） | -| **Max Iterations** | 5 轮（可配置）。Producer 修复 → Reviewer 再审 = 1 轮 | -| **Timeout** | 单轮超时 = 阶段超时（由各角色内部控制） | - -### Feedback Loop - -``` -Signal: review_result { verdict: "BLOCK", findings: [...] } - ↓ -Handler: Coordinator 解析 findings，按 severity 分类 - ↓ -Correction: 创建 IMPL-fix 任务，附带 findings 明细 - Producer 收到任务 → 读取 findings → 修复 → 重新提交 - ↓ -Loop: Reviewer 再次审查修订后的产出 -``` - -**反馈信号结构**: -```javascript -{ - verdict: "APPROVE" | "CONDITIONAL" | "BLOCK", - findings: { - critical: [{ file, line, description, suggestion }], - high: [...], - medium: [...], - low: [...] - }, - iteration: 2, - delta: "+3 fixed, -1 new issue" // 对比上一轮的变化 -} -``` - -### Fallback - -| Condition | Action | -|-----------|--------| -| 达到 max iterations 仍 BLOCK | 上报用户，附带全部 findings 历史 | -| Reviewer 发现 Producer 无法修复的设计问题 | 升级到 CP-5 Escalation，或回退到 CP-1 重新规划 | -| 连续 2 轮 findings 不减少（无改善） | 中断循环，上报用户请求介入 | - ---- - -## CP-3: Parallel Fan-out/Fan-in (并行扇出扇入) - -### Description - -Coordinator 将同一任务或同一类任务广播给多个 agent 并行执行，收集所有结果后聚合。适用于需要多角度分析、分片处理、或冗余验证的场景。 - -### Entry Condition - -- 任务可分解为独立的并行子任务 -- 需要多角度/多维度分析（如安全 + 性能 + 架构审查） -- 大型任务需要分片并行处理 - -### Roles Required - -`coordinator` → `worker-1, worker-2, ... worker-N` → `coordinator` (aggregation) - -### Workflow - -``` - ┌─ worker-1 ─┐ - │ 角度 A │───┐ - broadcast ├─ worker-2 ─┤ │ aggregate -coord ──────────────┤ 角度 B │───┼──── coord - ├─ worker-3 ─┤ │ - │ 角度 C │───┘ - └────────────┘ -``` - -```javascript -// Phase 1: Fan-out - broadcast tasks -const workerTasks = angles.map((angle, i) => { - const taskId = TaskCreate({ - subject: `ANALYZE-${i+1}: ${angle} analysis`, - description: `Analyze from ${angle} perspective: ${requirement}`, - owner: `worker-${i+1}`, - activeForm: `Analyzing ${angle}` - }) - return taskId -}) - -// Phase 2: Wait for all workers (Stop-Wait with parallel Task calls) -// 同步阻塞 Task() 调用即等待机制。若 worker 在 Phase 1 已用 Task(run_in_background: false) -// 同步 spawn，则 Phase 1 返回时所有 worker 已完成，无需额外等待。 -// 若使用 run_in_background: true 并行 spawn，则逐个 TaskOutput(block: true) 等待完成。 -function waitForCompletion(taskIds) { - let completedCount = 0 - for (const id of taskIds) { - const task = TaskGet({ taskId: id }) - if (task.status === 'completed') completedCount++ - } - return { completed: completedCount, total: taskIds.length, timedOut: false } -} - -// Phase 3: Fan-in - aggregate results -function aggregateResults(taskIds) { - const results = taskIds.map(id => { - const task = TaskGet({ taskId: id }) - return { angle: task.subject, result: task.metadata?.result } - }) - - // Conflict detection - const conflicts = detectConflicts(results) - - return { - results, - conflicts, - consensus: conflicts.length === 0, - summary: synthesize(results) - } -} -``` - -### Convergence - -| Element | Value | -|---------|-------| -| **Success Gate** | 所有 worker 完成（或达到 quorum 比例，默认 100%） | -| **Max Iterations** | 1 轮扇出（若聚合后有冲突，可触发 CP-4 Consensus） | -| **Timeout** | 可配置，默认 5 分钟。超时后用已完成的结果聚合 | - -### Feedback Loop - -``` -Signal: 每个 worker 的 {角度}_result message - ↓ -Handler: Coordinator 收集所有结果 - ↓ -Aggregate: 合并结果 + 冲突检测 - ├─ 无冲突 → 直接合成最终结果 - └─ 有冲突 → 升级到 CP-4 Consensus Gate -``` - -**聚合策略**: -- **Union（并集）**: 合并所有发现（适用于安全审查 - 不遗漏任何 finding） -- **Intersection（交集）**: 只保留多个 worker 共同发现的问题（适用于降噪） -- **Weighted（加权）**: 按 worker 的专业权重合并（适用于多专家评审） - -### Fallback - -| Condition | Action | -|-----------|--------| -| Worker 超时未完成 | 用已完成的 worker 结果聚合，标注缺失角度 | -| Worker 返回错误 | 跳过该 worker，用 N-1 结果聚合 | -| 聚合结果有冲突 | 触发 CP-4 Consensus Gate 解决分歧 | - ---- - -## CP-4: Consensus Gate (共识门控) - -### Description - -在做出重要决策前，要求多个 agent 投票表达意见，只有达到 quorum 才能通过。模拟软件开发中的 Design Review、Architecture Decision Record (ADR) 的决策流程。 - -### Entry Condition - -- 架构决策（选择技术方案 A vs B vs C） -- 安全决策（是否可接受某个风险） -- 影响面大的重构（需要多方确认） -- CP-3 扇出结果有冲突需要裁决 - -### Roles Required - -`proposer` → `voter-1, voter-2, ... voter-N` → `coordinator` (tally) - -### Workflow - -``` - ┌─ voter-1 ─────────────┐ - │ APPROVE + rationale │ - proposal ├─ voter-2 ─────────────┤ tally -proposer ─────────→ │ REJECT + rationale │ ────→ coordinator - ├─ voter-3 ─────────────┤ │ - │ APPROVE + conditions │ ▼ - └───────────────────────┘ decision -``` - -```javascript -// Phase 1: Proposal -const proposal = { - id: `PROPOSAL-${Date.now()}`, - title: "Adopt Strategy Pattern for payment gateway", - options: [ - { id: "A", description: "Strategy Pattern with factory", pros: [...], cons: [...] }, - { id: "B", description: "Plugin architecture", pros: [...], cons: [...] } - ], - context: "Payment module needs multi-gateway support", - deadline: Date.now() + 300000 // 5 min -} - -// Phase 2: Broadcast proposal to voters -voters.forEach(voter => { - SendMessage({ - recipient: voter, - content: `## Proposal: ${proposal.title}\n${JSON.stringify(proposal)}`, - summary: "Vote requested" - }) -}) - -// Phase 3: Collect votes -function collectVotes(proposalId, voterCount, quorum, deadline) { - const votes = [] - while (votes.length < voterCount && Date.now() < deadline) { - // Listen for vote messages - const msgs = team_msg({ operation: "list", type: "vote" }) - const newVotes = msgs.filter(m => - m.data.proposalId === proposalId && !votes.find(v => v.from === m.from) - ) - votes.push(...newVotes) - - // Check quorum - if (votes.length >= quorum) break - } - return votes -} - -// Phase 4: Tally and decide -function tallyVotes(votes, quorumRatio = 0.67) { - const approvals = votes.filter(v => v.data.vote === 'APPROVE') - const rejections = votes.filter(v => v.data.vote === 'REJECT') - const conditions = votes.flatMap(v => v.data.conditions || []) - - const approvalRatio = approvals.length / votes.length - const passed = approvalRatio >= quorumRatio - - return { - passed, - approvalRatio, - approvals: approvals.length, - rejections: rejections.length, - conditions: [...new Set(conditions)], - rationales: votes.map(v => ({ from: v.from, vote: v.data.vote, rationale: v.data.rationale })) - } -} -``` - -### Convergence - -| Element | Value | -|---------|-------| -| **Success Gate** | 赞成率 ≥ quorum（默认 2/3）且无 BLOCK 级别反对 | -| **Max Iterations** | 2 轮。第 1 轮未达 quorum → 修订提案 → 第 2 轮重投 | -| **Timeout** | 5 分钟。超时后以已收到的票数计算（≥ quorum 则通过） | - -### Feedback Loop - -``` -Signal: vote { vote: "REJECT", rationale: "...", conditions: [...] } - ↓ -Handler: Coordinator 聚合所有反对意见和附加条件 - ↓ -Correction: ├─ 未达 quorum → Proposer 修订提案，融合反对意见 → 重投 - ├─ 达到 quorum 但有 conditions → 记录 conditions 作为实施约束 - └─ 明确通过 → 执行决策 -``` - -**投票格式**: -```javascript -team_msg({ - type: "vote", - data: { - proposalId: "PROPOSAL-xxx", - vote: "APPROVE" | "REJECT" | "ABSTAIN", - rationale: "选择方案A因为...", // 必须提供理由 - conditions: ["需要增加向后兼容层"], // 可选附加条件 - confidence: 0.85 // 置信度 0-1 - } -}) -``` - -### Fallback - -| Condition | Action | -|-----------|--------| -| 2 轮都未达 quorum | 上报用户裁决 | -| 投票截止但票数不足（< N/2） | 延长截止时间 1 轮 | -| 全员 ABSTAIN | 由 Coordinator 做默认决策并记录 | - ---- - -## CP-5: Escalation Chain (逐级升级) - -### Description - -当 agent 遇到无法自行解决的问题时，逐级升级到更高层级的处理能力。模拟软件开发中的 on-call escalation / tiered support。 - -### Entry Condition - -- Agent 自修复失败（尝试 N 次后仍无法解决） -- 问题超出当前角色能力范围 -- 需要更高权限或更广视角的决策 - -### Roles Required - -`agent` → `specialist` → `coordinator` → `user` - -### Workflow - -``` -Level 0 Level 1 Level 2 Level 3 -┌──────────┐ ┌──────────┐ ┌──────────┐ ┌──────────┐ -│ Agent │────→│Specialist│────→│Coordinator│───→│ User │ -│ 自修复 │ │ 专家诊断 │ │ 全局视角 │ │ 人工裁决 │ -└──────────┘ └──────────┘ └──────────┘ └──────────┘ - │ │ │ │ - ▼ ▼ ▼ ▼ - retry 2x CLI analysis cross-team fix manual fix -``` - -```javascript -// Escalation state machine -const ESCALATION_LEVELS = [ - { - level: 0, - name: "Self-repair", - handler: "agent", - maxAttempts: 2, - actions: ["Retry with different approach", "Read more context", "Simplify approach"] - }, - { - level: 1, - name: "Specialist diagnosis", - handler: "specialist", - maxAttempts: 1, - actions: ["CLI analysis (gemini/qwen)", "Cross-file dependency trace", "Pattern matching"] - }, - { - level: 2, - name: "Coordinator intervention", - handler: "coordinator", - maxAttempts: 1, - actions: ["Reassign to different agent", "Modify task scope", "Create support task"] - }, - { - level: 3, - name: "User escalation", - handler: "user", - maxAttempts: 1, - actions: ["Present diagnosis chain", "Request manual guidance", "Offer options"] - } -] - -function escalate(issue, currentLevel) { - const nextLevel = ESCALATION_LEVELS[currentLevel + 1] - if (!nextLevel) { - // Already at highest level, wait for user - return { action: "wait", level: currentLevel } - } - - team_msg({ - type: "escalate", - data: { - issue: issue.description, - from_level: currentLevel, - to_level: nextLevel.level, - attempts_at_current: issue.attempts, - diagnosis_chain: issue.diagnosisHistory // 所有层级的诊断记录 - } - }) - - return { action: "escalate", nextHandler: nextLevel.handler, level: nextLevel.level } -} -``` - -### Convergence - -| Element | Value | -|---------|-------| -| **Success Gate** | 问题在某个层级被解决（agent 报告 issue resolved） | -| **Max Iterations** | 每个层级有独立的 maxAttempts（L0: 2, L1: 1, L2: 1, L3: 1） | -| **Timeout** | L0-L2 无显式超时；L3 用户层需等待用户响应 | - -### Feedback Loop - -``` -Signal: escalate { issue, from_level, diagnosis_chain } - ↓ -Handler: 上级接收问题 + 下级的全部诊断历史 - ↓ -Diagnosis: 上级基于更广视角/更强能力做出诊断 - ↓ -Response: ├─ 解决方案 → 传回原 agent 执行 - ├─ 重新定义问题 → 修改任务描述，agent 重试 - └─ 无法解决 → 继续升级到下一层 -``` - -**诊断链结构** (每层追加): -```javascript -{ - diagnosisHistory: [ - { level: 0, agent: "executor", attempts: 2, diagnosis: "TypeScript类型不匹配", tried: ["修改类型定义", "添加类型断言"] }, - { level: 1, agent: "specialist", attempts: 1, diagnosis: "循环依赖导致类型无法推断", recommendation: "重构模块边界" }, - // ... 每层追加自己的诊断 - ] -} -``` - -### Fallback - -| Condition | Action | -|-----------|--------| -| L3 用户无响应 | Agent 尝试最保守的方案继续，标记为 WORKAROUND | -| 诊断链显示根本问题（如架构缺陷） | 回退到 CP-1 重新规划 | -| 升级到 L1 后解决 | 将解决方案记录为 pattern，下次 L0 可直接处理 | - ---- - -## CP-6: Incremental Delivery (增量交付) - -### Description - -将大型任务分解为小的增量，每个增量独立交付并验证后再进行下一个。模拟 CI/CD 中的小批量交付和渐进式部署。 - -### Entry Condition - -- 大型特性（影响 > 10 个文件） -- 高风险变更（需要逐步验证） -- 用户要求渐进可见的进度 - -### Roles Required - -`coordinator` → `executor` (increment) → `validator` (per-increment) → `coordinator` (gate) - -### Workflow - -``` - ┌─────────────────────────────────────────────────┐ - │ Increment 1 Increment 2 Increment N │ - │ ┌──────────┐ ┌──────────┐ ┌──────────┐ │ - │ │ Implement│ │ Implement│ │ Implement│ │ - │ └────┬─────┘ └────┬─────┘ └────┬─────┘ │ - │ ▼ ▼ ▼ │ - │ ┌──────────┐ ┌──────────┐ ┌──────────┐ │ - │ │ Validate │ │ Validate │ │ Validate │ │ - │ └────┬─────┘ └────┬─────┘ └────┬─────┘ │ - │ ▼ ▼ ▼ │ - │ ┌──────────┐ ┌──────────┐ ┌──────────┐ │ - │ │ Gate ✓ │ │ Gate ✓ │ │ Gate ✓ │ │ - │ └──────────┘ └──────────┘ └──────────┘ │ - └─────────────────────────────────────────────────┘ - │ - ▼ - Full validation -``` - -```javascript -// Coordinator splits plan into increments -function createIncrements(plan) { - // Group tasks by dependency layers - const layers = topologicalSort(plan.tasks) - - return layers.map((layer, i) => ({ - id: `INCREMENT-${i+1}`, - tasks: layer, - gate: { - syntax_clean: true, - no_regression: true, // 已有测试不破坏 - increment_tests_pass: true // 增量相关测试通过 - } - })) -} - -// Execute increment cycle -for (const increment of increments) { - // Step 1: Executor implements increment - TaskCreate({ - subject: `IMPL-inc-${increment.id}`, - description: `Implement increment: ${increment.tasks.map(t => t.title).join(', ')}`, - owner: "executor" - }) - - // Step 2: Wait for implementation - // msg: increment_ready - - // Step 3: Validator checks increment gate - const gateResult = validateIncrement(increment) - - // Step 4: Gate decision - if (gateResult.passed) { - team_msg({ type: "increment_ready", data: { increment: increment.id, status: "PASS" } }) - // Continue to next increment - } else { - // Feedback: which gate criteria failed - team_msg({ type: "fix_required", data: { - increment: increment.id, - failed_gates: gateResult.failures, - suggestion: gateResult.fix_suggestion - }}) - // Executor fixes → re-validate (max 3 retries per increment) - } -} - -// Final: full validation after all increments -TaskCreate({ subject: "TEST-final", description: "Full test suite after all increments" }) -``` - -### Convergence - -| Element | Value | -|---------|-------| -| **Success Gate** | 所有增量通过各自的 gate + 最终全量验证通过 | -| **Max Iterations** | 每个增量最多 3 次重试，总增量数由 plan 决定 | -| **Timeout** | 单个增量超时 = 增量任务数 × 单任务超时 | - -### Feedback Loop - -``` -Signal: increment gate failure { failed_gates, affected_files } - ↓ -Handler: Coordinator 定位失败的 gate 条件 - ↓ -Correction: ├─ syntax_clean 失败 → Executor 修复语法 - ├─ no_regression 失败 → Executor 修复回归 + 回滚该增量 - └─ increment_tests 失败 → 触发 CP-2 Review-Fix Cycle -``` - -**增量进度追踪**: -```javascript -{ - total_increments: 4, - completed: 2, - current: 3, - progress_percent: 50, - gate_history: [ - { id: "INCREMENT-1", attempts: 1, status: "PASS" }, - { id: "INCREMENT-2", attempts: 2, status: "PASS" }, - { id: "INCREMENT-3", attempts: 1, status: "IN_PROGRESS" } - ] -} -``` - -### Fallback - -| Condition | Action | -|-----------|--------| -| 增量重试 3 次仍失败 | 回滚该增量代码，标记为 blocked，继续下一增量 | -| 超过半数增量被 blocked | 停止交付，上报用户评估是否重新规划 | -| 最终全量验证失败 | 识别失败增量组合，逐个回退定位 | - ---- - -## CP-7: Swarming (群策攻关) - -### Description - -当流水线被一个问题阻塞时，暂停正常工作流，所有可用 agent 集中力量解决该问题。模拟敏捷开发中的 swarming / mob debugging。 - -### Entry Condition - -- 关键任务被阻塞超过阈值时间 -- Agent 自修复和 L1 升级都失败 -- 问题影响多个下游任务 - -### Roles Required - -`coordinator` (发起) → `all available agents` (协同) → `coordinator` (裁决) - -### Workflow - -``` - ┌───────────────────────────────────┐ - │ SWARM MODE ACTIVE │ - │ │ - │ ┌────────┐ ┌────────┐ │ - │ │Agent A │ │Agent B │ │ - │ │诊断视角1│ │诊断视角2│ │ - │ └───┬────┘ └───┬────┘ │ - │ │ │ │ - │ ▼ ▼ │ - │ ┌─────────────────────┐ │ - │ │ Coordinator 汇总 │ │ - │ │ 选择最佳诊断 │ │ - │ └─────────┬───────────┘ │ - │ ▼ │ - │ ┌─────────────────────┐ │ - │ │ 指定 Agent 执行修复 │ │ - │ └─────────────────────┘ │ - │ │ - └───────────────────────────────────┘ - │ - ▼ - Resume normal pipeline -``` - -```javascript -// Coordinator initiates swarm -function initiateSwarm(blockingIssue) { - // Step 1: Pause all non-critical tasks - const activeTasks = TaskList().filter(t => t.status === 'in_progress') - activeTasks.forEach(t => { - TaskUpdate({ taskId: t.id, metadata: { paused_for_swarm: true } }) - }) - - // Step 2: Broadcast swarm request - team_msg({ - type: "swarm_join", - data: { - issue: blockingIssue.description, - affected_tasks: blockingIssue.blockedTasks, - diagnosis_so_far: blockingIssue.diagnosisHistory, - assignment: "All agents: diagnose from your expertise angle" - } - }) - - // Step 3: Each agent analyzes from their perspective - // planner: 架构视角诊断 - // executor: 实现细节诊断 - // tester: 测试/环境视角诊断 - - // Step 4: Collect diagnoses (fan-in) - // Uses CP-3 fan-in aggregation - - // Step 5: Coordinator selects best diagnosis + assigns fix - const bestDiagnosis = selectBestDiagnosis(diagnoses) - const fixer = selectBestFixer(bestDiagnosis, availableAgents) - - TaskCreate({ - subject: `SWARM-FIX: ${blockingIssue.summary}`, - description: `Fix based on swarm diagnosis:\n${bestDiagnosis.detail}`, - owner: fixer - }) - - // Step 6: Verify fix, resume pipeline - // ... wait for fix completion ... - - // Step 7: Resume paused tasks - activeTasks.forEach(t => { - TaskUpdate({ taskId: t.id, metadata: { paused_for_swarm: null } }) - }) -} -``` - -### Convergence - -| Element | Value | -|---------|-------| -| **Success Gate** | 阻塞问题解决（相关测试通过 / 错误消失） | -| **Max Iterations** | 2 轮诊断。第 1 轮全员诊断 → 修复 → 若失败 → 第 2 轮聚焦诊断 | -| **Timeout** | 10 分钟。超时后以最佳可用诊断尝试修复 | - -### Feedback Loop - -``` -Signal: 每个 agent 的 swarm_diagnosis { perspective, root_cause, confidence, fix_suggestion } - ↓ -Handler: Coordinator 按 confidence 排序，合并互补的诊断 - ↓ -Selection: 选择 confidence 最高且 fix_suggestion 最具体的方案 - ↓ -Execution: 指定最合适的 agent 执行修复 - ↓ -Verify: 修复后重新运行触发阻塞的场景 - ├─ 通过 → 恢复流水线 - └─ 失败 → 第 2 轮，排除已尝试方案 -``` - -### Fallback - -| Condition | Action | -|-----------|--------| -| 2 轮 swarm 未解决 | 升级到用户（CP-5 L3） | -| 修复引入新问题 | 回滚修复，尝试次优方案 | -| Agent 在 swarm 期间无响应 | 跳过该 agent，用其余 agent 的诊断 | - ---- - -## CP-8: Consulting/Advisory (咨询顾问) - -### Description - -工作中的 agent 暂停当前任务，向拥有特定领域知识的 specialist 请求建议，获得建议后继续工作。不同于升级（CP-5），consulting 不转移问题所有权。 - -### Entry Condition - -- Agent 遇到不熟悉的领域（如安全、性能优化、特定框架用法） -- 需要验证方案的正确性但不需要他人实现 -- 需要领域最佳实践参考 - -### Roles Required - -`requester` (任何工作中的 agent) → `consultant` (specialist agent) → `requester` (继续工作) - -### Workflow - -``` - requester consultant - ┌──────────┐ ┌──────────┐ - │ Working │ │ Idle │ - │ │──(1)请求────→│ │ - │ Paused │ │ 分析中 │ - │ │←─(2)建议────│ │ - │ Resume │ │ Idle │ - │ (应用建议)│ │ │ - └──────────┘ └──────────┘ -``` - -```javascript -// Requester sends consultation request -function requestConsultation(topic, context, urgency = 'normal') { - team_msg({ - type: "consult_request", - from: currentRole, - to: "coordinator", // coordinator routes to appropriate specialist - data: { - topic: topic, // "security", "performance", "database" - question: context.question, // 具体问题 - context: context.codeSnippet, // 相关代码片段 - options: context.options, // 可选方案（如果有） - urgency: urgency // "blocking" | "normal" | "low" - } - }) - // Pause current work, wait for response -} - -// Coordinator routes to specialist -function routeConsultation(request) { - const specialist = selectSpecialist(request.data.topic) - // If no specialist agent exists, use CLI tool as specialist - if (!specialist) { - // Fallback: invoke CLI analysis - Bash(`ccw cli -p "PURPOSE: Expert consultation on ${request.data.topic} -TASK: ${request.data.question} -CONTEXT: ${request.data.context} -EXPECTED: Actionable recommendation with confidence level -" --tool gemini --mode analysis`, { run_in_background: true }) - } -} - -// Consultant provides advice -function provideAdvice(request) { - team_msg({ - type: "consult_response", - from: "consultant", - to: request.from, - data: { - recommendation: "使用 bcrypt 而非 SHA-256 进行密码哈希", - rationale: "bcrypt 内置 salt 和自适应计算成本...", - confidence: 0.95, - references: ["OWASP Password Storage Cheat Sheet"], - caveats: ["需要增加 ~100ms 延迟"], - alternative: "如果延迟敏感，可考虑 Argon2id" - } - }) -} - -// Requester applies advice -function applyAdvice(advice) { - if (advice.data.confidence >= 0.8) { - // Apply recommendation directly - return { action: "apply", recommendation: advice.data.recommendation } - } else { - // Low confidence: request second opinion or escalate - return { action: "second_opinion" } - } -} -``` - -### Convergence - -| Element | Value | -|---------|-------| -| **Success Gate** | 咨询回复 confidence ≥ 0.8 且 requester 成功应用建议 | -| **Max Iterations** | 1 次主咨询 + 1 次追问（如果首次回复不够清晰） | -| **Timeout** | blocking: 2 分钟, normal: 5 分钟, low: 无超时 | - -### Feedback Loop - -``` -Signal: consult_response { recommendation, confidence, caveats } - ↓ -Handler: Requester 评估建议的适用性 - ├─ confidence ≥ 0.8 → 直接应用 - ├─ confidence < 0.8 → 追问一轮或请求 second opinion - └─ 与当前方案冲突 → 上报 coordinator 裁决 - ↓ -Correction: Requester 基于建议调整实现方案，继续原任务 -``` - -### Fallback - -| Condition | Action | -|-----------|--------| -| 无可用 specialist | 使用 CLI tool (gemini/qwen) 替代 | -| 咨询超时 | Requester 用自己的最佳判断继续，标注 unverified | -| 建议与当前设计冲突 | 上报 coordinator，触发 CP-4 Consensus | - ---- - -## CP-9: Dual-Track (双轨并行) - -### Description - -两条工作轨道并行推进，在预定义的同步点（checkpoint）对齐。典型应用：设计与实现并行、前端与后端并行、功能开发与测试开发并行。 - -### Entry Condition - -- 任务可分解为两条相对独立的工作流 -- 两条轨道有明确的同步点（interface contract、API spec、schema） -- 并行执行能提升整体效率 - -### Roles Required - -`coordinator` → `track-A` agent + `track-B` agent → `coordinator` (sync) - -### Workflow - -``` - Track A (Design/API) Track B (Implementation) - ┌────────────┐ ┌────────────┐ - │ Phase A-1 │ │ Phase B-1 │ - │ API 设计 │ │ 脚手架搭建 │ - └─────┬──────┘ └─────┬──────┘ - │ │ - ▼ ┌──────────┐ ▼ - ╔═══════════════╗│ SYNC-1 │╔═══════════════╗ - ║ checkpoint 1 ║│ 对齐接口 │║ checkpoint 1 ║ - ╚═══════════════╝└──────────┘╚═══════════════╝ - │ │ - ▼ ▼ - ┌────────────┐ ┌────────────┐ - │ Phase A-2 │ │ Phase B-2 │ - │ 详细设计 │ │ 核心实现 │ - └─────┬──────┘ └─────┬──────┘ - │ │ - ▼ ┌──────────┐ ▼ - ╔═══════════════╗│ SYNC-2 │╔═══════════════╗ - ║ checkpoint 2 ║│ 集成验证 │║ checkpoint 2 ║ - ╚═══════════════╝└──────────┘╚═══════════════╝ -``` - -```javascript -// Coordinator defines sync points -const syncPoints = [ - { - id: "SYNC-1", - name: "Interface Contract", - trackA_deliverable: "API schema / interface definitions", - trackB_deliverable: "Scaffold with interface stubs", - alignment_check: "Both tracks agree on interface signatures" - }, - { - id: "SYNC-2", - name: "Integration Verification", - trackA_deliverable: "Complete design + test specs", - trackB_deliverable: "Core implementation", - alignment_check: "Implementation passes design test specs" - } -] - -// Phase execution with sync barriers -for (const sync of syncPoints) { - // Launch both tracks in parallel - const trackATask = TaskCreate({ - subject: `TRACK-A-${sync.id}: ${sync.trackA_deliverable}`, - owner: "track-a-agent" - }) - const trackBTask = TaskCreate({ - subject: `TRACK-B-${sync.id}: ${sync.trackB_deliverable}`, - owner: "track-b-agent" - }) - - // Wait for both tracks to reach sync point - waitForBoth(trackATask, trackBTask) - - // Sync point: alignment check - const aligned = checkAlignment(sync.alignment_check, trackAResult, trackBResult) - - if (!aligned) { - // Misalignment detected → correction - team_msg({ type: "sync_checkpoint", data: { - sync_id: sync.id, - status: "MISALIGNED", - trackA_state: trackAResult.summary, - trackB_state: trackBResult.summary, - conflicts: aligned.conflicts - }}) - // Coordinator mediates: which track adjusts? - resolveAlignment(aligned.conflicts, trackATask, trackBTask) - } else { - team_msg({ type: "sync_checkpoint", data: { sync_id: sync.id, status: "ALIGNED" } }) - } -} -``` - -### Convergence - -| Element | Value | -|---------|-------| -| **Success Gate** | 所有 sync point 对齐 + 最终集成验证通过 | -| **Max Iterations** | 每个 sync point 最多 2 次对齐尝试 | -| **Timeout** | 先到达 sync point 的 track 等待另一个 track，超时 5 分钟 | - -### Feedback Loop - -``` -Signal: sync_checkpoint { status: "MISALIGNED", conflicts } - ↓ -Handler: Coordinator 分析冲突来源 - ├─ Track A 的设计不合理 → 要求 Track A 调整设计 - ├─ Track B 偏离了接口约定 → 要求 Track B 重新对齐 - └─ 双方都有偏差 → 协商折中方案 - ↓ -Correction: 被要求调整的 track agent 收到 fix 描述 - → 调整产出 → 重新到达 sync point -``` - -### Fallback - -| Condition | Action | -|-----------|--------| -| 一条 track 完全阻塞 | 另一条 track 暂停等待，触发 CP-7 Swarming 解决阻塞 | -| Sync 对齐 2 次失败 | 降级为 CP-1 Linear Pipeline（顺序执行） | -| 两条 track 差距过大（一快一慢） | 快 track 预做下一阶段，慢 track 加速 | - ---- - -## CP-10: Post-Mortem (复盘回顾) - -### Description - -任务完成后，对整个执行过程进行结构化回顾，提取经验教训和改进建议。这些知识可以反馈到项目的 CLAUDE.md 或 core memory 中，提升未来任务的执行质量。 - -### Entry Condition - -- 团队完成一个完整任务周期后（所有 task completed） -- 任务执行过程中出现显著问题（多次失败、多次升级） -- 用户主动请求回顾 - -### Roles Required - -`coordinator` (发起 + 汇总) → `all agents` (提供各自视角) → `coordinator` (文档化) - -### Workflow - -``` - ┌──────────────────────────────────────────┐ - │ POST-MORTEM PHASE │ - │ │ - │ 1. Coordinator 收集执行数据 │ - │ ├─ 任务链完成情况 │ - │ ├─ 消息总线历史 │ - │ └─ 迭代/升级/失败记录 │ - │ │ - │ 2. 每个 Agent 提交回顾 │ - │ ├─ Planner: 规划准确度 │ - │ ├─ Executor: 实现障碍 │ - │ └─ Tester: 质量发现 │ - │ │ - │ 3. Coordinator 汇总 │ - │ ├─ 成功因素 │ - │ ├─ 改进点 │ - │ └─ 行动建议 │ - │ │ - │ 4. 输出到 memory / CLAUDE.md │ - └──────────────────────────────────────────┘ -``` - -```javascript -// Coordinator initiates post-mortem -function conductPostMortem(teamName) { - // Step 1: Collect execution data - const messages = team_msg({ operation: "list", team: teamName }) - const tasks = TaskList() - const completedTasks = tasks.filter(t => t.status === 'completed') - const failedTasks = tasks.filter(t => t.status === 'in_progress' && t.metadata?.stuck) - - const executionData = { - total_tasks: tasks.length, - completed: completedTasks.length, - total_messages: messages.length, - escalations: messages.filter(m => m.type === 'escalate').length, - fix_cycles: messages.filter(m => m.type === 'fix_required').length, - errors: messages.filter(m => m.type === 'error').length - } - - // Step 2: Request agent retrospectives (Fan-out) - // Each agent answers: What went well? What was difficult? What should change? - agents.forEach(agent => { - SendMessage({ - recipient: agent.name, - content: `## Post-Mortem Request -请回顾本次任务，回答: -1. **顺利**: 哪些方面执行顺利？ -2. **困难**: 遇到了什么障碍？ -3. **建议**: 下次如何改进？ -4. **模式**: 发现了什么可复用的模式？`, - summary: "Post-mortem request" - }) - }) - - // Step 3: Aggregate findings - // Collect retro_finding messages from all agents - const findings = collectFindings(agents) - - // Step 4: Generate structured post-mortem report - const report = { - team: teamName, - timestamp: new Date().toISOString(), - execution_summary: executionData, - what_went_well: findings.flatMap(f => f.went_well), - what_was_difficult: findings.flatMap(f => f.difficult), - improvement_actions: findings.flatMap(f => f.suggestions), - reusable_patterns: findings.flatMap(f => f.patterns), - recommendations: generateRecommendations(executionData, findings) - } - - // Step 5: Persist learnings - // Option A: Write to session artifacts - Write(`${sessionFolder}/post-mortem.json`, JSON.stringify(report, null, 2)) - - // Option B: Import to core memory (if significant) - if (report.reusable_patterns.length > 0) { - mcp__ccw-tools__core_memory({ - operation: "import", - text: `Team ${teamName} post-mortem: ${report.reusable_patterns.join('; ')}` - }) - } - - return report -} -``` - -### Convergence - -| Element | Value | -|---------|-------| -| **Success Gate** | 所有 agent 提交回顾 + 报告生成完毕 | -| **Max Iterations** | 1 轮（回顾是单次活动） | -| **Timeout** | Agent 回顾提交超时 3 分钟，超时则仅用已收到的回顾 | - -### Feedback Loop - -``` -Signal: retro_finding { went_well, difficult, suggestions, patterns } - ↓ -Handler: Coordinator 分类、去重、优先级排序 - ↓ -Output: ├─ 高价值 patterns → 写入 core memory / CLAUDE.md - ├─ 改进建议 → 记录到项目 guidelines - └─ 问题根因 → 作为下次任务的预防措施 -``` - -**学习闭环**: Post-mortem 的输出反馈到未来任务的 Phase 2 Context Loading，实现持续改进。 - -### Fallback - -| Condition | Action | -|-----------|--------| -| Agent 无法提供回顾（已关闭） | 从消息总线历史中提取该 agent 的执行数据 | -| 无显著 findings | 生成最小报告，不写入 core memory | -| 执行数据缺失 | 基于现有数据生成部分报告 | - ---- - -## CP-11: Beat Pipeline (节拍流水线) - -### Description - -消除阶段间批处理同步屏障的流水线模式。上游角色每完成一个工作单元（如一个 issue 的 solution）立即输出信号，下游角色即时开始处理，两者并行重叠执行。核心区别于 CP-1（整阶段串行）和 CP-6（阶段内增量但阶段间仍串行）：CP-11 将"阶段边界"从同步屏障降级为轻量信号，实现真正的上下游并行。 - -三大支撑机制： -1. **逐条派发 (Per-item Dispatch)** — 每完成一个单元即输出 `item_ready` 信号，不等同批其他单元 -2. **中间产物 (Intermediate Artifacts)** — 上游将结果写入文件，下游从文件加载，解耦上下游上下文 -3. **内联轻量检查 (Inline Lightweight Check)** — 用 ~20 行内联逻辑替代重量级子 agent 调用（如冲突检测） - -### Entry Condition - -- 上游（规划）和下游（执行）存在天然流水线关系 -- 上游产出可以逐条独立消费（各单元间无强顺序依赖，或依赖可通过轻量检查标记） -- 下游处理耗时 ≥ 上游单元产出间隔（否则批处理反而更简单） -- 传统批处理导致下游大量空闲等待 - -### Roles Required - -`coordinator` → `producer`(上游) + `consumer`(下游, 可多实例) - -### Workflow - -``` - Producer (planner) Coordinator Consumer (executor) - ───────────────── ─────────── ────────────────── - │ │ │ - ┌────┴────┐ │ │ - │ Plan │ │ │ - │ Item 1 │ │ │ - └────┬────┘ │ │ - │ item_ready(1) │ │ - │─────────────────────────────→│ │ - │ │──spawn/dispatch────────→│ - ┌────┴────┐ │ ┌────┴────┐ - │ Plan │ │ │ Execute │ - │ Item 2 │ (parallel overlap) │ │ Item 1 │ - └────┬────┘ │ └────┬────┘ - │ item_ready(2) │ │ - │─────────────────────────────→│ │ - │ │──spawn/dispatch────────→│ (new instance) - ┌────┴────┐ │ │ - │ Plan │ │ ┌────┴────┐ - │ Item 3 │ │ │ Execute │ - └────┬────┘ │ │ Item 2 │ - │ all_planned │ └────┬────┘ - │─────────────────────────────→│ │ - │ │──wait all consumers────→│ - │ │ │ impl_complete - │ │←────────────────────────│ - │ │ │ - [aggregate results] -``` - -```javascript -// ── Coordinator: Per-item dispatch loop ── -const producer = spawnProducer(requirements) -const consumers = [] - -while (true) { - const output = waitForProducer(producer) - const itemData = parseItemReady(output) - - if (itemData) { - // Spawn consumer immediately — don't wait for other items - const consumer = spawnConsumer({ - item: itemData, - artifactFile: itemData.artifact_file // File-based handoff - }) - consumers.push(consumer) - } - - if (output.includes('all_planned')) break - - // Tell producer to continue next item - continueProducer(producer) -} - -// Wait for all consumers to finish -waitForAllConsumers(consumers) -aggregateResults(consumers) -``` - -#### 中间产物协议 - -上游将每个工作单元的完整数据写入文件，仅通过信号传递文件路径： - -```javascript -// Producer: 写中间产物 -const artifactFile = `${sessionDir}/artifacts/${itemId}.json` -writeFile(artifactFile, JSON.stringify({ - item_id: itemId, - data: solutionData, - config: executionConfig, - timestamp: new Date().toISOString() -}, null, 2)) - -// Signal: 仅传路径 -output({ status: 'item_ready', item_id: itemId, artifact_file: artifactFile }) -``` - -```javascript -// Consumer: 从文件加载（兼容无文件 fallback） -let data -if (artifactFile) { - try { - data = JSON.parse(readFile(artifactFile)) - } catch { - data = loadFromCli(itemId) // Fallback - } -} else { - data = loadFromCli(itemId) // Legacy path -} -``` - -#### 内联轻量检查 - -替代重量级子 agent 的冲突/依赖检测： - -```javascript -function inlineConflictCheck(itemId, itemData, dispatched) { - const currentFiles = itemData.files_touched || [] - const blockedBy = [] - - // 1. 文件冲突：当前 item 触及的文件与已派发 item 有重叠 - for (const prev of dispatched) { - const prevFiles = prev.data.files_touched || [] - if (currentFiles.some(f => prevFiles.includes(f))) { - blockedBy.push(prev.itemId) - } - } - - // 2. 显式依赖 - const explicitDeps = itemData.dependencies || [] - for (const dep of explicitDeps) { - if (!blockedBy.includes(dep)) blockedBy.push(dep) - } - - return blockedBy // Empty = can execute immediately -} -``` - -### Convergence - -| Element | Value | -|---------|-------| -| **Success Gate** | Producer 输出 `all_planned` + 所有 Consumer 输出 `impl_complete` | -| **Max Iterations** | Producer: N items (有限); Consumer: 每个 item 内部最多 2 次 test-fix retry | -| **Timeout** | Producer per-item: 10 min (超时则催促收敛); Consumer per-item: 15 min | - -### Feedback Loop - -``` -Signal: item_ready { item_id, artifact_file, depends_on } - ↓ -Handler: Coordinator 检查 depends_on，spawn Consumer（或标记 blocked） - ↓ -Signal: impl_complete { item_id, status, commit_hash } - ↓ -Handler: Coordinator 累积结果 - ├─ status=success → 记录 commit，解锁被阻塞的 items - ├─ status=failed → 记录错误，跳过（不阻塞其他独立 items） - └─ all consumers done → 汇总报告 -``` - -**流水线重叠效果**: Producer 规划 Item N+1 的同时，Consumer 执行 Item N。当 Producer 输出速度 < Consumer 执行速度时，Consumer 始终有工作可做，消除空闲等待。 - -### Fallback - -| Condition | Action | -|-----------|--------| -| Producer 长时间无输出 | send_input 催促收敛，retry wait 120s | -| Consumer 执行失败 | 记录 failed，继续其他 items（不级联失败） | -| 中间产物文件读取失败 | Consumer fallback 到 CLI 命令加载 | -| 内联冲突检查误判 | Consumer 执行时自然发现冲突（git merge conflict），报告 failed | -| Producer 异常退出 | 视为 all_planned，等待已派发 Consumers 完成 | -| 依赖链过长导致 Consumer 全部 blocked | 升级到 CP-1 串行模式 | - -### 与其他模式的区别 - -| 维度 | CP-1 Linear | CP-6 Incremental | CP-9 Dual-Track | **CP-11 Beat** | -|------|-------------|-------------------|------------------|----------------| -| 阶段边界 | 硬同步屏障 | 阶段内增量，阶段间串行 | 两条并行 track | 无边界，逐条流转 | -| 上下游关系 | 串行 | 串行（增量粒度） | 并行但独立 | 并行且流水线重叠 | -| 调度粒度 | 整阶段 | 增量批次 | Track 级 | 单个工作单元 | -| 空闲等待 | 下游等整阶段 | 下游等增量批次 | 两 track 独立 | 近零（流水线填充） | -| 中间产物 | 内存传递 | 内存传递 | 各 track 独立 | 文件传递（解耦上下文） | -| 冲突检测 | 无需 | 无需 | Sync checkpoint | 内联轻量检查 | - -### 适用实例 - -- **PlanEx Pipeline**: Planner 逐 issue 输出 solution，Executor 即时实现 -- **CI/CD Pipeline**: Builder 逐模块构建，Deployer 即时部署 -- **Document Pipeline**: Analyzer 逐章节分析，Writer 即时撰写 - -### 平台实现差异 - -| 维度 | Claude (TaskCreate/SendMessage) | Codex (spawn_agent/wait/send_input) | -|------|--------------------------------|--------------------------------------| -| 派发机制 | `TaskCreate` + `SendMessage` 通知 | `spawn_agent` 每个 Consumer | -| 信号传递 | `mcp__ccw-tools__team_msg` | Producer 文本输出 marker（ISSUE_READY/ALL_PLANNED） | -| 等待机制 | TaskList 轮询 + SendMessage 回调 | `wait({ ids: [...] })` | -| 催促收敛 | SendMessage 提醒 | `send_input` 催促 | -| 中间产物 | Write tool → Read tool | `write_file` → `read_file` | -| 依赖标记 | `TaskUpdate({ addBlockedBy })` | Producer 输出 `depends_on` 数组，Coordinator 控制 spawn 顺序 | - ---- - -## Pattern Composition (模式组合) - -### 常见组合 - -协作模式可以组合使用，形成更复杂的工作流： - -``` -1. Standard Development (标准开发) - CP-1 (Pipeline) + CP-2 (Review-Fix) + CP-10 (Post-Mortem) - -2. High-Risk Feature (高风险特性) - CP-4 (Consensus on design) → CP-6 (Incremental Delivery) → CP-2 (Review-Fix each increment) - -3. Complex Investigation (复杂问题调查) - CP-3 (Fan-out analysis) → CP-4 (Consensus on diagnosis) → CP-7 (Swarm if needed) - -4. Parallel Development (并行开发) - CP-9 (Dual-Track) + CP-2 (Review-Fix per track) + CP-10 (Post-Mortem) - -5. Expert-Guided Development (专家指导开发) - CP-8 (Consulting for design) → CP-1 (Pipeline implementation) → CP-2 (Review-Fix) - -6. Plan-and-Execute Pipeline (边规划边执行) - CP-11 (Beat Pipeline) + CP-2 (Review-Fix per item) + CP-10 (Post-Mortem) - -7. High-Throughput Batch Processing (高吞吐批处理) - CP-8 (Consulting for architecture) → CP-11 (Beat Pipeline) → CP-3 (Fan-out for testing) -``` - -### 组合规则 - -1. **不可重入**: 同一时间只能有一个 CP-7 (Swarming) 实例 -2. **可嵌套**: CP-6 的每个增量可以内部使用 CP-2 -3. **可升级**: CP-2 内发现无法修复的问题可升级到 CP-5 或 CP-7 -4. **可降级**: CP-9 对齐失败可降级到 CP-1; CP-11 依赖链过长可降级到 CP-1 -5. **CP-10 始终在最后**: Post-mortem 只在团队任务完成后执行 -6. **CP-11 可替代 CP-1**: 当上下游可流水线重叠时，CP-11 是 CP-1 的升级版 - -### State Machine (模式状态机) - -``` - ┌──────────────────────────────────────────┐ - │ COORDINATOR FSM │ - │ │ - 新需求 ────→ [PLAN] ──→ [EXECUTE] ──→ [VALIDATE] ──→ [DONE] │ - │ │ │ │ │ - │ │ │ │ │ - ▼ ▼ ▼ ▼ │ - CP-4? CP-6? CP-2? CP-10 │ - Consensus Incremental Review-Fix Post- │ - Gate Delivery Cycle Mortem │ - │ │ │ │ - ▼ ▼ ▼ │ - [blocked?] [blocked?] [blocked?] │ - │ │ │ │ - ▼ ▼ ▼ │ - CP-5/CP-7 CP-5/CP-7 CP-5/CP-7 │ - Escalate Escalate Escalate │ - /Swarm /Swarm /Swarm │ - └──────────────────────────────────────────┘ -``` - ---- - -## Coordinator Integration Guide - -### Coordinator 如何选择协作模式 - -```javascript -// In coordinate.md Phase 1 (需求澄清) or Phase 4 (协调主循环) - -function selectCollaborationPattern(context) { - const { taskType, complexity, riskLevel, teamSize, hasExpert } = context - - // Rule-based selection - const patterns = ['CP-1'] // CP-1 is always the base - - if (riskLevel === 'high') patterns.push('CP-4') // Consensus for risky decisions - if (complexity === 'High' && taskType === 'feature') patterns.push('CP-6') // Incremental for large features - if (taskType === 'review' || taskType === 'test') patterns.push('CP-2') // Review-Fix for quality - if (hasExpert && complexity !== 'Low') patterns.push('CP-8') // Consulting for expertise - if (taskType === 'batch' || taskType === 'multi-issue') patterns.push('CP-11') // Beat for pipeline overlap - patterns.push('CP-10') // Post-mortem always included - - return patterns -} -``` - -### Coordinator 消息路由表（含协作模式） - -| 消息类型 | 触发模式 | Coordinator 动作 | -|---------|---------|-----------------| -| `plan_ready` | CP-1 | 审批 plan → 通知 executor | -| `impl_complete` | CP-1/CP-6/CP-11 | 解锁 TEST/REVIEW 或下一增量/累积结果 | -| `review_result` (BLOCK) | CP-2 | 创建 fix 任务 → 启动 Review-Fix Cycle | -| `vote` | CP-4 | 收集投票 → 达到 quorum 则执行决策 | -| `escalate` | CP-5 | 路由到上一级处理者 | -| `increment_ready` | CP-6 | 验证增量 gate → 允许或拒绝 | -| `swarm_join` | CP-7 | 暂停其他任务 → 聚合诊断 | -| `consult_request` | CP-8 | 路由到 specialist 或 CLI tool | -| `sync_checkpoint` | CP-9 | 检查两条 track 对齐状态 | -| `retro_finding` | CP-10 | 收集回顾 → 生成报告 | -| `item_ready` | CP-11 | Spawn consumer → 传递 artifact_file | -| `all_planned` | CP-11 | 停止等待 producer → wait all consumers | diff --git a/.claude/skills_lib/team-skill-designer-v2/specs/quality-standards.md b/.claude/skills_lib/team-skill-designer-v2/specs/quality-standards.md deleted file mode 100644 index c7e5fe97..00000000 --- a/.claude/skills_lib/team-skill-designer-v2/specs/quality-standards.md +++ /dev/null @@ -1,242 +0,0 @@ -# Quality Standards for Team Skills (v2) - -Quality assessment criteria for generated team skill packages (v3 style: text + decision tables, no pseudocode). - -## When to Use - -| Phase | Usage | Section | -|-------|-------|---------| -| Phase 5 | Score generated command | All dimensions | -| Phase 3 | Guide generation quality | Checklist | - ---- - -## Quality Dimensions - -### 1. Completeness (25%) - -| Score | Criteria | -|-------|----------| -| 100% | All 15 required sections present with substantive content | -| 80% | 12+ sections present, minor gaps in non-critical areas | -| 60% | Core sections present (front matter, message bus, 5 phases, error handling) | -| 40% | Missing critical sections | -| 0% | Skeleton only | - -**Required Sections Checklist (role.md files):** -- [ ] Role Identity (name, task prefix, output tag, responsibility) -- [ ] Role Boundaries (MUST / MUST NOT) -- [ ] Toolbox section (Available Commands with markdown links) -- [ ] Phase 2: Context Loading (decision tables, no pseudocode) -- [ ] Phase 3: Core Work (decision tables + tool call templates) -- [ ] Phase 4: Validation/Summary (checklist tables) -- [ ] Error Handling table -- [ ] Phase 1/5: Reference to SKILL.md Shared Infrastructure (not inline) -- [ ] No JavaScript pseudocode in any phase -- [ ] All branching logic expressed as decision tables - -**Required Sections Checklist (SKILL.md):** -- [ ] Frontmatter (name, description, allowed-tools) -- [ ] Architecture Overview (role routing diagram with flow symbols) -- [ ] Role Router (Input Parsing + Role Registry table with markdown links) -- [ ] Shared Infrastructure (Worker Phase 1 Task Discovery + Phase 5 Report templates) -- [ ] Pipeline Definitions with Cadence Control (beat diagram + checkpoints) -- [ ] Compact Protection (Phase Reference table with Compact column) -- [ ] Coordinator Spawn Template -- [ ] Role Isolation Rules table -- [ ] Error Handling table - -**SKILL.md MUST NOT contain:** -- [ ] ❌ No JavaScript pseudocode (VALID_ROLES object, routing functions, etc.) -- [ ] ❌ No role-specific implementation logic (belongs in role.md or commands/*.md) -- [ ] ❌ No `${variable}` notation (use `` instead) - -> **Note**: For `commands/*.md` file quality criteria, see [Command File Quality Standards](#command-file-quality-standards) below. - -### 2. Pattern Compliance (25%) - -| Score | Criteria | -|-------|----------| -| 100% | All 9 infrastructure patterns + selected collaboration patterns fully implemented | -| 80% | 7 core infra patterns + at least 1 collaboration pattern with convergence | -| 60% | Minimum 6 infra patterns, collaboration patterns present but incomplete | -| 40% | Missing critical patterns (message bus or task lifecycle) | -| 0% | No pattern compliance | - -**Infrastructure Pattern Checklist:** -- [ ] Pattern 1: Message bus - team_msg before every SendMessage -- [ ] Pattern 1b: CLI fallback section -- [ ] Pattern 2: YAML front matter - all fields present -- [ ] Pattern 3: Task lifecycle - TaskList/Get/Update flow -- [ ] Pattern 4: Five-phase structure (Phase 1/5 shared in SKILL.md, Phase 2-4 in role.md) -- [ ] Pattern 5: Complexity-adaptive (if applicable) -- [ ] Pattern 6: Coordinator spawn compatible -- [ ] Pattern 7: Error handling table -- [ ] Pattern 8: Session files (if applicable) -- [ ] Pattern 9: Compact Protection (Phase Reference table + re-read directives) - -**Collaboration Pattern Checklist:** -- [ ] At least one CP selected (CP-1 minimum) -- [ ] Each selected CP has convergence criteria defined -- [ ] Each selected CP has feedback loop mechanism -- [ ] Each selected CP has timeout/fallback behavior -- [ ] CP-specific message types registered in message bus section -- [ ] Escalation path defined (CP-5) for error scenarios - -### 3. Integration (25%) - -| Score | Criteria | -|-------|----------| -| 100% | All integration checks pass, spawn snippet ready | -| 80% | Minor integration notes, no blocking issues | -| 60% | Some checks need attention but functional | -| 40% | Task prefix conflict or missing critical tools | -| 0% | Incompatible with team system | - -### 4. Consistency (25%) - -| Score | Criteria | -|-------|----------| -| 100% | Role name, task prefix, message types consistent throughout | -| 80% | Minor inconsistencies in non-critical areas | -| 60% | Some mixed terminology but intent clear | -| 40% | Confusing or contradictory content | -| 0% | Internally inconsistent | - ---- - -## Quality Gates - -| Gate | Threshold | Action | -|------|-----------|--------| -| PASS | >= 80% | Deliver to `.claude/skills/team-{name}/` | -| REVIEW | 60-79% | Fix recommendations, re-validate | -| FAIL | < 60% | Major rework needed, re-run from Phase 3 | - ---- - -## Issue Classification - -### Errors (Must Fix) - -- Missing YAML front matter -- Missing `group: team` -- No message bus section -- No task lifecycle (TaskList/Get/Update) -- No SendMessage to coordinator -- Task prefix conflicts with existing -- **Coordinator dispatch `owner` values not in Role Registry** — all task owners must match a role in SKILL.md Role Registry table -- **Monitor spawn prompt missing Skill callback** — spawn prompt must contain `Skill(skill="team-xxx", args="--role=yyy")` -- **Spawn template missing `description` parameter** — Task() requires `description` as a mandatory field -- **Spawn template missing `team_name` or `name` parameter** — agent will not join the team or have identity - -### Warnings (Should Fix) - -- Missing error handling table -- Incomplete Phase implementation (skeleton only) -- Missing team_msg before some SendMessage calls -- Missing CLI fallback section (`### CLI 回退` with `ccw team` examples) -- No complexity-adaptive routing when role is complex -- **Dispatch task IDs not aligned with pipeline diagram** — task IDs (e.g., RESEARCH-001, DRAFT-001) must match the pipeline defined in SKILL.md -- **Coordinator commands reference roles not in Message Routing Tables** — all roles in dispatch/monitor must appear in SKILL.md Available Roles table - -### Info (Nice to Have) - -- Decision tables could cover more edge cases -- Additional tool call examples -- Session file structure documentation - ---- - -## Coordinator Commands Consistency Standards - -Quality assessment for coordinator's `dispatch.md` and `monitor.md` command files. These files are the most common source of integration failures. - -### 6. Coordinator-SKILL Alignment (Applies to coordinator commands) - -| Score | Criteria | -|-------|----------| -| 100% | All 5 alignment checks pass | -| 80% | 4/5 pass, one minor mismatch | -| 60% | 3/5 pass, cosmetic role naming issues | -| 40% | Critical mismatch: roles not in VALID_ROLES or missing Skill callback | -| 0% | dispatch/monitor written independently of SKILL.md | - -#### Check 1: Role Name Alignment - -- [ ] Every `owner` value in dispatch.md TaskCreate calls exists in SKILL.md Role Registry table -- [ ] No invented role names (e.g., "spec-writer" when Role Registry has "writer") -- [ ] No typos or case mismatches in role names - -#### Check 2: Task ID-Pipeline Alignment - -- [ ] Task IDs in dispatch.md match the pipeline diagram in SKILL.md -- [ ] Task prefix mapping is consistent (e.g., RESEARCH-* → analyst, DRAFT-* → writer) -- [ ] Dependency chain in dispatch.md matches pipeline flow arrows - -#### Check 3: Spawn Template Completeness - -- [ ] monitor.md Task() calls include ALL required parameters: `description`, `team_name`, `name`, `prompt` -- [ ] Spawn prompt contains `Skill(skill="team-xxx", args="--role=yyy")` callback -- [ ] Spawn prompt includes role boundaries (task prefix constraint, output tag, communication rules) -- [ ] Spawn prompt is NOT a minimal generic instruction (e.g., "Execute task X") - -#### Check 4: Message Routing Table Alignment - -- [ ] All roles in dispatch.md appear in monitor.md's Message Routing Tables -- [ ] All message types used by roles are listed in the routing tables -- [ ] Sender roles in routing tables match Role Registry entries - -#### Check 5: v3 Style Compliance - -- [ ] No JavaScript pseudocode in any generated file -- [ ] All branching logic expressed as decision tables -- [ ] Code blocks contain only actual tool calls -- [ ] `` notation used (not `${variable}`) -- [ ] Phase 1/5 reference SKILL.md Shared Infrastructure (not inline) - ---- - -## Command File Quality Standards - -Quality assessment criteria for generated command `.md` files in `roles/{name}/commands/`. - -### 5. Command File Quality (Applies to folder-based roles) - -| Score | Criteria | -|-------|----------| -| 100% | All 4 dimensions pass, all command files self-contained | -| 80% | 3/4 dimensions pass, minor gaps in one area | -| 60% | 2/4 dimensions pass, some cross-references or missing sections | -| 40% | Missing required sections or broken references | -| 0% | No command files or non-functional | - -#### Dimension 1: Structural Completeness - -Each command file MUST contain: -- [ ] `## When to Use` - Trigger conditions -- [ ] `## Strategy` with delegation mode (Subagent / CLI / Sequential / Direct) -- [ ] `## Execution Steps` with decision tables and tool call templates -- [ ] `## Error Handling` table with Scenario/Resolution -- [ ] `## Output Format` section - -#### Dimension 2: Self-Containment - -- [ ] No `Ref:` or cross-references to other command files -- [ ] No imports or dependencies on sibling commands -- [ ] All context loaded within the command (task, plan, files) -- [ ] Any subagent can `Read()` the command and execute independently - -#### Dimension 3: Toolbox Consistency - -- [ ] Every command listed in role.md Toolbox has a corresponding file in `commands/` -- [ ] Every file in `commands/` is listed in role.md Toolbox -- [ ] Phase mapping in Toolbox matches command's `## When to Use` phase reference -- [ ] Delegation mode in command matches role's subagent/CLI capabilities - -#### Dimension 4: Pattern Compliance - -- [ ] Pre-built command patterns (explore, analyze, implement, validate, review, dispatch, monitor) follow templates/role-command-template.md -- [ ] Custom commands follow the template skeleton structure -- [ ] Delegation mode is appropriate for the command's complexity -- [ ] Output format is structured and parseable by the calling role.md diff --git a/.claude/skills_lib/team-skill-designer-v2/specs/team-design-patterns.md b/.claude/skills_lib/team-skill-designer-v2/specs/team-design-patterns.md deleted file mode 100644 index 67e4d0bb..00000000 --- a/.claude/skills_lib/team-skill-designer-v2/specs/team-design-patterns.md +++ /dev/null @@ -1,590 +0,0 @@ -# Team Command Design Patterns - -> Extracted from 5 production team commands: coordinate, plan, execute, test, review -> Extended with 10 collaboration patterns for diverse team interaction models - ---- - -## Pattern Architecture - -``` -Team Design Patterns -├── Section A: Infrastructure Patterns (9) ← HOW to build a team command -│ ├── Pattern 1: Message Bus Integration -│ ├── Pattern 2: YAML Front Matter -│ ├── Pattern 3: Task Lifecycle -│ ├── Pattern 4: Five-Phase Execution -│ ├── Pattern 5: Complexity-Adaptive Routing -│ ├── Pattern 6: Coordinator Spawn Integration -│ ├── Pattern 7: Error Handling Table -│ └── Pattern 8: Session File Structure -│ -└── Section B: Collaboration Patterns (10) ← HOW agents interact - ├── CP-1: Linear Pipeline (线性流水线) - ├── CP-2: Review-Fix Cycle (审查修复循环) - ├── CP-3: Parallel Fan-out/Fan-in (并行扇出扇入) - ├── CP-4: Consensus Gate (共识门控) - ├── CP-5: Escalation Chain (逐级升级) - ├── CP-6: Incremental Delivery (增量交付) - ├── CP-7: Swarming (群策攻关) - ├── CP-8: Consulting/Advisory (咨询顾问) - ├── CP-9: Dual-Track (双轨并行) - └── CP-10: Post-Mortem (复盘回顾) -``` - -**Section B** collaboration patterns are documented in: [collaboration-patterns.md](collaboration-patterns.md) - ---- - -## When to Use - -| Phase | Usage | Section | -|-------|-------|---------| -| Phase 0 | Understand all patterns before design | All sections | -| Phase 2 | Select applicable infrastructure + collaboration patterns | Pattern catalog | -| Phase 3 | Apply patterns during generation | Implementation details | -| Phase 4 | Verify compliance | Checklists | - ---- - -# Section A: Infrastructure Patterns - -## Pattern 1: Message Bus Integration - -Every teammate must use `mcp__ccw-tools__team_msg` for persistent logging before every `SendMessage`. - -### Structure - -```javascript -// BEFORE every SendMessage, call: -mcp__ccw-tools__team_msg({ - operation: "log", - team: teamName, - from: "", // planner | executor | tester | - to: "coordinator", - type: "", - summary: "", - ref: "", - data: { /* optional structured payload */ } -}) -``` - -### Standard Message Types - -| Type | Direction | Trigger | Payload | -|------|-----------|---------|---------| -| `plan_ready` | planner -> coordinator | Plan generation complete | `{ taskCount, complexity }` | -| `plan_approved` | coordinator -> planner | Plan reviewed | `{ approved: true }` | -| `plan_revision` | planner -> coordinator | Plan modified per feedback | `{ changes }` | -| `task_unblocked` | coordinator -> any | Dependency resolved | `{ taskId }` | -| `impl_complete` | executor -> coordinator | Implementation done | `{ changedFiles, syntaxClean }` | -| `impl_progress` | any -> coordinator | Progress update | `{ batch, total }` | -| `test_result` | tester -> coordinator | Test cycle end | `{ passRate, iterations }` | -| `review_result` | tester -> coordinator | Review done | `{ verdict, findings }` | -| `fix_required` | any -> coordinator | Critical issues | `{ details[] }` | -| `error` | any -> coordinator | Blocking error | `{ message }` | -| `shutdown` | coordinator -> all | Team dissolved | `{}` | - -### Collaboration Pattern Message Types - -| Type | Used By | Direction | Trigger | -|------|---------|-----------|---------| -| `vote` | CP-4 Consensus | any -> coordinator | Agent casts vote on proposal | -| `escalate` | CP-5 Escalation | any -> coordinator | Agent escalates unresolved issue | -| `increment_ready` | CP-6 Incremental | executor -> coordinator | Increment delivered for validation | -| `swarm_join` | CP-7 Swarming | any -> coordinator | Agent joins swarm on blocker | -| `consult_request` | CP-8 Consulting | any -> specialist | Agent requests expert advice | -| `consult_response` | CP-8 Consulting | specialist -> requester | Expert provides advice | -| `sync_checkpoint` | CP-9 Dual-Track | any -> coordinator | Track reaches sync point | -| `retro_finding` | CP-10 Post-Mortem | any -> coordinator | Retrospective insight | - -### Adding New Message Types - -When designing a new role, define role-specific message types following the convention: -- `{action}_ready` - Work product ready for review -- `{action}_complete` - Work phase finished -- `{action}_progress` - Intermediate progress update - -### CLI Fallback - -When `mcp__ccw-tools__team_msg` MCP is unavailable, use `ccw team` CLI as equivalent fallback: - -```javascript -// Fallback: Replace MCP call with Bash CLI (parameters map 1:1) -Bash(`ccw team log --team "${teamName}" --from "" --to "coordinator" --type "" --summary "" [--ref ] [--data ''] --json`) -``` - -**Parameter mapping**: `team_msg(params)` → `ccw team --team [--from/--to/--type/--summary/--ref/--data/--id/--last] [--json]` - -**Coordinator** uses all 4 operations: `log`, `list`, `status`, `read` -**Teammates** primarily use: `log` - -### Message Bus Section Template - -```markdown -## 消息总线 - -每次 SendMessage **前**，必须调用 `mcp__ccw-tools__team_msg` 记录消息： - -\`\`\`javascript -mcp__ccw-tools__team_msg({ operation: "log", team: teamName, from: "", to: "coordinator", type: "", summary: "" }) -\`\`\` - -### 支持的 Message Types - -| Type | 方向 | 触发时机 | 说明 | -|------|------|----------|------| -| `` | → coordinator | | | - -### CLI 回退 - -当 `mcp__ccw-tools__team_msg` MCP 不可用时，使用 `ccw team` CLI 作为等效回退： - -\`\`\`javascript -// 回退: 将 MCP 调用替换为 Bash CLI（参数一一对应） -Bash(\`ccw team log --team "${teamName}" --from "" --to "coordinator" --type "" --summary "" --json\`) -\`\`\` - -**参数映射**: `team_msg(params)` → `ccw team log --team --from --to coordinator --type --summary "" [--ref ] [--data ''] [--json]` -``` - ---- - -## Pattern 2: YAML Front Matter - -Every team command file must start with standardized YAML front matter. - -### Structure - -```yaml ---- -name: -description: Team - -argument-hint: "" -allowed-tools: SendMessage(*), TaskUpdate(*), TaskList(*), TaskGet(*), TodoWrite(*), Read(*), Write(*), Edit(*), Bash(*), Glob(*), Grep(*), Task(*) -group: team ---- -``` - -### Field Rules - -| Field | Rule | Example | -|-------|------|---------| -| `name` | Lowercase, matches filename | `plan`, `execute`, `test` | -| `description` | `Team -` prefix + Chinese capability list | `Team planner - 多角度代码探索、结构化实现规划` | -| `argument-hint` | Empty string for teammates, has hint for coordinator | `""` | -| `allowed-tools` | Start with `SendMessage(*), TaskUpdate(*), TaskList(*), TaskGet(*)` | See each role | -| `group` | Always `team` | `team` | - -### Minimum Tool Set (All Teammates) - -``` -SendMessage(*), TaskUpdate(*), TaskList(*), TaskGet(*), TodoWrite(*), Read(*), Bash(*), Glob(*), Grep(*) -``` - -### Role-Specific Additional Tools - -| Role Type | Additional Tools | -|-----------|-----------------| -| Read-only (reviewer, analyzer) | None extra | -| Write-capable (executor, fixer) | `Write(*), Edit(*)` | -| Agent-delegating (planner, executor) | `Task(*)` | - ---- - -## Pattern 3: Task Lifecycle - -All teammates follow the same task discovery and lifecycle pattern. - -### Standard Flow - -```javascript -// Step 1: Find my tasks -const tasks = TaskList() -const myTasks = tasks.filter(t => - t.subject.startsWith('-') && // PLAN-*, IMPL-*, TEST-*, REVIEW-* - t.owner === '' && - t.status === 'pending' && - t.blockedBy.length === 0 // Not blocked -) - -// Step 2: No tasks -> idle -if (myTasks.length === 0) return - -// Step 3: Claim task (lowest ID first) -const task = TaskGet({ taskId: myTasks[0].id }) -TaskUpdate({ taskId: task.id, status: 'in_progress' }) - -// Step 4: Execute work -// ... role-specific logic ... - -// Step 5: Complete and loop -TaskUpdate({ taskId: task.id, status: 'completed' }) - -// Step 6: Check for next task -const nextTasks = TaskList().filter(t => - t.subject.startsWith('-') && - t.owner === '' && - t.status === 'pending' && - t.blockedBy.length === 0 -) -if (nextTasks.length > 0) { - // Continue with next task -> back to Step 3 -} -``` - -### Task Prefix Convention - -| Prefix | Role | Example | -|--------|------|---------| -| `PLAN-` | planner | `PLAN-001: Explore and plan implementation` | -| `IMPL-` | executor | `IMPL-001: Implement approved plan` | -| `TEST-` | tester | `TEST-001: Test-fix cycle` | -| `REVIEW-` | tester | `REVIEW-001: Code review and requirement verification` | -| `-` | new role | Must be unique, uppercase, hyphen-suffixed | - -### Task Chain (defined in coordinate.md) - -``` -PLAN-001 → IMPL-001 → TEST-001 + REVIEW-001 - ↑ blockedBy ↑ blockedBy -``` - ---- - -## Pattern 4: Five-Phase Execution Structure - -Every team command follows a consistent 5-phase internal structure. - -### Standard Phases - -| Phase | Purpose | Common Actions | -|-------|---------|----------------| -| Phase 1: Task Discovery | Find and claim assigned tasks | TaskList, TaskGet, TaskUpdate | -| Phase 2: Context Loading | Load necessary context for work | Read plan/config, detect framework | -| Phase 3: Core Work | Execute primary responsibility | Role-specific logic | -| Phase 4: Validation/Summary | Verify work quality | Syntax check, criteria verification | -| Phase 5: Report + Loop | Report to coordinator, check next | SendMessage, TaskUpdate, TaskList | - -### Phase Structure Template - -```markdown -### Phase N: - -\`\`\`javascript -// Implementation code -\`\`\` -``` - ---- - -## Pattern 5: Complexity-Adaptive Routing - -All roles that process varying-difficulty tasks should implement adaptive routing. - -### Decision Logic - -```javascript -function assessComplexity(description) { - let score = 0 - if (/refactor|architect|restructure|module|system/.test(description)) score += 2 - if (/multiple|across|cross/.test(description)) score += 2 - if (/integrate|api|database/.test(description)) score += 1 - if (/security|performance/.test(description)) score += 1 - return score >= 4 ? 'High' : score >= 2 ? 'Medium' : 'Low' -} -``` - -### Routing Table - -| Complexity | Direct Claude | CLI Agent | Sub-agent | -|------------|---------------|-----------|-----------| -| Low | Direct execution | - | - | -| Medium | - | `cli-explore-agent` / `cli-lite-planning-agent` | - | -| High | - | CLI agent | `code-developer` / `universal-executor` | - -### Sub-agent Delegation Pattern - -```javascript -Task({ - subagent_type: "", - run_in_background: false, - description: "", - prompt: ` -## Task Objective -${taskDescription} - -## Output Location -${sessionFolder}/${outputFile} - -## MANDATORY FIRST STEPS -1. Read: .workflow/project-tech.json (if exists) -2. Read: .workflow/project-guidelines.json (if exists) - -## Expected Output -${expectedFormat} -` -}) -``` - ---- - -## Pattern 6: Coordinator Spawn Integration - -New teammates must be spawnable from coordinate.md using standard pattern. - -### Skill Path Format (Folder-Based) - -Team commands use folder-based organization with colon-separated skill paths: - -``` -File location: .claude/commands/team/{team-name}/{role-name}.md -Skill path: team:{team-name}:{role-name} - -Example: - .claude/commands/team/spec/analyst.md → team:spec:analyst - .claude/commands/team/security/scanner.md → team:security:scanner -``` - -### Spawn Template - -> **⚠️ CRITICAL**: Spawn prompt 必须包含完整的 Skill 回调指令。如果 prompt 过于简化（如仅 "Execute task X"），agent 会自行发挥而非通过 Skill → role.md 加载角色定义。 - -```javascript -Task({ - subagent_type: "general-purpose", - description: `Spawn ${roleName} worker`, // ← 必填参数 - team_name: teamName, - name: "", - prompt: `You are team "${teamName}" . - -## ⚠️ 首要指令（MUST） -你的所有工作必须通过调用 Skill 获取角色定义后执行，禁止自行发挥： -Skill(skill="team-${teamName}", args="--role=") - -When you receive -* tasks, execute via the Skill callback above. - -Current requirement: ${taskDescription} -Constraints: ${constraints} - -## Message Bus (Required) -Before each SendMessage, call mcp__ccw-tools__team_msg: -mcp__ccw-tools__team_msg({ operation: "log", team: "${teamName}", from: "", to: "coordinator", type: "", summary: "" }) - -Workflow: -1. 调用 Skill(skill="team-${teamName}", args="--role=") 获取角色定义 -2. 按 role.md 中的 5-Phase 流程执行（TaskList → 找到 -* 任务 → 执行 → 汇报） -3. team_msg log + SendMessage results to coordinator -4. TaskUpdate completed -> check next task` -}) -``` - -### Spawn Anti-Patterns（必须避免） - -| Anti-Pattern | 后果 | 正确做法 | -|-------------|------|---------| -| prompt 中缺少 `Skill(...)` 回调 | agent 自行发挥，不加载 role.md | 必须包含完整 Skill 回调指令 | -| 缺少 `description` 参数 | Task() 调用失败（必填参数） | 始终提供 `description` | -| 缺少 `team_name` 参数 | agent 不属于团队，无法收发消息 | 始终提供 `team_name` | -| 缺少 `name` 参数 | agent 无角色标识 | 始终提供 `name` | -| dispatch/monitor 中 `owner` 值不在 VALID_ROLES | Skill 路由失败 | owner 必须精确匹配 VALID_ROLES key | - ---- - -## Pattern 7: Error Handling Table - -Every command ends with a standardized error handling table. - -### Template - -```markdown -## Error Handling - -| Scenario | Resolution | -|----------|------------| -| No tasks available | Idle, wait for coordinator assignment | -| Plan/Context file not found | Notify coordinator, request location | -| Sub-agent failure | Retry once, then fallback to direct execution | -| Max iterations exceeded | Report to coordinator, suggest intervention | -| Critical issue beyond scope | SendMessage fix_required to coordinator | -``` - ---- - -## Pattern 8: Session File Structure - -Roles that produce artifacts follow standard session directory patterns. - -### Convention - -``` -.workflow/.team-/{identifier}-{YYYY-MM-DD}/ -├── -├── manifest.json (if multiple outputs) -└── .task/ (if generating task files) - ├── TASK-001.json - └── TASK-002.json -``` - ---- - -# Section B: Collaboration Patterns - -> Complete specification: [collaboration-patterns.md](collaboration-patterns.md) - -## Collaboration Pattern Quick Reference - -Every collaboration pattern has these standard elements: - -| Element | Description | -|---------|-------------| -| **Entry Condition** | When to activate this pattern | -| **Workflow** | Step-by-step execution flow | -| **Convergence Criteria** | How the pattern terminates successfully | -| **Feedback Loop** | How information flows back to enable correction | -| **Timeout/Fallback** | What happens when the pattern doesn't converge | -| **Max Iterations** | Hard limit on cycles (where applicable) | - -### Pattern Selection Guide - -| Scenario | Recommended Pattern | Why | -|----------|-------------------|-----| -| Standard feature development | CP-1: Linear Pipeline | Well-defined sequential stages | -| Code review with fixes needed | CP-2: Review-Fix Cycle | Iterative improvement until quality met | -| Multi-angle analysis needed | CP-3: Fan-out/Fan-in | Parallel exploration, aggregated results | -| Critical decision (architecture, security) | CP-4: Consensus Gate | Multiple perspectives before committing | -| Agent stuck / self-repair failed | CP-5: Escalation Chain | Progressive expertise levels | -| Large feature (many files) | CP-6: Incremental Delivery | Validated increments reduce risk | -| Blocking issue stalls pipeline | CP-7: Swarming | All resources on one problem | -| Domain-specific expertise needed | CP-8: Consulting | Expert advice without role change | -| Design + Implementation parallel | CP-9: Dual-Track | Faster delivery with sync checkpoints | -| Post-completion learning | CP-10: Post-Mortem | Capture insights for future improvement | -| Multi-issue plan + execute overlap | CP-11: Beat Pipeline | Per-item dispatch eliminates stage idle time | - ---- - -## Pattern Summary Checklist - -When designing a new team command, verify: - -### Infrastructure Patterns -- [ ] YAML front matter with `group: team` -- [ ] Message bus section with `team_msg` logging -- [ ] CLI fallback section with `ccw team` CLI examples and parameter mapping -- [ ] Role-specific message types defined -- [ ] Task lifecycle: TaskList -> TaskGet -> TaskUpdate flow -- [ ] Unique task prefix (no collision with existing PLAN/IMPL/TEST/REVIEW, scan `team/**/*.md`) -- [ ] 5-phase execution structure -- [ ] Complexity-adaptive routing (if applicable) -- [ ] Coordinator spawn template integration -- [ ] Error handling table -- [ ] SendMessage communication to coordinator only -- [ ] Session file structure (if producing artifacts) - -### Collaboration Patterns -- [ ] At least one collaboration pattern selected -- [ ] Convergence criteria defined (max iterations / quality gate / timeout) -- [ ] Feedback loop implemented (how results flow back) -- [ ] Timeout/fallback behavior specified -- [ ] Pattern-specific message types registered -- [ ] Coordinator aware of pattern (can route messages accordingly) -- [ ] If using CP-11: intermediate artifact protocol defined (file path + format) -- [ ] If using CP-11: inline conflict check implemented (no heavy subagent for dependency detection) - ---- - -## Pattern 9: Parallel Subagent Orchestration - -Roles that need to perform complex, multi-perspective work can delegate to subagents or CLI tools rather than executing everything inline. This pattern defines three delegation modes and context management rules. - -### Delegation Modes - -#### Mode A: Subagent Fan-out - -Launch multiple Task agents in parallel for independent work streams. - -```javascript -// Launch 2-4 parallel agents for different perspectives -const agents = [ - Task({ - subagent_type: "cli-explore-agent", - run_in_background: false, - description: "Explore angle 1", - prompt: `Analyze from perspective 1: ${taskDescription}` - }), - Task({ - subagent_type: "cli-explore-agent", - run_in_background: false, - description: "Explore angle 2", - prompt: `Analyze from perspective 2: ${taskDescription}` - }) -] -// Aggregate results after all complete -``` - -**When to use**: Multi-angle exploration, parallel code analysis, independent subtask execution. - -#### Mode B: CLI Fan-out - -Launch multiple `ccw cli` calls for multi-perspective analysis. - -```javascript -// Parallel CLI calls for different analysis angles -Bash(`ccw cli -p "PURPOSE: Analyze from security angle..." --tool gemini --mode analysis`, { run_in_background: true }) -Bash(`ccw cli -p "PURPOSE: Analyze from performance angle..." --tool gemini --mode analysis`, { run_in_background: true }) -// Wait for all CLI results, then synthesize -``` - -**When to use**: Multi-dimensional code review, architecture analysis, security + performance audits. - -#### Mode C: Sequential Delegation - -Delegate a single heavy task to a specialized agent. - -```javascript -Task({ - subagent_type: "code-developer", - run_in_background: false, - description: "Implement complex feature", - prompt: `## Goal\n${plan.summary}\n\n## Tasks\n${taskDetails}` -}) -``` - -**When to use**: Complex implementation, test-fix cycles, large-scope refactoring. - -### Context Management Hierarchy - -| Level | Location | Context Size | Use Case | -|-------|----------|-------------|----------| -| Small | role.md inline | < 200 lines | Simple logic, direct execution | -| Medium | commands/*.md | 200-500 lines | Structured delegation with strategy | -| Large | Subagent prompt | Unlimited | Full autonomous execution | - -**Rule**: role.md Phase 1/5 are always inline (standardized). Phases 2-4 either inline (small) or delegate to commands (medium/large). - -### Command File Extraction Criteria - -Extract a phase into a command file when ANY of these conditions are met: - -1. **Subagent delegation**: Phase launches Task() agents -2. **CLI fan-out**: Phase runs parallel `ccw cli` calls -3. **Complex strategy**: Phase has >3 conditional branches -4. **Reusable logic**: Same logic used by multiple roles - -If none apply, keep the phase inline in role.md. - -### Relationship to Other Patterns - -- **Pattern 5 (Complexity-Adaptive)**: Pattern 9 provides the delegation mechanisms that Pattern 5 routes to. Low complexity → inline, Medium → CLI agent, High → Subagent fan-out. -- **CP-3 (Parallel Fan-out)**: Pattern 9 Mode A/B are the implementation mechanisms for CP-3 at the role level. -- **Pattern 4 (Five-Phase)**: Pattern 9 does NOT replace the 5-phase structure. It provides delegation options WITHIN phases 2-4. - -### Checklist - -- [ ] Delegation mode selected based on task characteristics -- [ ] Context management level appropriate (small/medium/large) -- [ ] Command files extracted only when criteria met -- [ ] Subagent prompts include mandatory first steps (read project config) -- [ ] CLI fan-out uses `--mode analysis` by default -- [ ] Results aggregated after parallel completion -- [ ] Error handling covers agent/CLI failure with fallback diff --git a/.claude/skills_lib/team-skill-designer-v2/templates/role-command-template.md b/.claude/skills_lib/team-skill-designer-v2/templates/role-command-template.md deleted file mode 100644 index 6dcba3b9..00000000 --- a/.claude/skills_lib/team-skill-designer-v2/templates/role-command-template.md +++ /dev/null @@ -1,820 +0,0 @@ -# Role Command Template - -Template for generating command files in `roles//commands/.md` (v3 style). - -## Purpose - -| Phase | Usage | -|-------|-------| -| Phase 0 | Read to understand command file structure | -| Phase 3 | Apply with role-specific content | - -## Style Rules - -Generated output follows v3 conventions: - -| Rule | Description | -|------|-------------| -| No JS pseudocode | All logic uses text + decision tables + flow symbols | -| Code blocks = tool calls only | Only Task(), Bash(), Read(), Grep() etc. | -| `` in output | Not `${variable}` in generated content | -| Decision tables | Strategy selection, error routing all use tables | -| Self-contained | Each command executable independently | - -> **Note**: The template itself uses `{{handlebars}}` for variable substitution during Phase 3 generation. The **generated output** must not contain `{{handlebars}}` or JS pseudocode. - ---- - -## Template - -```markdown -# Command: {{command_name}} - -## Purpose - -{{command_description}} - -## Phase 2: Context Loading - -| Input | Source | Required | -|-------|--------|----------| -{{#each context_inputs}} -| {{this.name}} | {{this.source}} | {{this.required}} | -{{/each}} - -## Phase 3: Core Work - -{{core_work_content}} - -## Phase 4: Validation - -{{validation_content}} - -## Error Handling - -| Scenario | Resolution | -|----------|------------| -{{#each error_handlers}} -| {{this.scenario}} | {{this.resolution}} | -{{/each}} -``` - ---- - -## 7 Pre-built Command Patterns - -Each pattern below provides the complete v3-style structure. During Phase 3 generation, select the matching pattern and customize with team-specific content. - -### 1. explore.md (Multi-angle Exploration) - -**Maps to**: Orchestration roles, Phase 2 -**Delegation**: Subagent Fan-out - -```markdown -# Command: explore - -## Purpose - -Multi-angle codebase exploration using parallel exploration agents. Discovers patterns, dependencies, and architecture before planning. - -## Phase 2: Context Loading - -| Input | Source | Required | -|-------|--------|----------| -| Task description | TaskGet result | Yes | -| Project root | `git rev-parse --show-toplevel` | Yes | -| Existing explorations | /explorations/ | No | -| Wisdom | /wisdom/ | No | - -## Phase 3: Core Work - -### Angle Selection - -Determine exploration angles from task description: - -| Signal in Description | Angle | -|-----------------------|-------| -| architect, structure, design | architecture | -| pattern, convention, style | patterns | -| depend, import, module | dependencies | -| test, spec, coverage | testing | -| No signals matched | general + patterns (default) | - -### Execution Strategy - -| Angle Count | Strategy | -|-------------|----------| -| 1 angle | Single agent exploration | -| 2-4 angles | Parallel agents, one per angle | - -**Per-angle agent spawn**: - -\`\`\` -Task({ - subagent_type: "cli-explore-agent", - run_in_background: false, - description: "Explore: ", - prompt: "Explore the codebase from the perspective of . -Focus on: -Project root: - -Report findings as structured markdown with file references." -}) -\`\`\` - -### Result Aggregation - -After all agents complete: - -1. Merge key findings across all angles (deduplicate) -2. Collect relevant file paths (deduplicate) -3. Extract discovered patterns -4. Write aggregated results to `/explorations/.md` - -### Output Format - -\`\`\` -## Exploration Results - -### Angles Explored: [list] - -### Key Findings -- [finding with file:line reference] - -### Relevant Files -- [file path with relevance note] - -### Patterns Found -- [pattern name: description] -\`\`\` - -## Phase 4: Validation - -| Check | Method | Pass Criteria | -|-------|--------|---------------| -| All angles covered | Compare planned vs completed | All planned angles explored | -| Findings non-empty | Check result count | At least 1 finding per angle | -| File references valid | Verify referenced files exist | >= 80% files exist | - -## Error Handling - -| Scenario | Resolution | -|----------|------------| -| Agent returns no results | Retry with broader search scope | -| Agent timeout | Use partial results, note incomplete angles | -| Project root not found | Fall back to current directory | -| Exploration cache exists | Load cached, skip re-exploration | -``` - -### 2. analyze.md (Multi-perspective Analysis) - -**Maps to**: Read-only analysis roles, Phase 3 -**Delegation**: CLI Fan-out - -```markdown -# Command: analyze - -## Purpose - -Multi-perspective code analysis using parallel CLI calls. Each perspective produces severity-ranked findings with file:line references. - -## Phase 2: Context Loading - -| Input | Source | Required | -|-------|--------|----------| -| Target files | `git diff --name-only HEAD~1` or `--cached` | Yes | -| Plan file | /plan/plan.json | No | -| Wisdom | /wisdom/ | No | - -**File discovery**: - -\`\`\` -Bash("git diff --name-only HEAD~1 2>/dev/null || git diff --name-only --cached") -\`\`\` - -## Phase 3: Core Work - -### Perspective Selection - -Determine analysis perspectives from task description: - -| Signal in Description | Perspective | -|-----------------------|-------------| -| security, auth, inject, xss | security | -| performance, speed, optimize, memory | performance | -| quality, clean, maintain, debt | code-quality | -| architect, pattern, structure | architecture | -| No signals matched | code-quality + architecture (default) | - -### Execution Strategy - -| Perspective Count | Strategy | -|-------------------|----------| -| 1 perspective | Single CLI call | -| 2-4 perspectives | Parallel CLI calls, one per perspective | - -**Per-perspective CLI call**: - -\`\`\` -Bash("ccw cli -p \"PURPOSE: Analyze code from perspective -TASK: Review changes in: -MODE: analysis -CONTEXT: @ -EXPECTED: Findings with severity, file:line references, remediation -CONSTRAINTS: Focus on \" --tool gemini --mode analysis", { run_in_background: true }) -\`\`\` - -### Finding Aggregation - -After all perspectives complete: - -1. Parse findings from each CLI response -2. Classify by severity: Critical / High / Medium / Low -3. Deduplicate across perspectives -4. Sort by severity then by file location - -### Output Format - -\`\`\` -## Analysis Results - -### Perspectives Analyzed: [list] - -### Findings by Severity -#### Critical -- [finding with file:line] -#### High -- [finding] -#### Medium -- [finding] -#### Low -- [finding] -\`\`\` - -## Phase 4: Validation - -| Check | Method | Pass Criteria | -|-------|--------|---------------| -| All perspectives covered | Compare planned vs completed | All perspectives analyzed | -| Findings have file refs | Check file:line format | >= 90% findings have references | -| No duplicate findings | Dedup check | No identical findings | - -## Error Handling - -| Scenario | Resolution | -|----------|------------| -| CLI tool unavailable | Fall back to secondary tool | -| CLI returns empty | Retry with broader scope | -| Too many findings | Prioritize critical/high, summarize medium/low | -| Target files empty | Report no changes to analyze | -``` - -### 3. implement.md (Code Implementation) - -**Maps to**: Code generation roles, Phase 3 -**Delegation**: Sequential Delegation - -```markdown -# Command: implement - -## Purpose - -Code implementation via subagent delegation with batch routing. Reads plan tasks and executes code changes, grouping by module for efficiency. - -## Phase 2: Context Loading - -| Input | Source | Required | -|-------|--------|----------| -| Plan file | /plan/plan.json | Yes | -| Task files | /plan/.task/.json | Yes | -| Wisdom conventions | /wisdom/conventions.md | No | - -**Loading steps**: - -1. Extract plan path from task description -2. Read plan.json -> get task list -3. Read each task file for detailed specs -4. Load coding conventions from wisdom - -## Phase 3: Core Work - -### Strategy Selection - -| Task Count | Strategy | Description | -|------------|----------|-------------| -| <= 2 | Direct | Inline Edit/Write by this role | -| 3-5 | Single agent | One code-developer subagent for all tasks | -| > 5 | Batch agent | Group by module, one agent per batch | - -### Direct Strategy (1-2 tasks) - -For each task, for each file in task spec: -1. Read existing file (if modifying) -2. Apply changes via Edit or Write -3. Verify file saved - -### Agent Strategy (3+ tasks) - -**Single agent spawn**: - -\`\`\` -Task({ - subagent_type: "code-developer", - run_in_background: false, - description: "Implement tasks", - prompt: "## Goal - - -## Tasks - - -Complete each task according to its convergence criteria." -}) -\`\`\` - -**Batch agent** (> 5 tasks): Group tasks by module/directory, spawn one agent per batch using the template above. - -### Output Tracking - -After implementation: -1. Get list of changed files: `Bash("git diff --name-only")` -2. Count completed vs total tasks -3. Record changed file paths for validation phase - -## Phase 4: Validation - -| Check | Method | Pass Criteria | -|-------|--------|---------------| -| Syntax clean | Language-specific check (tsc, python -c, etc.) | No syntax errors | -| All files created | Verify plan-specified files exist | All files present | -| Import resolution | Check for broken imports | All imports resolve | - -**Auto-fix on failure** (max 2 attempts): - -| Attempt | Action | -|---------|--------| -| 1 | Parse error, apply targeted fix | -| 2 | Delegate fix to code-developer subagent | -| Failed | Report remaining issues to coordinator | - -## Error Handling - -| Scenario | Resolution | -|----------|------------| -| Plan file not found | Notify coordinator, request plan path | -| Agent fails on task | Retry once, then mark task as blocked | -| Syntax errors after impl | Attempt auto-fix, report if unresolved | -| File conflict | Check git status, resolve or report | -``` - -### 4. validate.md (Test-Fix Cycle) - -**Maps to**: Validation roles, Phase 3 -**Delegation**: Sequential Delegation - -```markdown -# Command: validate - -## Purpose - -Iterative test-fix cycle with max iteration control. Runs tests, identifies failures, delegates fixes, and re-validates until passing or max iterations reached. - -## Phase 2: Context Loading - -| Input | Source | Required | -|-------|--------|----------| -| Test command | Auto-detect from project config | Yes | -| Changed files | `git diff --name-only` | Yes | -| Plan file | /plan/plan.json | No | - -**Test command detection**: - -| Detection Signal | Test Command | -|-----------------|--------------| -| package.json has "test" script | `npm test` | -| pytest.ini or conftest.py exists | `pytest` | -| Makefile has "test" target | `make test` | -| go.mod exists | `go test ./...` | -| No signal detected | Notify coordinator | - -## Phase 3: Core Work - -### Test-Fix Cycle - -| Step | Action | Exit Condition | -|------|--------|----------------| -| 1. Run tests | `Bash(" 2>&1 || true")` | - | -| 2. Parse results | Extract pass/fail counts | - | -| 3. Check pass rate | Compare against threshold | Pass rate >= 95% -> exit SUCCESS | -| 4. Extract failures | Parse failing test names and errors | - | -| 5. Delegate fix | Spawn code-developer subagent | - | -| 6. Increment counter | iteration++ | iteration >= 5 -> exit MAX_REACHED | -| 7. Loop | Go to Step 1 | - | - -**Fix delegation**: - -\`\`\` -Task({ - subagent_type: "code-developer", - run_in_background: false, - description: "Fix test failures (iteration )", - prompt: "Test failures: - - -Fix the failing tests. Changed files: " -}) -\`\`\` - -### Outcome Routing - -| Outcome | Action | -|---------|--------| -| SUCCESS (pass rate >= 95%) | Proceed to Phase 4 | -| MAX_REACHED (5 iterations) | Report failures, mark for manual intervention | -| ENV_ERROR (test env broken) | Report environment issue to coordinator | - -## Phase 4: Validation - -| Metric | Source | Threshold | -|--------|--------|-----------| -| Pass rate | Final test run | >= 95% | -| Iterations used | Counter | Report count | -| Remaining failures | Last test output | List details | - -## Error Handling - -| Scenario | Resolution | -|----------|------------| -| No test command found | Notify coordinator | -| Max iterations exceeded | Report failures, suggest manual intervention | -| Test environment broken | Report environment issue | -| Flaky tests detected | Re-run once to confirm, exclude if consistently flaky | -``` - -### 5. review.md (Multi-dimensional Review) - -**Maps to**: Read-only analysis roles (reviewer type), Phase 3 -**Delegation**: CLI Fan-out - -```markdown -# Command: review - -## Purpose - -Multi-dimensional code review producing a verdict (BLOCK/CONDITIONAL/APPROVE) with categorized findings across quality, security, architecture, and requirements dimensions. - -## Phase 2: Context Loading - -| Input | Source | Required | -|-------|--------|----------| -| Plan file | /plan/plan.json | Yes | -| Git diff | `git diff HEAD~1` or `git diff --cached` | Yes | -| Modified files | From git diff --name-only | Yes | -| Test results | Tester output (if available) | No | -| Wisdom | /wisdom/ | No | - -## Phase 3: Core Work - -### Dimension Overview - -| Dimension | Focus | What to Detect | -|-----------|-------|----------------| -| Quality | Code correctness, type safety, clean code | Empty catch, ts-ignore, any type, console.log | -| Security | Vulnerability patterns, secret exposure | Hardcoded secrets, SQL injection, eval, XSS | -| Architecture | Module structure, coupling, file size | Circular deps, deep imports, large files | -| Requirements | Acceptance criteria coverage | Unmet criteria, missing error handling, missing tests | - -### Per-Dimension Detection - -For each dimension, scan modified files using pattern detection: - -**Example: Quality scan for console statements**: - -\`\`\` -Grep(pattern="console\\.(log|debug|info)", path="", output_mode="content", "-n"=true) -\`\`\` - -**Example: Architecture scan for deep imports**: - -\`\`\` -Grep(pattern="from\\s+['\"](\\.\\./){3,}", path="", output_mode="content", "-n"=true) -\`\`\` - -### Requirements Verification - -1. Read plan file -> extract acceptance criteria section -2. For each criterion -> extract keywords (4+ char meaningful words) -3. Search modified files for keyword matches -4. Score coverage: - -| Match Rate | Status | -|------------|--------| -| >= 70% | Met | -| 40-69% | Partial | -| < 40% | Unmet | - -### Verdict Routing - -| Verdict | Criteria | Action | -|---------|----------|--------| -| BLOCK | Any critical-severity issues found | Must fix before merge | -| CONDITIONAL | High or medium issues, no critical | Should address, can merge with tracking | -| APPROVE | Only low issues or none | Ready to merge | - -### Report Format - -\`\`\` -# Code Review Report - -**Verdict**: - -## Blocking Issues (if BLOCK) -- **** (:): - -## Review Dimensions - -### Quality Issues -**CRITICAL** () -- (:) - -### Security Issues -(same format per severity) - -### Architecture Issues -(same format per severity) - -### Requirements Issues -(same format per severity) - -## Recommendations -1. -\`\`\` - -## Phase 4: Validation - -| Field | Description | -|-------|-------------| -| Total issues | Sum across all dimensions and severities | -| Critical count | Must be 0 for APPROVE | -| Blocking issues | Listed explicitly in report header | -| Dimensions covered | Must be 4/4 | - -## Error Handling - -| Scenario | Resolution | -|----------|------------| -| Plan file not found | Skip requirements dimension, note in report | -| Git diff empty | Report no changes to review | -| File read fails | Skip file, note in report | -| No modified files | Report empty review | -| Codex unavailable | Skip codex review dimension, report 3-dimension review | -``` - -### 6. dispatch.md (Task Distribution) - -**Maps to**: Coordinator role, Phase 3 -**Delegation**: Direct (coordinator acts directly) - -```markdown -# Command: dispatch - -## Purpose - -Task chain creation with dependency management. Creates all pipeline tasks with correct blockedBy relationships and role-based ownership. - -## Phase 2: Context Loading - -| Input | Source | Required | -|-------|--------|----------| -| Pipeline definition | SKILL.md Pipeline Definitions | Yes | -| Task metadata | SKILL.md Task Metadata Registry | Yes | -| Session folder | From Phase 2 initialization | Yes | -| Mode | From Phase 1 requirements | Yes | - -## Phase 3: Core Work - -### Pipeline Selection - -Select pipeline based on mode: - -| Mode | Pipeline | Task Count | -|------|----------|------------| -{{#each pipeline_modes}} -| {{this.mode}} | {{this.pipeline}} | {{this.task_count}} | -{{/each}} - -### Task Creation Flow - -For each task in the selected pipeline (in dependency order): - -1. **Create task**: - -\`\`\` -TaskCreate({ - subject: ": ", - description: "\n\nSession: ", - activeForm: " in progress" -}) -\`\`\` - -2. **Set owner and dependencies**: - -\`\`\` -TaskUpdate({ - taskId: , - owner: "", - addBlockedBy: [] -}) -\`\`\` - -3. Record created task ID for downstream dependency references - -### Dependency Mapping - -Follow SKILL.md Task Metadata Registry for: -- Task ID naming convention -- Role assignment (owner field) -- Dependencies (blockedBy relationships) -- Task description with session folder reference - -### Parallel Task Handling - -| Condition | Action | -|-----------|--------| -| Tasks share same blockedBy and no mutual dependency | Create both, they run in parallel | -| N parallel tasks for same role | Use instance-specific owner: `-1`, `-2` | - -## Phase 4: Validation - -| Check | Method | Pass Criteria | -|-------|--------|---------------| -| All tasks created | Compare pipeline spec vs TaskList | Count matches | -| Dependencies correct | Verify blockedBy for each task | All deps point to valid tasks | -| Owners assigned | Check owner field | Every task has valid role owner | -| No orphan tasks | Verify all tasks reachable from pipeline start | No disconnected tasks | - -## Error Handling - -| Scenario | Resolution | -|----------|------------| -| Task creation fails | Retry, then report to user | -| Dependency cycle detected | Flatten dependencies, warn | -| Role not spawned yet | Queue task, spawn role first | -| Task prefix conflict | Log warning, proceed | -``` - -### 7. monitor.md (Message-Driven Coordination) - -**Maps to**: Coordinator role, Phase 4 -**Delegation**: Message-Driven (no polling) - -```markdown -# Command: monitor - -## Purpose - -Message-driven coordination. Team members (spawned in Phase 2) execute tasks autonomously and report via SendMessage. Coordinator receives messages and routes next actions. - -## Phase 2: Context Loading - -| Input | Source | Required | -|-------|--------|----------| -| Pipeline state | TaskList() | Yes | -| Session file | /team-session.json | Yes | -| Team config | Team member list | Yes | - -## Phase 3: Core Work - -### Design Principles - -| Principle | Description | -|-----------|-------------| -| No re-spawning | Team members already spawned in Phase 2 -- do NOT spawn again here | -| No polling loops | No `while` + `sleep` + status check (wastes API turns) | -| Event-driven | Worker SendMessage is the trigger signal | -| One beat per wake | Coordinator processes one event then STOPs | - -### Entry Handlers - -When coordinator wakes, route based on Entry Router detection: - -| Handler | Trigger | Actions | -|---------|---------|---------| -| handleCallback | Worker `[role-name]` message received | 1. Log received message 2. Check task status 3. Route to next action | -| handleCheck | User says "check"/"status" | 1. Load TaskList 2. Output status graph 3. STOP (no advancement) | -| handleResume | User says "resume"/"continue" | 1. Load TaskList 2. Find ready tasks 3. Spawn/notify workers 4. STOP | - -### handleCallback Flow - -1. Identify sender role from message tag `[role-name]` -2. Log received message via team_msg -3. Load TaskList for current state -4. Route based on message content: - -| Message Content | Action | -|-----------------|--------| -| Contains "fix_required" or "error" | Assess severity -> escalate to user if critical | -| Normal completion | Check pipeline progress (see below) | - -5. Check pipeline progress: - -| State | Condition | Action | -|-------|-----------|--------| -| All done | completed count >= total pipeline tasks | -> Phase 5 | -| Tasks unblocked | pending tasks with empty blockedBy | Notify/spawn workers for unblocked tasks | -| Checkpoint | Pipeline at spec->impl transition | Pause, ask user to `resume` | -| Stalled | No ready + no running + has pending | Report blocking point | - -6. Output status summary -> STOP - -### handleCheck Flow (Status Only) - -1. Load all tasks via TaskList -2. Build status overview: - -\`\`\` -Pipeline Status: - Completed: / - In Progress: - Pending: - Blocked: -\`\`\` - -3. STOP (no pipeline advancement) - -### handleResume Flow - -1. Load TaskList -2. Find tasks with: status=pending, blockedBy all resolved -3. For each ready task: - -| Condition | Action | -|-----------|--------| -| Worker already spawned and idle | SendMessage to worker: "Task unblocked, please proceed" | -| Worker not spawned | Spawn worker using SKILL.md Spawn Template | - -4. Output status summary -> STOP - -### Status Graph Format - -\`\`\` -Pipeline Progress: / - - [DONE] TASK-001 (role) - description - [DONE] TASK-002 (role) - description - [>> ] TASK-003 (role) - description <- in_progress - [ ] TASK-004 (role) - description <- blocked by TASK-003 - ... -\`\`\` - -## Phase 4: Validation - -| Check | Method | Pass Criteria | -|-------|--------|---------------| -| Message routed | Verify handler executed | Handler completed without error | -| State consistent | TaskList reflects actions taken | Tasks updated correctly | -| No orphan workers | All spawned workers have assigned tasks | No idle workers without tasks | - -## Error Handling - -| Scenario | Resolution | -|----------|------------| -| Teammate reports error | Assess severity -> retry SendMessage or escalate to user | -| Task stuck (no callback) | Send follow-up to teammate, 2x -> suggest respawn | -| Critical issue beyond scope | AskUserQuestion: retry/skip/terminate | -| Session file corrupted | Rebuild state from TaskList | -``` - ---- - -## Variable Reference - -| Variable | Source | Description | -|----------|--------|-------------| -| `{{command_name}}` | Command identifier | e.g., "explore", "analyze" | -| `{{command_description}}` | One-line description | What this command does | -| `{{context_inputs}}` | Array of {name, source, required} | Context loading table rows | -| `{{core_work_content}}` | Generated from pattern | Phase 3 content | -| `{{validation_content}}` | Generated from pattern | Phase 4 content | -| `{{error_handlers}}` | Array of {scenario, resolution} | Error handling table rows | -| `{{pipeline_modes}}` | config.pipeline_modes | Array of {mode, pipeline, task_count} for dispatch | - -## Self-Containment Rules - -1. **No cross-command references**: Each command.md must be executable independently -2. **Include all context inputs**: List all required context (files, configs) in Phase 2 -3. **Complete error handling**: Every command handles its own failures -4. **Explicit output format**: Define what the command produces -5. **Strategy in decision tables**: All routing logic in tables, not code - -## Key Differences from v1 - -| Aspect | v1 (old) | v2 (this template) | -|--------|----------|---------------------| -| Strategy logic | JS `if/else` + regex matching | Decision tables | -| Execution steps | JS code blocks (pseudocode) | Step lists + actual tool call templates | -| Result processing | JS object construction | Text aggregation description | -| Output format | Embedded in JS template literals | Standalone markdown format block | -| Error handling | JS try/catch with fallbacks | Decision table with clear routing | -| Context prep | JS variable assignments | Phase 2 table + loading steps | -| Monitor design | JS while loop + polling | Event-driven handlers + STOP pattern | diff --git a/.claude/skills_lib/team-skill-designer-v2/templates/role-template.md b/.claude/skills_lib/team-skill-designer-v2/templates/role-template.md deleted file mode 100644 index ad353272..00000000 --- a/.claude/skills_lib/team-skill-designer-v2/templates/role-template.md +++ /dev/null @@ -1,586 +0,0 @@ -# Role File Template - -Template for generating per-role execution detail files in `roles//role.md` (v3 style). - -## Purpose - -| Phase | Usage | -|-------|-------| -| Phase 0 | Read to understand role file structure | -| Phase 3 | Apply with role-specific content | - -## Style Rules - -Generated output follows v3 conventions: - -| Rule | Description | -|------|-------------| -| Phase 1/5 shared | Reference "See SKILL.md Shared Infrastructure" instead of inline code | -| No JS pseudocode | Message Bus, Task Lifecycle all use text + tool call templates | -| Decision tables | All branching logic uses `| Condition | Action |` tables | -| Code blocks = tool calls only | Only actual executable calls (Read(), TaskList(), SendMessage(), etc.) | -| `` in output | Not `${variable}` in generated content | -| Phase 2-4 only | Role files define Phase 2-4 role-specific logic | - -> **Note**: The template itself uses `{{handlebars}}` for variable substitution during Phase 3 generation. The **generated output** must not contain `{{handlebars}}` or JS pseudocode. - ---- - -## Template - -### Worker Role Template - -```markdown -# {{display_name}} Role - -{{role_description}} - -## Identity - -- **Name**: `{{role_name}}` | **Tag**: `[{{role_name}}]` -- **Task Prefix**: `{{task_prefix}}-*` -- **Responsibility**: {{responsibility_type}} - -## Boundaries - -### MUST -- Only process `{{task_prefix}}-*` prefixed tasks -- All output (SendMessage, team_msg, logs) must carry `[{{role_name}}]` identifier -- Only communicate with coordinator via SendMessage -- Work strictly within {{responsibility_type}} responsibility scope -{{#each must_rules}} -- {{this}} -{{/each}} - -### MUST NOT -- Execute work outside this role's responsibility scope -- Communicate directly with other worker roles (must go through coordinator) -- Create tasks for other roles (TaskCreate is coordinator-exclusive) -- Modify files or resources outside this role's responsibility -- Omit `[{{role_name}}]` identifier in any output -{{#each must_not_rules}} -- {{this}} -{{/each}} - ---- - -## Toolbox - -### Available Commands - -| Command | File | Phase | Description | -|---------|------|-------|-------------| -{{#each commands}} -| `{{this.name}}` | [commands/{{this.name}}.md](commands/{{this.name}}.md) | Phase {{this.phase}} | {{this.description}} | -{{/each}} - -{{#if has_no_commands}} -> No command files -- all phases execute inline. -{{/if}} - -### Tool Capabilities - -| Tool | Type | Used By | Purpose | -|------|------|---------|---------| -{{#each tool_capabilities}} -| `{{this.tool}}` | {{this.type}} | {{this.used_by}} | {{this.purpose}} | -{{/each}} - ---- - -## Message Types - -| Type | Direction | Trigger | Description | -|------|-----------|---------|-------------| -{{#each message_types}} -| `{{this.type}}` | {{this.direction}} | {{this.trigger}} | {{this.description}} | -{{/each}} - -## Message Bus - -Before every SendMessage, log via `mcp__ccw-tools__team_msg`: - -\`\`\` -mcp__ccw-tools__team_msg({ - operation: "log", - team: , - from: "{{role_name}}", - to: "coordinator", - type: , - summary: "[{{role_name}}] complete: ", - ref: -}) -\`\`\` - -**CLI fallback** (when MCP unavailable): - -\`\`\` -Bash("ccw team log --team --from {{role_name}} --to coordinator --type --summary \"[{{role_name}}] complete\" --ref --json") -\`\`\` - ---- - -## Execution (5-Phase) - -### Phase 1: Task Discovery - -> See SKILL.md Shared Infrastructure -> Worker Phase 1: Task Discovery - -Standard task discovery flow: TaskList -> filter by prefix `{{task_prefix}}-*` + owner match + pending + unblocked -> TaskGet -> TaskUpdate in_progress. - -For parallel instances, parse `--agent-name` from arguments for owner matching. Falls back to `{{role_name}}` for single-instance roles. - -### Phase 2: {{phase2_name}} - -{{phase2_content}} - -### Phase 3: {{phase3_name}} - -{{phase3_content}} - -### Phase 4: {{phase4_name}} - -{{phase4_content}} - -### Phase 5: Report to Coordinator - -> See SKILL.md Shared Infrastructure -> Worker Phase 5: Report - -Standard report flow: team_msg log -> SendMessage with `[{{role_name}}]` prefix -> TaskUpdate completed -> Loop to Phase 1 for next task. - ---- - -## Error Handling - -| Scenario | Resolution | -|----------|------------| -| No {{task_prefix}}-* tasks available | Idle, wait for coordinator assignment | -| Context/Plan file not found | Notify coordinator, request location | -{{#if has_commands}} -| Command file not found | Fall back to inline execution | -{{/if}} -{{#each additional_error_handlers}} -| {{this.scenario}} | {{this.resolution}} | -{{/each}} -| Critical issue beyond scope | SendMessage fix_required to coordinator | -| Unexpected error | Log error via team_msg, report to coordinator | -``` - ---- - -### Coordinator Role Template - -The coordinator role is special and always generated. Its template differs from worker roles: - -```markdown -# Coordinator Role - -Orchestrate the {{team_display_name}} workflow: team creation, task dispatching, progress monitoring, session state. - -## Identity - -- **Name**: `coordinator` | **Tag**: `[coordinator]` -- **Responsibility**: Parse requirements -> Create team -> Dispatch tasks -> Monitor progress -> Report results - -## Boundaries - -### MUST -- Parse user requirements and clarify ambiguous inputs via AskUserQuestion -- Create team and spawn worker subagents in background -- Dispatch tasks with proper dependency chains (see SKILL.md Task Metadata Registry) -- Monitor progress via worker callbacks and route messages -- Maintain session state persistence -{{#each coordinator_must_rules}} -- {{this}} -{{/each}} - -### MUST NOT -- Execute {{team_purpose}} work directly (delegate to workers) -- Modify task outputs (workers own their deliverables) -- Call implementation subagents directly -- Skip dependency validation when creating task chains -{{#each coordinator_must_not_rules}} -- {{this}} -{{/each}} - -> **Core principle**: coordinator is the orchestrator, not the executor. All actual work must be delegated to worker roles via TaskCreate. - ---- - -## Entry Router - -When coordinator is invoked, first detect the invocation type: - -| Detection | Condition | Handler | -|-----------|-----------|---------| -| Worker callback | Message contains `[role-name]` tag from a known worker role | -> handleCallback: auto-advance pipeline | -| Status check | Arguments contain "check" or "status" | -> handleCheck: output execution graph, no advancement | -| Manual resume | Arguments contain "resume" or "continue" | -> handleResume: check worker states, advance pipeline | -| New session | None of the above | -> Phase 0 (Session Resume Check) | - -For callback/check/resume: load `commands/monitor.md` and execute the appropriate handler, then STOP. - ---- - -## Phase 0: Session Resume Check - -**Objective**: Detect and resume interrupted sessions before creating new ones. - -**Workflow**: -1. Scan session directory for sessions with status "active" or "paused" -2. No sessions found -> proceed to Phase 1 -3. Single session found -> resume it (-> Session Reconciliation) -4. Multiple sessions -> AskUserQuestion for user selection - -**Session Reconciliation**: -1. Audit TaskList -> get real status of all tasks -2. Reconcile: session state <-> TaskList status (bidirectional sync) -3. Reset any in_progress tasks -> pending (they were interrupted) -4. Determine remaining pipeline from reconciled state -5. Rebuild team if disbanded (TeamCreate + spawn needed workers only) -6. Create missing tasks with correct blockedBy dependencies -7. Verify dependency chain integrity -8. Update session file with reconciled state -9. Kick first executable task's worker -> Phase 4 - ---- - -## Phase 1: Requirement Clarification - -**Objective**: Parse user input and gather execution parameters. - -**Workflow**: - -1. **Parse arguments** for explicit settings: mode, scope, focus areas -2. **Ask for missing parameters** via AskUserQuestion: - -{{phase1_questions}} - -3. **Store requirements**: mode, scope, focus, constraints - -**Success**: All parameters captured, mode finalized. - ---- - -## Phase 2: Create Team + Initialize Session - -**Objective**: Initialize team, session file, and wisdom directory. - -**Workflow**: -1. Generate session ID -2. Create session folder -3. Call TeamCreate with team name -4. Initialize wisdom directory (learnings.md, decisions.md, conventions.md, issues.md) -5. Write session file with: session_id, mode, scope, status="active" -6. Spawn worker roles (see SKILL.md Coordinator Spawn Template) - -**Success**: Team created, session file written, wisdom initialized, workers spawned. - ---- - -## Phase 3: Create Task Chain - -**Objective**: Dispatch tasks based on mode with proper dependencies. - -{{#if has_dispatch_command}} -Delegate to `commands/dispatch.md` which creates the full task chain: -1. Reads SKILL.md Task Metadata Registry for task definitions -2. Creates tasks via TaskCreate with correct blockedBy -3. Assigns owner based on role mapping -4. Includes `Session: ` in every task description -{{else}} -{{phase3_dispatch_content}} -{{/if}} - ---- - -## Phase 4: Spawn-and-Stop - -**Objective**: Spawn first batch of ready workers in background, then STOP. - -**Design**: Spawn-and-Stop + Callback pattern. -- Spawn workers with `Task(run_in_background: true)` -> immediately return -- Worker completes -> SendMessage callback -> auto-advance -- User can use "check" / "resume" to manually advance -- Coordinator does one operation per invocation, then STOPS - -**Workflow**: -{{#if has_monitor_command}} -1. Load `commands/monitor.md` -{{/if}} -2. Find tasks with: status=pending, blockedBy all resolved, owner assigned -3. For each ready task -> spawn worker (see SKILL.md Spawn Template) -4. Output status summary -5. STOP - -**Pipeline advancement** driven by three wake sources: -- Worker callback (automatic) -> Entry Router -> handleCallback -- User "check" -> handleCheck (status only) -- User "resume" -> handleResume (advance) - ---- - -## Phase 5: Report + Next Steps - -**Objective**: Completion report and follow-up options. - -**Workflow**: -1. Load session state -> count completed tasks, duration -2. List deliverables with output paths -3. Update session status -> "completed" -4. Offer next steps to user - ---- - -## Error Handling - -| Error | Resolution | -|-------|------------| -| Task timeout | Log, mark failed, ask user to retry or skip | -| Worker crash | Respawn worker, reassign task | -| Dependency cycle | Detect, report to user, halt | -| Invalid mode | Reject with error, ask to clarify | -| Session corruption | Attempt recovery, fallback to manual reconciliation | -{{#each coordinator_error_handlers}} -| {{this.error}} | {{this.resolution}} | -{{/each}} -``` - ---- - -## Phase 2-4 Content by Responsibility Type - -The following sections provide Phase 2-4 content templates based on `responsibility_type`. During Phase 3 generation, select the matching section and fill into `{{phase2_content}}`, `{{phase3_content}}`, `{{phase4_content}}`. - -### Read-only Analysis - -**Phase 2: Context Loading** - -``` -| Input | Source | Required | -|-------|--------|----------| -| Plan file | /plan/plan.json | Yes | -| Git diff | `git diff HEAD~1` or `git diff --cached` | Yes | -| Modified files | From git diff --name-only | Yes | -| Wisdom | /wisdom/ | No | - -**Loading steps**: - -1. Extract session path from task description -2. Read plan file for criteria reference -3. Get changed files list - -\`\`\` -Bash("git diff --name-only HEAD~1 2>/dev/null || git diff --name-only --cached") -\`\`\` - -4. Read file contents for analysis (limit to 20 files) -5. Load wisdom files if available -``` - -**Phase 3: Analysis Execution** - -``` -Delegate to `commands/.md` if available, otherwise execute inline. - -Analysis strategy selection: - -| Condition | Strategy | -|-----------|----------| -| Single dimension analysis | Direct inline scan | -| Multi-dimension analysis | Per-dimension sequential scan | -| Deep analysis needed | CLI Fan-out to external tool | - -For each dimension, scan modified files for patterns. Record findings with severity levels. -``` - -**Phase 4: Finding Summary** - -``` -Classify findings by severity: - -| Severity | Criteria | -|----------|----------| -| Critical | Must fix before merge | -| High | Should fix, may merge with tracking | -| Medium | Recommended improvement | -| Low | Informational, optional | - -Generate structured report with file:line references and remediation suggestions. -``` - -### Code Generation - -**Phase 2: Task & Plan Loading** - -``` -**Loading steps**: - -1. Extract session path from task description -2. Read plan file -> extract task list and acceptance criteria -3. Read individual task files from `.task/` directory -4. Load wisdom files for conventions and patterns - -Fail-safe: If plan file not found -> SendMessage to coordinator requesting location. -``` - -**Phase 3: Code Implementation** - -``` -Implementation strategy selection: - -| Task Count | Complexity | Strategy | -|------------|------------|----------| -| <= 2 tasks | Low | Direct: inline Edit/Write | -| 3-5 tasks | Medium | Single agent: one code-developer for all | -| > 5 tasks | High | Batch agent: group by module, one agent per batch | - -{{#if phase3_command}} -Delegate to `commands/{{phase3_command}}.md`. -{{else}} -Execute inline based on strategy selection above. -{{/if}} -``` - -**Phase 4: Self-Validation** - -``` -Validation checks: - -| Check | Method | Pass Criteria | -|-------|--------|---------------| -| Syntax | `Bash("tsc --noEmit 2>&1 || true")` or equivalent | No errors | -| File existence | Verify all planned files exist | All files present | -| Import resolution | Check no broken imports | All imports resolve | - -If validation fails -> attempt auto-fix (max 2 attempts) -> report remaining issues. -``` - -### Orchestration - -**Phase 2: Context & Complexity Assessment** - -``` -Complexity assessment: - -| Signal | Weight | Keywords | -|--------|--------|----------| -| Structural change | +2 | refactor, architect, restructure, module, system | -| Cross-cutting | +2 | multiple, across, cross | -| Integration | +1 | integrate, api, database | -| Non-functional | +1 | security, performance | - -| Score | Complexity | Approach | -|-------|------------|----------| -| >= 4 | High | Multi-stage with sub-orchestration | -| 2-3 | Medium | Standard pipeline | -| 0-1 | Low | Simplified flow | -``` - -**Phase 3: Orchestrated Execution** - -``` -Launch execution based on complexity: - -| Complexity | Execution Pattern | -|------------|-------------------| -| High | Parallel sub-agents + synchronization barriers | -| Medium | Sequential stages with dependency tracking | -| Low | Direct delegation to single worker | -``` - -**Phase 4: Result Aggregation** - -``` -Merge and summarize sub-agent results: - -1. Collect all sub-agent outputs -2. Deduplicate findings across agents -3. Prioritize by severity/importance -4. Generate consolidated summary -``` - -### Validation - -**Phase 2: Environment Detection** - -``` -**Detection steps**: - -1. Get changed files from git diff -2. Detect test framework from project files - -| Detection | Method | -|-----------|--------| -| Changed files | `Bash("git diff --name-only HEAD~1 2>/dev/null || git diff --name-only --cached")` | -| Test command | Check package.json scripts, pytest.ini, Makefile | -| Coverage tool | Check for nyc, coverage.py, jest --coverage config | -``` - -**Phase 3: Execution & Fix Cycle** - -``` -Iterative test-fix cycle: - -| Step | Action | -|------|--------| -| 1 | Run test command | -| 2 | Parse results -> check pass rate | -| 3 | Pass rate >= 95% -> exit loop (success) | -| 4 | Extract failing test details | -| 5 | Delegate fix to code-developer subagent | -| 6 | Increment iteration counter | -| 7 | iteration >= MAX (5) -> exit loop (report failures) | -| 8 | Go to Step 1 | -``` - -**Phase 4: Result Analysis** - -``` -Analyze test outcomes: - -| Metric | Source | Threshold | -|--------|--------|-----------| -| Pass rate | Test output parser | >= 95% | -| Coverage | Coverage tool output | >= 80% | -| Flaky tests | Compare runs | 0 flaky | - -Generate test report with: pass/fail counts, coverage data, failure details, fix attempts made. -``` - ---- - -## Variable Reference - -| Variable | Source | Description | -|----------|--------|-------------| -| `{{role_name}}` | config.role_name | Role identifier | -| `{{display_name}}` | config.display_name | Human-readable role name | -| `{{task_prefix}}` | config.task_prefix | UPPERCASE task prefix | -| `{{responsibility_type}}` | config.responsibility_type | Role type (read-only analysis, code generation, orchestration, validation) | -| `{{role_description}}` | config.role_description | One-line role description | -| `{{phase2_name}}` | patterns.phase_structure.phase2 | Phase 2 label | -| `{{phase3_name}}` | patterns.phase_structure.phase3 | Phase 3 label | -| `{{phase4_name}}` | patterns.phase_structure.phase4 | Phase 4 label | -| `{{phase2_content}}` | Generated from responsibility template | Phase 2 text content | -| `{{phase3_content}}` | Generated from responsibility template | Phase 3 text content | -| `{{phase4_content}}` | Generated from responsibility template | Phase 4 text content | -| `{{message_types}}` | config.message_types | Array of message type definitions | -| `{{commands}}` | config.commands | Array of command definitions | -| `{{has_commands}}` | config.commands.length > 0 | Boolean: has extracted commands | -| `{{has_no_commands}}` | config.commands.length === 0 | Boolean: all phases inline | -| `{{tool_capabilities}}` | config.tool_capabilities | Array of tool/subagent/CLI capabilities | -| `{{must_rules}}` | config.must_rules | Additional MUST rules | -| `{{must_not_rules}}` | config.must_not_rules | Additional MUST NOT rules | -| `{{additional_error_handlers}}` | config.additional_error_handlers | Array of {scenario, resolution} | - -## Key Differences from v1 - -| Aspect | v1 (old) | v2 (this template) | -|--------|----------|---------------------| -| Phase 1/5 | Inline JS code | Reference SKILL.md Shared Infrastructure | -| Message Bus | JS function call pseudocode | Text description + actual tool call template | -| Task Lifecycle | JS filter/map code | Step list description | -| Phase 2-4 | JS code per responsibility_type | Text + decision tables per responsibility_type | -| Command delegation | JS try/catch block | Text "Delegate to commands/xxx.md" | -| Coordinator template | JS spawn loops | Text phases with decision tables | diff --git a/.claude/skills_lib/team-skill-designer-v2/templates/skill-router-template.md b/.claude/skills_lib/team-skill-designer-v2/templates/skill-router-template.md deleted file mode 100644 index 279f8e1f..00000000 --- a/.claude/skills_lib/team-skill-designer-v2/templates/skill-router-template.md +++ /dev/null @@ -1,360 +0,0 @@ -# Skill Router Template - -Template for the generated SKILL.md with role-based routing (v3 style). - -## Purpose - -| Phase | Usage | -|-------|-------| -| Phase 0 | Read to understand generated SKILL.md structure | -| Phase 3 | Apply with team-specific content | - -## Style Rules - -Generated output follows v3 conventions: - -| Rule | Description | -|------|-------------| -| No pseudocode | Flow uses text + decision tables + flow symbols | -| Code blocks = tool calls only | Only Task(), TaskCreate(), Bash(), Read() etc. | -| `` in output | Not `${variable}` or `{{handlebars}}` in generated content | -| Decision tables | All branching logic uses `| Condition | Action |` tables | -| Cadence Control | Beat diagram + checkpoint definitions | -| Compact Protection | Phase Reference with Compact column | - -> **Note**: The template itself uses `{{handlebars}}` for variable substitution during Phase 3 generation. The **generated output** must not contain `{{handlebars}}` or JS pseudocode. - ---- - -## Template - -```markdown ---- -name: team-{{team_name}} -description: Unified team skill for {{team_name}}. All roles invoke this skill with --role arg for role-specific execution. Triggers on "team {{team_name}}". -allowed-tools: {{all_roles_tools_union}} ---- - -# Team {{team_display_name}} - -Unified team skill: {{team_purpose}}. All team members invoke with `--role=xxx` to route to role-specific execution. - -## Architecture - -\`\`\` -{{architecture_diagram}} -\`\`\` - -## Role Router - -### Input Parsing - -Parse `$ARGUMENTS` to extract `--role`. If absent -> Orchestration Mode (auto route to coordinator). - -### Role Registry - -| Role | File | Task Prefix | Type | Compact | -|------|------|-------------|------|---------| -{{#each roles}} -| {{this.name}} | [roles/{{this.name}}/role.md](roles/{{this.name}}/role.md) | {{this.task_prefix}}-* | {{this.type}} | Compress after must re-read | -{{/each}} - -> **COMPACT PROTECTION**: Role files are execution documents, not reference material. When context compression occurs and role instructions are reduced to summaries, **you MUST immediately `Read` the corresponding role.md to reload before continuing execution**. Do not execute any Phase based on summaries. - -### Dispatch - -1. Extract `--role` from arguments -2. If no `--role` -> route to coordinator (Orchestration Mode) -3. Look up role in registry -> Read the role file -> Execute its phases - -### Orchestration Mode - -When invoked without `--role`, coordinator auto-starts. User just provides task description. - -**Invocation**: `Skill(skill="team-{{team_name}}", args="")` - -**Lifecycle**: -\`\`\` -User provides task description - -> coordinator Phase 1-3: Requirement clarification -> TeamCreate -> Create task chain - -> coordinator Phase 4: spawn first batch workers (background) -> STOP - -> Worker executes -> SendMessage callback -> coordinator advances next step - -> Loop until pipeline complete -> Phase 5 report -\`\`\` - -**User Commands** (wake paused coordinator): - -| Command | Action | -|---------|--------| -| `check` / `status` | Output execution status graph, no advancement | -| `resume` / `continue` | Check worker states, advance next step | - ---- - -## Shared Infrastructure - -The following templates apply to all worker roles. Each role.md only needs to write **Phase 2-4** role-specific logic. - -### Worker Phase 1: Task Discovery (shared by all workers) - -Every worker executes the same task discovery flow on startup: - -1. Call `TaskList()` to get all tasks -2. Filter: subject matches this role's prefix + owner is this role + status is pending + blockedBy is empty -3. No tasks -> idle wait -4. Has tasks -> `TaskGet` for details -> `TaskUpdate` mark in_progress - -**Resume Artifact Check** (prevent duplicate output after resume): -- Check whether this task's output artifact already exists -- Artifact complete -> skip to Phase 5 report completion -- Artifact incomplete or missing -> normal Phase 2-4 execution - -### Worker Phase 5: Report (shared by all workers) - -Standard reporting flow after task completion: - -1. **Message Bus**: Call `mcp__ccw-tools__team_msg` to log message - - Parameters: operation="log", team=, from=, to="coordinator", type=, summary="[] ", ref= - - **CLI fallback**: When MCP unavailable -> `ccw team log --team --from --to coordinator --type --summary "[] ..." --json` -2. **SendMessage**: Send result to coordinator (content and summary both prefixed with `[]`) -3. **TaskUpdate**: Mark task completed -4. **Loop**: Return to Phase 1 to check next task - -### Wisdom Accumulation (all roles) - -Cross-task knowledge accumulation. Coordinator creates `wisdom/` directory at session initialization. - -**Directory**: -\`\`\` -/wisdom/ -+-- learnings.md # Patterns and insights -+-- decisions.md # Architecture and design decisions -+-- conventions.md # Codebase conventions -+-- issues.md # Known risks and issues -\`\`\` - -**Worker Load** (Phase 2): Extract `Session: ` from task description, read wisdom directory files. -**Worker Contribute** (Phase 4/5): Write this task's discoveries to corresponding wisdom files. - -### Role Isolation Rules - -| Allowed | Forbidden | -|---------|-----------| -| Process tasks with own prefix | Process tasks with other role prefixes | -| SendMessage to coordinator | Communicate directly with other workers | -| Use tools declared in Toolbox | Create tasks for other roles | -| Delegate to commands/ files | Modify resources outside own responsibility | - -Coordinator additional restrictions: Do not write/modify code directly, do not call implementation subagents, do not execute analysis/test/review directly. - ---- - -## Pipeline Definitions - -### Pipeline Diagram - -\`\`\` -{{pipeline_diagram}} -\`\`\` - -### Cadence Control - -**Beat model**: Event-driven, each beat = coordinator wake -> process -> spawn -> STOP. - -\`\`\` -Beat Cycle (single beat) -======================================================== - Event Coordinator Workers --------------------------------------------------------- - callback/resume --> +- handleCallback -+ - | mark completed | - | check pipeline | - +- handleSpawnNext -+ - | find ready tasks | - | spawn workers ---+--> [Worker A] Phase 1-5 - | (parallel OK) --+--> [Worker B] Phase 1-5 - +- STOP (idle) -----+ | - | - callback <-----------------------------------------+ - (next beat) SendMessage + TaskUpdate(completed) -======================================================== -\`\`\` - -{{cadence_beat_view}} - -**Checkpoints**: - -{{checkpoint_table}} - -**Stall Detection** (coordinator `handleCheck` executes): - -| Check | Condition | Resolution | -|-------|-----------|------------| -| Worker no response | in_progress task no callback | Report waiting task list, suggest user `resume` | -| Pipeline deadlock | no ready + no running + has pending | Check blockedBy dependency chain, report blocking point | -{{#if has_gc_loop}} -| GC loop exceeded | iteration > max_rounds | Terminate loop, output latest report | -{{/if}} - -### Task Metadata Registry - -| Task ID | Role | Phase | Dependencies | Description | -|---------|------|-------|-------------|-------------| -{{#each task_metadata}} -| {{this.task_id}} | {{this.role}} | {{this.phase}} | {{this.dependencies}} | {{this.description}} | -{{/each}} - -## Coordinator Spawn Template - -When coordinator spawns workers, use background mode (Spawn-and-Stop): - -\`\`\` -Task({ - subagent_type: "general-purpose", - description: "Spawn worker", - team_name: , - name: "", - run_in_background: true, - prompt: `You are team "" . - -## Primary Directive -All your work must be executed through Skill to load role definition: -Skill(skill="team-{{team_name}}", args="--role=") - -Current requirement: -Session: - -## Role Guidelines -- Only process -* tasks, do not execute other role work -- All output prefixed with [] identifier -- Only communicate with coordinator -- Do not use TaskCreate for other roles -- Call mcp__ccw-tools__team_msg before every SendMessage - -## Workflow -1. Call Skill -> load role definition and execution logic -2. Follow role.md 5-Phase flow -3. team_msg + SendMessage results to coordinator -4. TaskUpdate completed -> check next task` -}) -\`\`\` - -{{#if has_parallel_spawn}} -### Parallel Spawn (N agents for same role) - -> When pipeline has parallel tasks assigned to the same role, spawn N distinct agents with unique names. A single agent can only process tasks serially. - -**Parallel detection**: - -| Condition | Action | -|-----------|--------| -| N parallel tasks for same role prefix | Spawn N agents named `-1`, `-2` ... | -| Single task for role | Standard spawn (single agent) | - -**Parallel spawn template**: - -\`\`\` -Task({ - subagent_type: "general-purpose", - description: "Spawn - worker", - team_name: , - name: "-", - run_in_background: true, - prompt: `You are team "" (-). -Your agent name is "-", use this name for task discovery owner matching. - -## Primary Directive -Skill(skill="team-{{team_name}}", args="--role= --agent-name=-") - -## Role Guidelines -- Only process tasks where owner === "-" with -* prefix -- All output prefixed with [] identifier - -## Workflow -1. TaskList -> find tasks where owner === "-" with -* prefix -2. Skill -> execute role definition -3. team_msg + SendMessage results to coordinator -4. TaskUpdate completed -> check next task` -}) -\`\`\` - -**Dispatch must match agent names**: In dispatch, parallel tasks use instance-specific owner: `-`. In role.md, task discovery uses --agent-name for owner matching. -{{/if}} - -## Session Directory - -\`\`\` -{{session_directory_tree}} -\`\`\` - -{{#if has_session_resume}} -## Session Resume - -Coordinator supports `--resume` / `--continue` for interrupted sessions: - -1. Scan session directory for sessions with status "active" or "paused" -2. Multiple matches -> AskUserQuestion for selection -3. Audit TaskList -> reconcile session state <-> task status -4. Reset in_progress -> pending (interrupted tasks) -5. Rebuild team and spawn needed workers only -6. Create missing tasks with correct blockedBy -7. Kick first executable task -> Phase 4 coordination loop -{{/if}} - -{{#if shared_resources}} -## Shared Resources - -| Resource | Path | Usage | -|----------|------|-------| -{{#each shared_resources}} -| {{this.name}} | [{{this.path}}]({{this.path}}) | {{this.usage}} | -{{/each}} -{{/if}} - -## Error Handling - -| Scenario | Resolution | -|----------|------------| -| Unknown --role value | Error with available role list | -| Missing --role arg | Orchestration Mode -> auto route to coordinator | -| Role file not found | Error with expected path (roles//role.md) | -| Command file not found | Fallback to inline execution in role.md | -{{#each additional_error_handlers}} -| {{this.scenario}} | {{this.resolution}} | -{{/each}} -``` - ---- - -## Variable Reference - -| Variable | Source | Description | -|----------|--------|-------------| -| `{{team_name}}` | config.team_name | Team identifier (lowercase) | -| `{{team_display_name}}` | config.team_display_name | Human-readable team name | -| `{{team_purpose}}` | config.team_purpose | One-line team purpose | -| `{{all_roles_tools_union}}` | Union of all roles' allowed-tools | Combined tool list | -| `{{roles}}` | config.roles[] | Array of role definitions | -| `{{architecture_diagram}}` | Generated from role structure | ASCII architecture diagram | -| `{{pipeline_diagram}}` | Generated from task chain | ASCII pipeline diagram | -| `{{cadence_beat_view}}` | Generated from pipeline | Pipeline beat view diagram | -| `{{checkpoint_table}}` | Generated from pipeline | Checkpoint trigger/location/behavior table | -| `{{task_metadata}}` | Generated from pipeline | Task metadata registry entries | -| `{{session_directory_tree}}` | Generated from session structure | Session directory tree | -| `{{has_parallel_spawn}}` | config.has_parallel_spawn | Boolean: pipeline has parallel same-role tasks | -| `{{has_session_resume}}` | config.has_session_resume | Boolean: supports session resume | -| `{{has_gc_loop}}` | config.has_gc_loop | Boolean: has guard-and-correct loops | -| `{{shared_resources}}` | config.shared_resources | Array of shared resource definitions | -| `{{additional_error_handlers}}` | config.additional_error_handlers | Array of {scenario, resolution} | - -## Key Differences from v1 - -| Aspect | v1 (old) | v2 (this template) | -|--------|----------|---------------------| -| Role lookup | `VALID_ROLES` JS object | Role Registry decision table with markdown links | -| Routing | JS regex + if/else | Text dispatch flow (3 steps) | -| Spawn template | JS code with `${variable}` | Text template with `` | -| Infrastructure | Inline JS per role | Shared Infrastructure section (Phase 1/5 templates) | -| Pipeline | ASCII only | Cadence Control + beat view + checkpoints | -| Compact safety | None | Compact Protection with re-read mandate | -| Orchestration Mode | JS if/else block | Decision table + lifecycle flow diagram | diff --git a/.gitignore b/.gitignore index b20002d0..33801300 100644 --- a/.gitignore +++ b/.gitignore @@ -132,3 +132,6 @@ ccw/.tmp-ccw-auth-home/ .claude/skills_lib/team-skill-designer/templates/role-command-template.md .claude/skills_lib/team-skill-designer/templates/role-template.md .claude/skills_lib/team-skill-designer/templates/skill-router-template.md + +# Skills library (local only) +.claude/skills_lib/