diff --git a/.ccw/workflows/workflow-architecture.md b/.ccw/workflows/workflow-architecture.md index b145800e..ac134ab8 100644 --- a/.ccw/workflows/workflow-architecture.md +++ b/.ccw/workflows/workflow-architecture.md @@ -783,7 +783,7 @@ All workflows use the same file structure definition regardless of complexity. * **Examples**: *Workflow Commands (lightweight):* -- `/workflow-lite-planex "feature idea"` (exploratory) → `.scratchpad/lite-plan-feature-idea-20250105-143110.md` +- `/workflow-lite-plan "feature idea"` (exploratory) → `.scratchpad/lite-plan-feature-idea-20250105-143110.md` - `/workflow:lite-fix "bug description"` (bug fixing) → `.scratchpad/lite-fix-bug-20250105-143130.md` > **Note**: Direct CLI commands (`/cli:analyze`, `/cli:execute`, etc.) have been replaced by semantic invocation and workflow commands. diff --git a/.claude/commands/ccw-coordinator.md b/.claude/commands/ccw-coordinator.md index e2641594..54709504 100644 --- a/.claude/commands/ccw-coordinator.md +++ b/.claude/commands/ccw-coordinator.md @@ -17,7 +17,8 @@ Interactive orchestration tool: analyze task → discover commands → recommend | Skill | 包含操作 | |-------|---------| -| `workflow-lite-planex` | lite-plan (includes execution phase internally) | +| `workflow-lite-plan` | lite-plan (Skill handoff to lite-execute) | +| `workflow-lite-execute` | lite-execute (multi-mode execution engine) | | `workflow-plan` | plan, plan-verify, replan | | `workflow-execute` | execute | | `workflow-multi-cli-plan` | multi-cli-plan (includes execution phase internally) | @@ -547,7 +548,7 @@ Pipeline (管道视图): 需求 → lite-plan → 代码 → test-cycle-execute → 测试通过 Commands (命令列表): -1. /workflow-lite-planex +1. /workflow-lite-plan 2. /workflow-test-fix Proceed? [Confirm / Show Details / Adjust / Cancel] @@ -851,7 +852,7 @@ workflow 操作通过 `Skill()` 调用对应的 Skill。 ```javascript // Skill 调用方式 -Skill({ skill: 'workflow-lite-planex', args: '"task description"' }); +Skill({ skill: 'workflow-lite-plan', args: '"task description"' }); Skill({ skill: 'workflow-execute', args: '--resume-session="WFS-xxx"' }); Skill({ skill: 'brainstorm', args: '"exploration topic"' }); Skill({ skill: 'spec-generator', args: '"product specification"' }); @@ -904,7 +905,8 @@ Task: | Skill | 包含操作 | |-------|---------| -| `workflow-lite-planex` | lite-plan (includes execution phase internally) | +| `workflow-lite-plan` | lite-plan (Skill handoff to lite-execute) | +| `workflow-lite-execute` | lite-execute (multi-mode execution engine) | | `workflow-plan` | plan, plan-verify, replan | | `workflow-execute` | execute | | `workflow-multi-cli-plan` | multi-cli-plan (includes execution phase internally) | diff --git a/.claude/commands/ccw.md b/.claude/commands/ccw.md index 72468529..fe3f7d58 100644 --- a/.claude/commands/ccw.md +++ b/.claude/commands/ccw.md @@ -15,7 +15,8 @@ Main process orchestrator: intent analysis → workflow selection → command ch | Skill | 内部流水线 | |-------|-----------| -| `workflow-lite-planex` | explore → plan → confirm → execute | +| `workflow-lite-plan` | explore → plan → confirm → handoff | +| `workflow-lite-execute` | task grouping → batch execution → code review → sync | | `workflow-plan` | session → context → convention → gen → verify/replan | | `workflow-execute` | session discovery → task processing → commit | | `workflow-tdd-plan` | 6-phase TDD plan → verify | @@ -43,14 +44,14 @@ Main process orchestrator: intent analysis → workflow selection → command ch | 单元类型 | Skill | 说明 | |---------|-------|------| -| 轻量 Plan+Execute | `workflow-lite-planex` | 内部完成 plan→execute | +| 轻量 Plan+Execute | `workflow-lite-plan` → `workflow-lite-execute` | plan handoff 到 execute，分离 Skill，TodoWrite 跟踪延续 (LP-Phase → LE-Phase) | | 标准 Planning | `workflow-plan` → `workflow-execute` | plan 和 execute 是独立 Skill | | TDD Planning | `workflow-tdd-plan` → `workflow-execute` | tdd-plan 和 execute 是独立 Skill | | 规格驱动 | `spec-generator` → `workflow-plan` → `workflow-execute` | 规格文档驱动完整开发 | | 测试流水线 | `workflow-test-fix` | 内部完成 gen→cycle | | 代码审查 | `review-cycle` | 内部完成 review→fix | -| 多CLI协作 | `workflow-multi-cli-plan` | ACE context → CLI discussion → plan → execute | -| 分析→规划 | `workflow:analyze-with-file` → `workflow-lite-planex` | 协作分析产物自动传递给 lite-plan | +| 多CLI协作 | `workflow-multi-cli-plan` | ACE context → CLI discussion → plan → Skill(lite-execute) | +| 分析→规划 | `workflow:analyze-with-file` → `workflow-lite-plan` → `workflow-lite-execute` | 协作分析产物自动传递给 lite-plan，Skill 调用 lite-execute | | 头脑风暴→规划 | `workflow:brainstorm-with-file` → `workflow-plan` → `workflow-execute` | 头脑风暴产物自动传递给正式规划 | | 0→1 开发(小) | `workflow:brainstorm-with-file` → `workflow-plan` → `workflow-execute` | 小规模从零开始，探索+正式规划+实现 | | 0→1 开发(中/大) | `workflow:brainstorm-with-file` → `workflow-plan` → `workflow-execute` | 探索后正式规划+执行 | @@ -231,7 +232,7 @@ function buildCommandChain(workflow, analysis) { const chains = { // Level 2 - Lightweight 'rapid': [ - { cmd: 'workflow-lite-planex', args: `"${analysis.goal}"` }, + { cmd: 'workflow-lite-plan', args: `"${analysis.goal}"` }, ...(analysis.constraints?.includes('skip-tests') ? [] : [ { cmd: 'workflow-test-fix', args: '' } ]) @@ -239,21 +240,21 @@ function buildCommandChain(workflow, analysis) { // Level 2 Bridge - Lightweight to Issue Workflow 'rapid-to-issue': [ - { cmd: 'workflow-lite-planex', args: `"${analysis.goal}" --plan-only` }, + { cmd: 'workflow-lite-plan', args: `"${analysis.goal}" --plan-only` }, { cmd: 'issue:convert-to-plan', args: '--latest-lite-plan -y' }, { cmd: 'issue:queue', args: '' }, { cmd: 'issue:execute', args: '--queue auto' } ], 'bugfix.standard': [ - { cmd: 'workflow-lite-planex', args: `--bugfix "${analysis.goal}"` }, + { cmd: 'workflow-lite-plan', args: `--bugfix "${analysis.goal}"` }, ...(analysis.constraints?.includes('skip-tests') ? [] : [ { cmd: 'workflow-test-fix', args: '' } ]) ], 'bugfix.hotfix': [ - { cmd: 'workflow-lite-planex', args: `--hotfix "${analysis.goal}"` } + { cmd: 'workflow-lite-plan', args: `--hotfix "${analysis.goal}"` } ], 'multi-cli-plan': [ @@ -264,13 +265,13 @@ function buildCommandChain(workflow, analysis) { ], 'docs': [ - { cmd: 'workflow-lite-planex', args: `"${analysis.goal}"` } + { cmd: 'workflow-lite-plan', args: `"${analysis.goal}"` } ], // With-File → Auto Chain to lite-plan 'analyze-to-plan': [ { cmd: 'workflow:analyze-with-file', args: `"${analysis.goal}"` }, - { cmd: 'workflow-lite-planex', args: '' } // auto receives analysis artifacts (discussion.md) + { cmd: 'workflow-lite-plan', args: '' } // auto receives analysis artifacts (discussion.md) ], 'brainstorm-to-plan': [ @@ -476,7 +477,7 @@ function setupTodoTracking(chain, workflow, analysis) { ``` **Output**: -- TODO: `-> CCW:rapid: [1/2] workflow-lite-planex | CCW:rapid: [2/2] workflow-test-fix | ...` +- TODO: `-> CCW:rapid: [1/2] workflow-lite-plan | CCW:rapid: [2/2] workflow-test-fix | ...` - Status File: `.workflow/.ccw/{session_id}/status.json` --- @@ -628,10 +629,10 @@ Phase 5: Execute Command Chain | Input | Type | Level | Pipeline | |-------|------|-------|----------| -| "Add API endpoint" | feature (low) | 2 | workflow-lite-planex → workflow-test-fix | -| "Fix login timeout" | bugfix | 2 | workflow-lite-planex → workflow-test-fix | -| "Use issue workflow" | issue-transition | 2.5 | workflow-lite-planex(plan-only) → convert-to-plan → queue → execute | -| "协作分析: 认证架构" | analyze-file | 3 | analyze-with-file → workflow-lite-planex | +| "Add API endpoint" | feature (low) | 2 | workflow-lite-plan → workflow-test-fix | +| "Fix login timeout" | bugfix | 2 | workflow-lite-plan → workflow-test-fix | +| "Use issue workflow" | issue-transition | 2.5 | workflow-lite-plan(plan-only) → convert-to-plan → queue → execute | +| "协作分析: 认证架构" | analyze-file | 3 | analyze-with-file → workflow-lite-plan | | "深度调试 WebSocket" | debug-file | 3 | workflow:debug-with-file | | "从零开始: 用户系统" | greenfield (medium) | 3 | brainstorm-with-file → workflow-plan → workflow-execute → workflow-test-fix | | "greenfield: 大型平台" | greenfield (high) | 4 | brainstorm-with-file → workflow-plan → workflow-execute → review-cycle → workflow-test-fix | @@ -673,13 +674,13 @@ Phase 5: Execute Command Chain ```javascript // Initial state (rapid workflow: 2 steps) todos = [ - { content: "CCW:rapid: [1/2] workflow-lite-planex", status: "in_progress" }, + { content: "CCW:rapid: [1/2] workflow-lite-plan", status: "in_progress" }, { content: "CCW:rapid: [2/2] workflow-test-fix", status: "pending" } ]; // After step 1 completes todos = [ - { content: "CCW:rapid: [1/2] workflow-lite-planex", status: "completed" }, + { content: "CCW:rapid: [1/2] workflow-lite-plan", status: "completed" }, { content: "CCW:rapid: [2/2] workflow-test-fix", status: "in_progress" } ]; ``` @@ -704,7 +705,7 @@ todos = [ "complexity": "medium" }, "command_chain": [ - { "index": 0, "command": "workflow-lite-planex", "status": "completed" }, + { "index": 0, "command": "workflow-lite-plan", "status": "completed" }, { "index": 1, "command": "workflow-test-fix", "status": "running" } ], "current_index": 1 @@ -724,11 +725,11 @@ todos = [ |----------|---------|------------|---------------| | **brainstorm-with-file** | Multi-perspective ideation | → workflow-plan → workflow-execute (auto) | `.workflow/.brainstorm/` | | **debug-with-file** | Hypothesis-driven debugging | Standalone (self-contained) | `.workflow/.debug/` | -| **analyze-with-file** | Collaborative analysis | → workflow-lite-planex (auto) | `.workflow/.analysis/` | +| **analyze-with-file** | Collaborative analysis | → workflow-lite-plan → workflow-lite-execute (auto) | `.workflow/.analysis/` | | **collaborative-plan-with-file** | Multi-agent collaborative planning | → unified-execute-with-file | `.workflow/.planning/` | | **roadmap-with-file** | Strategic requirement roadmap | → team-planex | `.workflow/.planning/` | -**Auto Chain Mechanism**: When `analyze-with-file` completes, its artifacts (discussion.md) are automatically passed to `workflow-lite-planex`. When `brainstorm-with-file` completes, its artifacts (brainstorm.md) are passed to `workflow-plan` for formal planning. No user intervention needed. +**Auto Chain Mechanism**: When `analyze-with-file` completes, its artifacts (discussion.md) are automatically passed to `workflow-lite-plan`. When `brainstorm-with-file` completes, its artifacts (brainstorm.md) are passed to `workflow-plan` for formal planning. No user intervention needed. **Detection Keywords**: - **brainstorm**: 头脑风暴, 创意, 发散思维, multi-perspective, compare perspectives @@ -793,7 +794,7 @@ todos = [ /ccw "全新开发: 实时通知系统" # → brainstorm-with-file → workflow-plan → workflow-execute → review-cycle → workflow-test-fix # With-File workflows → auto chain -/ccw "协作分析: 理解现有认证架构的设计决策" # → analyze-with-file → workflow-lite-planex +/ccw "协作分析: 理解现有认证架构的设计决策" # → analyze-with-file → workflow-lite-plan → workflow-lite-execute /ccw "头脑风暴: 用户通知系统重新设计" # → brainstorm-with-file → workflow-plan → workflow-execute → workflow-test-fix /ccw "深度调试: 系统随机崩溃问题" # → debug-with-file (standalone) /ccw "从头脑风暴 BS-通知系统-2025-01-28 创建 issue" # → brainstorm-to-issue (bridge) diff --git a/.claude/commands/cli/cli-init.md b/.claude/commands/cli/cli-init.md index 5fc52b21..0dc3030c 100644 --- a/.claude/commands/cli/cli-init.md +++ b/.claude/commands/cli/cli-init.md @@ -378,7 +378,7 @@ docker-compose.override.yml ## Integration Points ### Workflow Commands -- **After `workflow-lite-planex` skill**: Suggest running cli-init for better analysis +- **After `workflow-lite-plan` skill**: Suggest running cli-init for better analysis - **Before analysis**: Recommend updating ignore patterns for cleaner results ### CLI Tool Integration diff --git a/.claude/commands/flow-create.md b/.claude/commands/flow-create.md index c312f65b..7d05907e 100644 --- a/.claude/commands/flow-create.md +++ b/.claude/commands/flow-create.md @@ -107,7 +107,7 @@ async function selectCommandCategory() { async function selectCommand(category) { const commandOptions = { 'Planning': [ - { label: "/workflow-lite-planex", description: "Lightweight merged-mode planning" }, + { label: "/workflow-lite-plan", description: "Lightweight merged-mode planning" }, { label: "/workflow-plan", description: "Full planning with architecture design" }, { label: "/workflow-multi-cli-plan", description: "Multi-CLI collaborative planning (Gemini+Codex+Claude)" }, { label: "/workflow-tdd-plan", description: "TDD workflow planning with Red-Green-Refactor" }, @@ -132,7 +132,7 @@ async function selectCommand(category) { { label: "/workflow:review", description: "Post-implementation review" } ], 'Bug Fix': [ - { label: "/workflow-lite-planex", description: "Lightweight bug diagnosis and fix (with --bugfix flag)" }, + { label: "/workflow-lite-plan", description: "Lightweight bug diagnosis and fix (with --bugfix flag)" }, { label: "/workflow:debug-with-file", description: "Hypothesis-driven debugging with documentation" } ], 'Brainstorm': [ @@ -302,7 +302,7 @@ async function defineSteps(templateDesign) { "description": "Quick implementation with testing", "level": 2, "steps": [ - { "cmd": "/workflow-lite-planex", "args": "\"{{goal}}\"", "unit": "quick-implementation", "execution": { "type": "slash-command", "mode": "mainprocess" }, "contextHint": "Create lightweight implementation plan (includes execution)" }, + { "cmd": "/workflow-lite-plan", "args": "\"{{goal}}\"", "unit": "quick-implementation", "execution": { "type": "slash-command", "mode": "mainprocess" }, "contextHint": "Create lightweight implementation plan (includes execution)" }, { "cmd": "/workflow-test-fix", "unit": "test-validation", "execution": { "type": "slash-command", "mode": "mainprocess" }, "contextHint": "Generate test tasks" }, { "cmd": "/workflow-test-fix", "unit": "test-validation", "execution": { "type": "slash-command", "mode": "async" }, "contextHint": "Execute test-fix cycle until pass rate >= 95%" } ] @@ -334,7 +334,7 @@ async function defineSteps(templateDesign) { "description": "Bug diagnosis and fix with testing", "level": 2, "steps": [ - { "cmd": "/workflow-lite-planex", "args": "--bugfix \"{{goal}}\"", "unit": "bug-fix", "execution": { "type": "slash-command", "mode": "mainprocess" }, "contextHint": "Diagnose, plan, and execute bug fix" }, + { "cmd": "/workflow-lite-plan", "args": "--bugfix \"{{goal}}\"", "unit": "bug-fix", "execution": { "type": "slash-command", "mode": "mainprocess" }, "contextHint": "Diagnose, plan, and execute bug fix" }, { "cmd": "/workflow-test-fix", "unit": "test-validation", "execution": { "type": "slash-command", "mode": "mainprocess" }, "contextHint": "Generate regression tests" }, { "cmd": "/workflow-test-fix", "unit": "test-validation", "execution": { "type": "slash-command", "mode": "async" }, "contextHint": "Verify fix with tests" } ] @@ -348,7 +348,7 @@ async function defineSteps(templateDesign) { "description": "Urgent production bug fix (no tests)", "level": 2, "steps": [ - { "cmd": "/workflow-lite-planex", "args": "--hotfix \"{{goal}}\"", "unit": "standalone", "execution": { "type": "slash-command", "mode": "mainprocess" }, "contextHint": "Emergency hotfix mode" } + { "cmd": "/workflow-lite-plan", "args": "--hotfix \"{{goal}}\"", "unit": "standalone", "execution": { "type": "slash-command", "mode": "mainprocess" }, "contextHint": "Emergency hotfix mode" } ] } ``` @@ -417,7 +417,7 @@ async function defineSteps(templateDesign) { "description": "Bridge lightweight planning to issue workflow", "level": 2, "steps": [ - { "cmd": "/workflow-lite-planex", "args": "\"{{goal}}\"", "unit": "rapid-to-issue", "execution": { "type": "slash-command", "mode": "mainprocess" }, "contextHint": "Create lightweight plan" }, + { "cmd": "/workflow-lite-plan", "args": "\"{{goal}}\"", "unit": "rapid-to-issue", "execution": { "type": "slash-command", "mode": "mainprocess" }, "contextHint": "Create lightweight plan" }, { "cmd": "/issue:convert-to-plan", "args": "--latest-lite-plan -y", "unit": "rapid-to-issue", "execution": { "type": "slash-command", "mode": "mainprocess" }, "contextHint": "Convert to issue plan" }, { "cmd": "/issue:queue", "unit": "rapid-to-issue", "execution": { "type": "slash-command", "mode": "mainprocess" }, "contextHint": "Form execution queue" }, { "cmd": "/issue:execute", "args": "--queue auto", "unit": "rapid-to-issue", "execution": { "type": "slash-command", "mode": "async" }, "contextHint": "Execute issue queue" } diff --git a/.claude/commands/idaw/resume.md b/.claude/commands/idaw/resume.md index 69a78e7c..05ec4d7c 100644 --- a/.claude/commands/idaw/resume.md +++ b/.claude/commands/idaw/resume.md @@ -15,16 +15,16 @@ When `--yes` or `-y`: Auto-skip interrupted task, continue with remaining. ```javascript const SKILL_CHAIN_MAP = { - 'bugfix': ['workflow-lite-planex', 'workflow-test-fix'], - 'bugfix-hotfix': ['workflow-lite-planex'], - 'feature': ['workflow-lite-planex', 'workflow-test-fix'], + 'bugfix': ['workflow-lite-plan', 'workflow-test-fix'], + 'bugfix-hotfix': ['workflow-lite-plan'], + 'feature': ['workflow-lite-plan', 'workflow-test-fix'], 'feature-complex': ['workflow-plan', 'workflow-execute', 'workflow-test-fix'], 'refactor': ['workflow:refactor-cycle'], 'tdd': ['workflow-tdd-plan', 'workflow-execute'], 'test': ['workflow-test-fix'], 'test-fix': ['workflow-test-fix'], 'review': ['review-cycle'], - 'docs': ['workflow-lite-planex'] + 'docs': ['workflow-lite-plan'] }; ``` diff --git a/.claude/commands/idaw/run-coordinate.md b/.claude/commands/idaw/run-coordinate.md index 9fead94e..1ae42eb5 100644 --- a/.claude/commands/idaw/run-coordinate.md +++ b/.claude/commands/idaw/run-coordinate.md @@ -26,16 +26,16 @@ Coordinator variant of `/idaw:run`: external CLI execution with background tasks ```javascript const SKILL_CHAIN_MAP = { - 'bugfix': ['workflow-lite-planex', 'workflow-test-fix'], - 'bugfix-hotfix': ['workflow-lite-planex'], - 'feature': ['workflow-lite-planex', 'workflow-test-fix'], + 'bugfix': ['workflow-lite-plan', 'workflow-test-fix'], + 'bugfix-hotfix': ['workflow-lite-plan'], + 'feature': ['workflow-lite-plan', 'workflow-test-fix'], 'feature-complex': ['workflow-plan', 'workflow-execute', 'workflow-test-fix'], 'refactor': ['workflow:refactor-cycle'], 'tdd': ['workflow-tdd-plan', 'workflow-execute'], 'test': ['workflow-test-fix'], 'test-fix': ['workflow-test-fix'], 'review': ['review-cycle'], - 'docs': ['workflow-lite-planex'] + 'docs': ['workflow-lite-plan'] }; ``` @@ -472,11 +472,11 @@ function assembleCliPrompt(skillName, task, previousResult, autoYes) { const yFlag = autoYes ? ' -y' : ''; // Map skill to command invocation - if (skillName === 'workflow-lite-planex') { + if (skillName === 'workflow-lite-plan') { const goal = sanitize(`${task.title}\n${task.description}`); - prompt = `/workflow-lite-planex${yFlag} "${goal}"`; - if (task.task_type === 'bugfix') prompt = `/workflow-lite-planex${yFlag} --bugfix "${goal}"`; - if (task.task_type === 'bugfix-hotfix') prompt = `/workflow-lite-planex${yFlag} --hotfix "${goal}"`; + prompt = `/workflow-lite-plan${yFlag} "${goal}"`; + if (task.task_type === 'bugfix') prompt = `/workflow-lite-plan${yFlag} --bugfix "${goal}"`; + if (task.task_type === 'bugfix-hotfix') prompt = `/workflow-lite-plan${yFlag} --hotfix "${goal}"`; } else if (skillName === 'workflow-plan') { prompt = `/workflow-plan${yFlag} "${sanitize(task.title)}"`; @@ -608,8 +608,8 @@ Phase 5: handleStepCompletion() { "task_id": "IDAW-001", "skill_index": 0, - "skill": "workflow-lite-planex", - "prompt": "/workflow-lite-planex -y \"Fix login timeout\"", + "skill": "workflow-lite-plan", + "prompt": "/workflow-lite-plan -y \"Fix login timeout\"", "timestamp": "ISO" } ] diff --git a/.claude/commands/idaw/run.md b/.claude/commands/idaw/run.md index 7bb87092..2b71e449 100644 --- a/.claude/commands/idaw/run.md +++ b/.claude/commands/idaw/run.md @@ -15,16 +15,16 @@ When `--yes` or `-y`: Skip all confirmations, auto-skip on failure, proceed with ```javascript const SKILL_CHAIN_MAP = { - 'bugfix': ['workflow-lite-planex', 'workflow-test-fix'], - 'bugfix-hotfix': ['workflow-lite-planex'], - 'feature': ['workflow-lite-planex', 'workflow-test-fix'], + 'bugfix': ['workflow-lite-plan', 'workflow-test-fix'], + 'bugfix-hotfix': ['workflow-lite-plan'], + 'feature': ['workflow-lite-plan', 'workflow-test-fix'], 'feature-complex': ['workflow-plan', 'workflow-execute', 'workflow-test-fix'], 'refactor': ['workflow:refactor-cycle'], 'tdd': ['workflow-tdd-plan', 'workflow-execute'], 'test': ['workflow-test-fix'], 'test-fix': ['workflow-test-fix'], 'review': ['review-cycle'], - 'docs': ['workflow-lite-planex'] + 'docs': ['workflow-lite-plan'] }; ``` diff --git a/.claude/commands/workflow/analyze-with-file.md b/.claude/commands/workflow/analyze-with-file.md index f8fbab5d..0349edb0 100644 --- a/.claude/commands/workflow/analyze-with-file.md +++ b/.claude/commands/workflow/analyze-with-file.md @@ -611,8 +611,8 @@ ${conclusions.open_questions.length > 0 ? `\n**Open Questions**:\n${conclusions. 5. **Post-Completion Options** (⚠️ TERMINAL — analyze-with-file ends after user selection) > **WORKFLOW BOUNDARY**: After user selects any option below, the analyze-with-file workflow is **COMPLETE**. - > If "执行任务" is selected, workflow-lite-planex takes over exclusively — do NOT return to any analyze-with-file phase. - > The "Phase" numbers in workflow-lite-planex (LP-Phase 1-5) are SEPARATE from analyze-with-file phases. + > If "执行任务" is selected, workflow-lite-plan takes over exclusively — do NOT return to any analyze-with-file phase. + > The "Phase" numbers in workflow-lite-plan (LP-Phase 1-5) are SEPARATE from analyze-with-file phases. ```javascript const hasActionableRecs = conclusions.recommendations?.some(r => r.priority === 'high' || r.priority === 'medium') @@ -623,7 +623,7 @@ ${conclusions.open_questions.length > 0 ? `\n**Open Questions**:\n${conclusions. header: "Next Step", multiSelect: false, options: [ - { label: hasActionableRecs ? "执行任务 (Recommended)" : "执行任务", description: "Launch workflow-lite-planex to plan & execute" }, + { label: hasActionableRecs ? "执行任务 (Recommended)" : "执行任务", description: "Launch workflow-lite-plan to plan & execute" }, { label: "产出Issue", description: "Launch issue-discover with conclusions" }, { label: "完成", description: "No further action" } ] @@ -665,7 +665,7 @@ DO NOT reference any analyze-with-file phase instructions beyond this point. `) // 4. Hand off to lite-plan — analyze-with-file COMPLETE, do NOT return to any analyze phase - Skill(skill="workflow-lite-planex", args=`"${taskDescription}\n\n${contextLines.join('\n')}"`) + Skill(skill="workflow-lite-plan", args=`"${taskDescription}\n\n${contextLines.join('\n')}"`) return // ⛔ analyze-with-file terminates here } ``` @@ -845,7 +845,7 @@ User agrees with current direction, wants deeper code analysis - Quick information gathering without multi-round iteration - Follow-up analysis building on existing session -**Use `Skill(skill="workflow-lite-planex", args="\"task description\"")` when:** +**Use `Skill(skill="workflow-lite-plan", args="\"task description\"")` when:** - Ready to implement (past analysis phase) - Need simple task breakdown - Focus on quick execution planning diff --git a/.claude/commands/workflow/brainstorm-with-file.md b/.claude/commands/workflow/brainstorm-with-file.md index 24c02bfe..38538ef5 100644 --- a/.claude/commands/workflow/brainstorm-with-file.md +++ b/.claude/commands/workflow/brainstorm-with-file.md @@ -769,7 +769,7 @@ See full markdown template in original file (lines 955-1161). - Want shared collaborative planning document - Need structured task breakdown with agent coordination -**Use `Skill(skill="workflow-lite-planex", args="\"task description\"")` when:** +**Use `Skill(skill="workflow-lite-plan", args="\"task description\"")` when:** - Direction is already clear - Ready to move from ideas to execution - Need simple implementation breakdown diff --git a/.claude/commands/workflow/debug-with-file.md b/.claude/commands/workflow/debug-with-file.md index bfb209c7..53799388 100644 --- a/.claude/commands/workflow/debug-with-file.md +++ b/.claude/commands/workflow/debug-with-file.md @@ -651,6 +651,6 @@ if (autoYes) { | Empty debug.log | Verify reproduction triggered the code path | | All hypotheses rejected | Use Gemini to generate new hypotheses based on disproven assumptions | | Fix doesn't work | Document failed fix attempt, iterate with refined understanding | -| >5 iterations | Review consolidated understanding, escalate to `workflow-lite-planex` skill with full context | +| >5 iterations | Review consolidated understanding, escalate to `workflow-lite-plan` skill with full context | | Gemini unavailable | Fallback to manual hypothesis generation, document without Gemini insights | | Understanding too long | Consolidate aggressively, archive old iterations to separate file | diff --git a/.claude/commands/workflow/refactor-cycle.md b/.claude/commands/workflow/refactor-cycle.md index 77f1264f..cd733f18 100644 --- a/.claude/commands/workflow/refactor-cycle.md +++ b/.claude/commands/workflow/refactor-cycle.md @@ -827,7 +827,7 @@ AskUserQuestion({ - Need regression-safe iterative refactoring with rollback - Want documented reasoning for each refactoring decision -**Use `workflow-lite-planex` skill when:** +**Use `workflow-lite-plan` skill when:** - Single specific bug or issue to fix - No systematic debt analysis needed diff --git a/.claude/commands/workflow/roadmap-with-file.md b/.claude/commands/workflow/roadmap-with-file.md index 910165a2..87af84fb 100644 --- a/.claude/commands/workflow/roadmap-with-file.md +++ b/.claude/commands/workflow/roadmap-with-file.md @@ -534,10 +534,10 @@ ${selectedMode === 'progressive' ? `**Progressive Mode**: | Scenario | Recommended Command | |----------|-------------------| | Strategic planning, need issue tracking | `/workflow:roadmap-with-file` | -| Quick task breakdown, immediate execution | `/workflow-lite-planex` | +| Quick task breakdown, immediate execution | `/workflow-lite-plan` | | Collaborative multi-agent planning | `/workflow:collaborative-plan-with-file` | | Full specification documents | `spec-generator` skill | -| Code implementation from existing plan | `/workflow-lite-planex` (Phase 1: plan → Phase 2: execute) | +| Code implementation from existing plan | `/workflow-lite-plan` (Phase 1: plan → Phase 2: execute) | --- diff --git a/.claude/scripts/cleanup-ghost-commands.mjs b/.claude/scripts/cleanup-ghost-commands.mjs index d102f213..c3ac70b6 100644 --- a/.claude/scripts/cleanup-ghost-commands.mjs +++ b/.claude/scripts/cleanup-ghost-commands.mjs @@ -45,9 +45,9 @@ const COMMAND_TO_SKILL_MAP = { // workflow commands → skills '/workflow-plan': 'workflow-plan', '/workflow-execute': 'workflow-execute', - '/workflow-lite-planex': 'workflow-lite-planex', - '/workflow:lite-execute': 'workflow-lite-planex', // lite-execute is part of lite-plan skill - '/workflow:lite-fix': 'workflow-lite-planex', // lite-fix is part of lite-plan skill + '/workflow-lite-plan': 'workflow-lite-plan', + '/workflow:lite-execute': 'workflow-lite-plan', // lite-execute is part of lite-plan skill + '/workflow:lite-fix': 'workflow-lite-plan', // lite-fix is part of lite-plan skill '/workflow-multi-cli-plan': 'workflow-multi-cli-plan', '/workflow-plan-verify': 'workflow-plan', // plan-verify is a phase of workflow-plan '/workflow:replan': 'workflow-plan', // replan is a phase of workflow-plan @@ -87,7 +87,7 @@ const COMMAND_TO_SKILL_MAP = { // general commands '/ccw-debug': null, // deleted, no replacement '/ccw view': null, // deleted, no replacement - '/workflow:lite-lite-lite': 'workflow-lite-planex', + '/workflow:lite-lite-lite': 'workflow-lite-plan', // ui-design (these still exist as commands) '/workflow:ui-design:auto': '/workflow:ui-design:explore-auto', '/workflow:ui-design:update': '/workflow:ui-design:generate', @@ -302,8 +302,8 @@ function fixBrokenReferences() { "skill='compact'": "skill='memory-capture'", 'skill="workflow:brainstorm:role-analysis"': 'skill="brainstorm"', "skill='workflow:brainstorm:role-analysis'": "skill='brainstorm'", - 'skill="workflow:lite-execute"': 'skill="workflow-lite-planex"', - "skill='workflow:lite-execute'": "skill='workflow-lite-planex'", + 'skill="workflow:lite-execute"': 'skill="workflow-lite-plan"', + "skill='workflow:lite-execute'": "skill='workflow-lite-plan'", }; for (const [oldCall, newCall] of Object.entries(skillCallFixes)) { @@ -321,8 +321,8 @@ function fixBrokenReferences() { const proseRefFixes = { '`/workflow-plan`': '`workflow-plan` skill', '`/workflow-execute`': '`workflow-execute` skill', - '`/workflow:lite-execute`': '`workflow-lite-planex` skill', - '`/workflow:lite-fix`': '`workflow-lite-planex` skill', + '`/workflow:lite-execute`': '`workflow-lite-plan` skill', + '`/workflow:lite-fix`': '`workflow-lite-plan` skill', '`/workflow-plan-verify`': '`workflow-plan` skill (plan-verify phase)', '`/workflow:replan`': '`workflow-plan` skill (replan phase)', '`/workflow-tdd-plan`': '`workflow-tdd-plan` skill', @@ -347,8 +347,8 @@ function fixBrokenReferences() { '`/workflow:ui-design:auto`': '`/workflow:ui-design:explore-auto`', '`/workflow:ui-design:update`': '`/workflow:ui-design:generate`', '`/workflow-multi-cli-plan`': '`workflow-multi-cli-plan` skill', - '`/workflow-lite-planex`': '`workflow-lite-planex` skill', - '`/cli:plan`': '`workflow-lite-planex` skill', + '`/workflow-lite-plan`': '`workflow-lite-plan` skill', + '`/cli:plan`': '`workflow-lite-plan` skill', '`/test-cycle-execute`': '`workflow-test-fix` skill', }; diff --git a/.claude/skills/ccw-help/SKILL.md b/.claude/skills/ccw-help/SKILL.md index 257028a8..5697f0b7 100644 --- a/.claude/skills/ccw-help/SKILL.md +++ b/.claude/skills/ccw-help/SKILL.md @@ -77,7 +77,7 @@ CCW 命令帮助系统，提供命令搜索、推荐、文档查看、Skill/Team - **With-File Workflows**: Documented exploration with multi-CLI collaboration - `brainstorm-with-file`: Multi-perspective ideation → workflow-plan → workflow-execute - `debug-with-file`: Hypothesis-driven debugging (standalone) - - `analyze-with-file`: Collaborative analysis → workflow-lite-planex + - `analyze-with-file`: Collaborative analysis → workflow-lite-plan - `collaborative-plan-with-file`: Multi-agent planning → unified-execute - `roadmap-with-file`: Strategic requirement roadmap → team-planex - **Issue Workflow**: Batch issue discovery, planning, queueing, execution @@ -131,7 +131,7 @@ Single source of truth: **[command.json](command.json)** | Skill | 内部流水线 | 触发词 | |-------|-----------|--------| -| `workflow-lite-planex` | explore → plan → confirm → execute | "lite-plan", 快速任务 | +| `workflow-lite-plan` | explore → plan → confirm → execute | "lite-plan", 快速任务 | | `workflow-plan` | session → context → convention → gen → verify | "workflow-plan", 正式规划 | | `workflow-execute` | session discovery → task processing → commit | "workflow-execute", 执行 | | `workflow-tdd-plan` | 6-phase TDD plan → verify | "tdd-plan", TDD 开发 | @@ -186,9 +186,9 @@ CCW 根据任务意图自动选择工作流级别（参考 [ccw.md](../../comman | 输入示例 | 类型 | 级别 | 流水线 | |---------|------|------|--------| -| "Add API endpoint" | feature (low) | 2 | workflow-lite-planex → workflow-test-fix | -| "Fix login timeout" | bugfix | 2 | workflow-lite-planex → workflow-test-fix | -| "协作分析: 认证架构" | analyze-file | 3 | analyze-with-file → workflow-lite-planex | +| "Add API endpoint" | feature (low) | 2 | workflow-lite-plan → workflow-test-fix | +| "Fix login timeout" | bugfix | 2 | workflow-lite-plan → workflow-test-fix | +| "协作分析: 认证架构" | analyze-file | 3 | analyze-with-file → workflow-lite-plan | | "重构 auth 模块" | refactor | 3 | workflow:refactor-cycle | | "multi-cli: API设计" | multi-cli | 3 | workflow-multi-cli-plan → workflow-test-fix | | "头脑风暴: 通知系统" | brainstorm | 4 | brainstorm-with-file → workflow-plan → workflow-execute | diff --git a/.claude/skills/ccw-help/command.json b/.claude/skills/ccw-help/command.json index 0e720a0b..2f9402e1 100644 --- a/.claude/skills/ccw-help/command.json +++ b/.claude/skills/ccw-help/command.json @@ -955,14 +955,14 @@ "source": "../../../skills/workflow-execute/SKILL.md" }, { - "name": "workflow-lite-planex", - "description": "Lightweight planning and execution skill (Phase 1: plan, Phase 2: execute). Triggers on \"workflow-lite-planex\".", + "name": "workflow-lite-plan", + "description": "Lightweight planning and execution skill (Phase 1: plan, Phase 2: execute). Triggers on \"workflow-lite-plan\".", "category": "workflow", "is_team": false, "has_phases": true, "has_role_specs": false, "version": "", - "source": "../../../skills/workflow-lite-planex/SKILL.md" + "source": "../../../skills/workflow-lite-plan/SKILL.md" }, { "name": "workflow-multi-cli-plan", diff --git a/.claude/skills/ccw-help/index/all-skills.json b/.claude/skills/ccw-help/index/all-skills.json index 9476ff99..814a8acb 100644 --- a/.claude/skills/ccw-help/index/all-skills.json +++ b/.claude/skills/ccw-help/index/all-skills.json @@ -290,14 +290,14 @@ "source": "../../../skills/workflow-execute/SKILL.md" }, { - "name": "workflow-lite-planex", - "description": "Lightweight planning and execution skill (Phase 1: plan, Phase 2: execute). Triggers on \"workflow-lite-planex\".", + "name": "workflow-lite-plan", + "description": "Lightweight planning and execution skill (Phase 1: plan, Phase 2: execute). Triggers on \"workflow-lite-plan\".", "category": "workflow", "is_team": false, "has_phases": true, "has_role_specs": false, "version": "", - "source": "../../../skills/workflow-lite-planex/SKILL.md" + "source": "../../../skills/workflow-lite-plan/SKILL.md" }, { "name": "workflow-multi-cli-plan", diff --git a/.claude/skills/ccw-help/index/command-relationships.json b/.claude/skills/ccw-help/index/command-relationships.json index 56e10aeb..51033ac5 100644 --- a/.claude/skills/ccw-help/index/command-relationships.json +++ b/.claude/skills/ccw-help/index/command-relationships.json @@ -70,7 +70,7 @@ "workflow:session:list" ] }, - "workflow-lite-planex": { + "workflow-lite-plan": { "calls_internally": [], "next_steps": [ "workflow:session:list" diff --git a/.claude/skills/ccw-help/index/skills-by-category.json b/.claude/skills/ccw-help/index/skills-by-category.json index 1bfaaff5..3ea2b2ba 100644 --- a/.claude/skills/ccw-help/index/skills-by-category.json +++ b/.claude/skills/ccw-help/index/skills-by-category.json @@ -301,14 +301,14 @@ "source": "../../../skills/workflow-execute/SKILL.md" }, { - "name": "workflow-lite-planex", - "description": "Lightweight planning and execution skill (Phase 1: plan, Phase 2: execute). Triggers on \"workflow-lite-planex\".", + "name": "workflow-lite-plan", + "description": "Lightweight planning and execution skill (Phase 1: plan, Phase 2: execute). Triggers on \"workflow-lite-plan\".", "category": "workflow", "is_team": false, "has_phases": true, "has_role_specs": false, "version": "", - "source": "../../../skills/workflow-lite-planex/SKILL.md" + "source": "../../../skills/workflow-lite-plan/SKILL.md" }, { "name": "workflow-multi-cli-plan", diff --git a/.claude/skills/ccw-help/scripts/analyze_commands.py b/.claude/skills/ccw-help/scripts/analyze_commands.py index 37a2b151..055db0a2 100644 --- a/.claude/skills/ccw-help/scripts/analyze_commands.py +++ b/.claude/skills/ccw-help/scripts/analyze_commands.py @@ -239,7 +239,7 @@ def build_command_relationships() -> Dict[str, Any]: "alternatives": ["workflow:resume"], "related": ["workflow:session:list", "workflow:status"] }, - "workflow-lite-planex": { + "workflow-lite-plan": { "calls_internally": [], "next_steps": ["workflow:status"], "alternatives": ["workflow-plan"], @@ -247,7 +247,7 @@ def build_command_relationships() -> Dict[str, Any]: }, "workflow:lite-fix": { "next_steps": ["workflow:status"], - "alternatives": ["workflow-lite-planex"], + "alternatives": ["workflow-lite-plan"], "related": ["workflow-test-fix"] }, "workflow:review-session-cycle": { @@ -272,7 +272,7 @@ def build_command_relationships() -> Dict[str, Any]: def identify_essential_commands(all_commands: List[Dict]) -> List[Dict]: """Identify the most essential commands for beginners.""" essential_names = [ - "workflow-lite-planex", "workflow:lite-fix", "workflow-plan", + "workflow-lite-plan", "workflow:lite-fix", "workflow-plan", "workflow-execute", "workflow:status", "workflow:session:start", "workflow:review-session-cycle", "cli:analyze", "cli:chat", "memory:docs", "workflow:brainstorm:artifacts", diff --git a/.claude/skills/spec-generator/README.md b/.claude/skills/spec-generator/README.md index 65ffd74a..59514e42 100644 --- a/.claude/skills/spec-generator/README.md +++ b/.claude/skills/spec-generator/README.md @@ -88,7 +88,7 @@ Available types: `service`, `api`, `library`, `platform` ## Handoff After Phase 6, choose execution path: -- `workflow-lite-planex` - Execute per Epic +- `workflow-lite-plan` - Execute per Epic - `workflow:req-plan-with-file` - Roadmap decomposition - `workflow-plan` - Full planning - `issue:new` - Create issues per Epic diff --git a/.claude/skills/spec-generator/phases/06-readiness-check.md b/.claude/skills/spec-generator/phases/06-readiness-check.md index a01942c3..0d8fccaf 100644 --- a/.claude/skills/spec-generator/phases/06-readiness-check.md +++ b/.claude/skills/spec-generator/phases/06-readiness-check.md @@ -214,7 +214,7 @@ AskUserQuestion({ options: [ { label: "Execute via lite-plan", - description: "Start implementing with /workflow-lite-planex, one Epic at a time" + description: "Start implementing with /workflow-lite-plan, one Epic at a time" }, { label: "Create roadmap", @@ -250,7 +250,7 @@ if (selection === "Execute via lite-plan") { const epicContent = Read(firstMvpFile); const title = extractTitle(epicContent); // First # heading const description = extractSection(epicContent, "Description"); - Skill(skill="workflow-lite-planex", args=`"${title}: ${description}"`) + Skill(skill="workflow-lite-plan", args=`"${title}: ${description}"`) } if (selection === "Full planning" || selection === "Create roadmap") { diff --git a/.claude/skills/workflow-lite-execute/SKILL.md b/.claude/skills/workflow-lite-execute/SKILL.md index 80108e84..14225b09 100644 --- a/.claude/skills/workflow-lite-execute/SKILL.md +++ b/.claude/skills/workflow-lite-execute/SKILL.md @@ -29,8 +29,12 @@ Flexible task execution command supporting three input modes: in-memory plan (fr Task description string, or path to file (required) ``` -Mode 1 (In-Memory) is triggered by workflow-lite-plan direct handoff when `executionContext` is available. -Workflow preferences (`autoYes`) are passed from SKILL.md via `workflowPreferences` context variable. +### Flags +| Flag | Description | +|------|-------------| +| `--in-memory` | Mode 1: Use executionContext from workflow-lite-plan handoff (via Skill({ skill: "workflow-lite-execute", args: "--in-memory" }) | + +Mode 1 (In-Memory) is triggered by `--in-memory` flag or when `executionContext` global variable is available. ## Input Modes diff --git a/.claude/skills/workflow-lite-plan/SKILL.md b/.claude/skills/workflow-lite-plan/SKILL.md index 1837e432..917650c6 100644 --- a/.claude/skills/workflow-lite-plan/SKILL.md +++ b/.claude/skills/workflow-lite-plan/SKILL.md @@ -36,6 +36,13 @@ Intelligent lightweight planning command with dynamic workflow adaptation based Task description or path to .md file (required) ``` +### Flags + +| Flag | Description | +|------|-------------| +| `-y`, `--yes` | Auto mode: Skip clarification, auto-confirm plan, auto-select execution, skip review | +| `--force-explore` | Force code exploration even when task has prior analysis | + Workflow preferences (`autoYes`, `forceExplore`) are collected by SKILL.md via AskUserQuestion and passed as `workflowPreferences` context variable. ## Output Artifacts @@ -767,12 +774,24 @@ executionContext = { } ``` -**Step 5.2: Handoff** +**Step 5.2: Handoff with Tracking** ```javascript +// Update TodoWrite to show handoff to lite-execute +const taskCount = (plan.task_ids || []).length +TodoWrite({ todos: [ + { content: "LP-Phase 1: Exploration", status: "completed", activeForm: "Exploring codebase" }, + { content: "LP-Phase 2: Clarification", status: "completed", activeForm: "Collecting clarifications" }, + { content: "LP-Phase 3: Planning", status: "completed", activeForm: "Generating plan" }, + { content: `LP-Phase 4: Confirmed [${executionLabel}]`, status: "completed", activeForm: "Confirmed" }, + { content: `LP-Phase 5: Handoff → lite-execute`, status: "completed", activeForm: "Handoff to execution" }, + { content: `LE-Phase 1: Task Loading [${taskCount} tasks]`, status: "in_progress", activeForm: "Loading tasks" } +]}) + // Invoke lite-execute skill with executionContext Skill("lite-execute") // executionContext is passed as global variable (Mode 1: In-Memory Plan) +// lite-execute will continue TodoWrite tracking with LE-Phase prefix ``` ## Session Folder Structure diff --git a/.claude/skills/workflow-multi-cli-plan/SKILL.md b/.claude/skills/workflow-multi-cli-plan/SKILL.md index 07baee40..b2674bf7 100644 --- a/.claude/skills/workflow-multi-cli-plan/SKILL.md +++ b/.claude/skills/workflow-multi-cli-plan/SKILL.md @@ -4,10 +4,519 @@ description: Multi-CLI collaborative planning with ACE context gathering, iterat allowed-tools: Skill, Agent, AskUserQuestion, TodoWrite, Read, Write, Edit, Bash, Glob, Grep --- -# Workflow-Multi-CLI-Plan +# Multi-CLI Collaborative Planning -Multi-CLI collaborative planning with ACE context gathering and iterative cross-verification. +## Auto Mode -## Execution +When `workflowPreferences.autoYes` is true: Auto-approve plan, use recommended solution and execution method (Agent, Skip review). -Execute Phase 1 directly: [phases/01-multi-cli-plan.md](phases/01-multi-cli-plan.md) +## Quick Start + +```bash +# Basic usage +/workflow-multi-cli-plan "Implement user authentication" + +# With options +/workflow-multi-cli-plan "Add dark mode support" --max-rounds=3 +/workflow-multi-cli-plan "Refactor payment module" --tools=gemini,codex,claude +/workflow-multi-cli-plan "Fix memory leak" --mode=serial +``` + +**Context Source**: ACE semantic search + Multi-CLI analysis +**Output Directory**: `.workflow/.multi-cli-plan/{session-id}/` +**Default Max Rounds**: 3 (convergence may complete earlier) +**CLI Tools**: @cli-discuss-agent (analysis), @cli-lite-planning-agent (plan generation) +**Execution**: Auto-hands off to workflow-lite-execute after plan approval + +## What & Why + +### Core Concept + +Multi-CLI collaborative planning with **three-phase architecture**: ACE context gathering → Iterative multi-CLI discussion → Plan generation. Orchestrator delegates analysis to agents, only handles user decisions and session management. + +**Process**: +- **Phase 1**: ACE semantic search gathers codebase context +- **Phase 2**: cli-discuss-agent orchestrates Gemini/Codex/Claude for cross-verified analysis +- **Phase 3-5**: User decision → Plan generation → Execution handoff + +**vs Single-CLI Planning**: +- **Single**: One model perspective, potential blind spots +- **Multi-CLI**: Cross-verification catches inconsistencies, builds consensus on solutions + +### Value Proposition + +1. **Multi-Perspective Analysis**: Gemini + Codex + Claude analyze from different angles +2. **Cross-Verification**: Identify agreements/disagreements, build confidence +3. **User-Driven Decisions**: Every round ends with user decision point +4. **Iterative Convergence**: Progressive refinement until consensus reached + +### Orchestrator Boundary (CRITICAL) + +- **ONLY command** for multi-CLI collaborative planning +- Manages: Session state, user decisions, agent delegation, phase transitions +- Delegates: CLI execution to @cli-discuss-agent, plan generation to @cli-lite-planning-agent + +### Execution Flow + +``` +Phase 1: Context Gathering + └─ ACE semantic search, extract keywords, build context package + +Phase 2: Multi-CLI Discussion (Iterative, via @cli-discuss-agent) + ├─ Round N: Agent executes Gemini + Codex + Claude + ├─ Cross-verify findings, synthesize solutions + ├─ Write synthesis.json to rounds/{N}/ + └─ Loop until convergence or max rounds + +Phase 3: Present Options + └─ Display solutions with trade-offs from agent output + +Phase 4: User Decision + ├─ Select solution approach + ├─ Select execution method (Agent/Codex/Auto) + ├─ Select code review tool (Skip/Gemini/Codex/Agent) + └─ Route: + ├─ Approve → Phase 5 + ├─ Need More Analysis → Return to Phase 2 + └─ Cancel → Save session + +Phase 5: Plan Generation & Execution Handoff + ├─ Generate plan.json + .task/*.json (via @cli-lite-planning-agent, two-layer output) + ├─ Build executionContext with user selections and taskFiles + └─ Execute via workflow-lite-execute +``` + +### Agent Roles + +| Agent | Responsibility | +|-------|---------------| +| **Orchestrator** | Session management, ACE context, user decisions, phase transitions, executionContext assembly | +| **@cli-discuss-agent** | Multi-CLI execution (Gemini/Codex/Claude), cross-verification, solution synthesis, synthesis.json output | +| **@cli-lite-planning-agent** | Task decomposition, two-layer output: plan.json (overview with task_ids[]) + .task/*.json (task files) | + +## Core Responsibilities + +### Phase 1: Context Gathering + +**Session Initialization**: +```javascript +const sessionId = `MCP-${taskSlug}-${date}` +const sessionFolder = `.workflow/.multi-cli-plan/${sessionId}` +Bash(`mkdir -p ${sessionFolder}/rounds`) +``` + +**ACE Context Queries**: +```javascript +const aceQueries = [ + `Project architecture related to ${keywords}`, + `Existing implementations of ${keywords[0]}`, + `Code patterns for ${keywords} features`, + `Integration points for ${keywords[0]}` +] +// Execute via mcp__ace-tool__search_context +``` + +**Context Package** (passed to agent): +- `relevant_files[]` - Files identified by ACE +- `detected_patterns[]` - Code patterns found +- `architecture_insights` - Structure understanding + +### Phase 2: Agent Delegation + +**Core Principle**: Orchestrator only delegates and reads output - NO direct CLI execution. + +**⚠️ CRITICAL - CLI EXECUTION REQUIREMENT**: +- **MUST** execute CLI calls via `Bash` with `run_in_background: true` +- **MUST** wait for hook callback to receive complete results +- **MUST NOT** proceed with next phase until CLI execution fully completes +- Do NOT use `TaskOutput` polling during CLI execution - wait passively for results +- Minimize scope: Proceed only when 100% result available + +**Agent Invocation**: +```javascript +Agent({ + subagent_type: "cli-discuss-agent", + run_in_background: false, + description: `Discussion round ${currentRound}`, + prompt: ` +## Input Context +- task_description: ${taskDescription} +- round_number: ${currentRound} +- session: { id: "${sessionId}", folder: "${sessionFolder}" } +- ace_context: ${JSON.stringify(contextPackageage)} +- previous_rounds: ${JSON.stringify(analysisResults)} +- user_feedback: ${userFeedback || 'None'} +- cli_config: { tools: ["gemini", "codex"], mode: "parallel", fallback_chain: ["gemini", "codex", "claude"] } + +## Execution Process +1. Parse input context (handle JSON strings) +2. Check if ACE supplementary search needed +3. Build CLI prompts with context +4. Execute CLIs (parallel or serial per cli_config.mode) +5. Parse CLI outputs, handle failures with fallback +6. Perform cross-verification between CLI results +7. Synthesize solutions, calculate scores +8. Calculate convergence, generate clarification questions +9. Write synthesis.json + +## Output +Write: ${sessionFolder}/rounds/${currentRound}/synthesis.json + +## Completion Checklist +- [ ] All configured CLI tools executed (or fallback triggered) +- [ ] Cross-verification completed with agreements/disagreements +- [ ] 2-3 solutions generated with file:line references +- [ ] Convergence score calculated (0.0-1.0) +- [ ] synthesis.json written with all Primary Fields +` +}) +``` + +**Read Agent Output**: +```javascript +const synthesis = JSON.parse(Read(`${sessionFolder}/rounds/${round}/synthesis.json`)) +// Access top-level fields: solutions, convergence, cross_verification, clarification_questions +``` + +**Convergence Decision**: +```javascript +if (synthesis.convergence.recommendation === 'converged') { + // Proceed to Phase 3 +} else if (synthesis.convergence.recommendation === 'user_input_needed') { + // Collect user feedback, return to Phase 2 +} else { + // Continue to next round if new_insights && round < maxRounds +} +``` + +### Phase 3: Present Options + +**Display from Agent Output** (no processing): +```javascript +console.log(` +## Solution Options + +${synthesis.solutions.map((s, i) => ` +**Option ${i+1}: ${s.name}** +Source: ${s.source_cli.join(' + ')} +Effort: ${s.effort} | Risk: ${s.risk} + +Pros: ${s.pros.join(', ')} +Cons: ${s.cons.join(', ')} + +Files: ${s.affected_files.slice(0,3).map(f => `${f.file}:${f.line}`).join(', ')} +`).join('\n')} + +## Cross-Verification +Agreements: ${synthesis.cross_verification.agreements.length} +Disagreements: ${synthesis.cross_verification.disagreements.length} +`) +``` + +### Phase 4: User Decision + +**Decision Options**: +```javascript +AskUserQuestion({ + questions: [ + { + question: "Which solution approach?", + header: "Solution", + multiSelect: false, + options: solutions.map((s, i) => ({ + label: `Option ${i+1}: ${s.name}`, + description: `${s.effort} effort, ${s.risk} risk` + })).concat([ + { label: "Need More Analysis", description: "Return to Phase 2" } + ]) + }, + { + question: "Execution method:", + header: "Execution", + multiSelect: false, + options: [ + { label: "Agent", description: "@code-developer agent" }, + { label: "Codex", description: "codex CLI tool" }, + { label: "Auto", description: "Auto-select based on complexity" } + ] + }, + { + question: "Code review after execution?", + header: "Review", + multiSelect: false, + options: [ + { label: "Skip", description: "No review" }, + { label: "Gemini Review", description: "Gemini CLI tool" }, + { label: "Codex Review", description: "codex review --uncommitted" }, + { label: "Agent Review", description: "Current agent review" } + ] + } + ] +}) +``` + +**Routing**: +- Approve + execution method → Phase 5 +- Need More Analysis → Phase 2 with feedback +- Cancel → Save session for resumption + +**TodoWrite Update (Phase 4 Decision)**: +```javascript +const executionLabel = userSelection.execution_method // "Agent" / "Codex" / "Auto" + +TodoWrite({ todos: [ + { content: "Phase 1: Context Gathering", status: "completed", activeForm: "Gathering context" }, + { content: "Phase 2: Multi-CLI Discussion", status: "completed", activeForm: "Running discussion" }, + { content: "Phase 3: Present Options", status: "completed", activeForm: "Presenting options" }, + { content: `Phase 4: User Decision [${executionLabel}]`, status: "completed", activeForm: "Decision recorded" }, + { content: `Phase 5: Plan Generation [${executionLabel}]`, status: "in_progress", activeForm: `Generating plan [${executionLabel}]` } +]}) +``` + +### Phase 5: Plan Generation & Execution Handoff + +**Step 1: Build Context-Package** (Orchestrator responsibility): +```javascript +// Extract key information from user decision and synthesis +const contextPackage = { + // Core solution details + solution: { + name: selectedSolution.name, + source_cli: selectedSolution.source_cli, + feasibility: selectedSolution.feasibility, + effort: selectedSolution.effort, + risk: selectedSolution.risk, + summary: selectedSolution.summary + }, + // Implementation plan (tasks, flow, milestones) + implementation_plan: selectedSolution.implementation_plan, + // Dependencies + dependencies: selectedSolution.dependencies || { internal: [], external: [] }, + // Technical concerns + technical_concerns: selectedSolution.technical_concerns || [], + // Consensus from cross-verification + consensus: { + agreements: synthesis.cross_verification.agreements, + resolved_conflicts: synthesis.cross_verification.resolution + }, + // User constraints (from Phase 4 feedback) + constraints: userConstraints || [], + // Task context + task_description: taskDescription, + session_id: sessionId +} + +// Write context-package for traceability +Write(`${sessionFolder}/context-package.json`, JSON.stringify(contextPackage, null, 2)) +``` + +**Step 2: Invoke Planning Agent**: +```javascript +Agent({ + subagent_type: "cli-lite-planning-agent", + run_in_background: false, + description: "Generate implementation plan", + prompt: ` +## Schema Reference +Execute: cat ~/.ccw/workflows/cli-templates/schemas/plan-overview-base-schema.json +Execute: cat ~/.ccw/workflows/cli-templates/schemas/task-schema.json + +## Output Format: Two-Layer Structure +- plan.json: Overview with task_ids[] referencing .task/ files (NO tasks[] array) +- .task/TASK-*.json: Independent task files following task-schema.json + +plan.json required: summary, approach, task_ids, task_count, _metadata (with plan_type) +Task files required: id, title, description, depends_on, convergence (with criteria[]) +Task fields: files[].change (not modification_points), convergence.criteria (not acceptance), test (not verification) + +## Context-Package (from orchestrator) +${JSON.stringify(contextPackage, null, 2)} + +## Execution Process +1. Read plan-overview-base-schema.json + task-schema.json for output structure +2. Read project-tech.json and specs/*.md +3. Parse context-package fields: + - solution: name, feasibility, summary + - implementation_plan: tasks[], execution_flow, milestones + - dependencies: internal[], external[] + - technical_concerns: risks/blockers + - consensus: agreements, resolved_conflicts + - constraints: user requirements +4. Use implementation_plan.tasks[] as task foundation +5. Preserve task dependencies (depends_on) and execution_flow +6. Expand tasks with convergence.criteria (testable completion conditions) +7. Create .task/ directory and write individual TASK-*.json files +8. Generate plan.json with task_ids[] referencing .task/ files + +## Output +- ${sessionFolder}/plan.json (overview with task_ids[]) +- ${sessionFolder}/.task/TASK-*.json (independent task files) + +## Completion Checklist +- [ ] plan.json has task_ids[] and task_count (NO embedded tasks[]) +- [ ] .task/*.json files preserve task dependencies from implementation_plan +- [ ] Task execution order follows execution_flow +- [ ] Key_points reflected in task descriptions +- [ ] User constraints applied to implementation +- [ ] convergence.criteria are testable +- [ ] plan.json follows plan-overview-base-schema.json +- [ ] Task files follow task-schema.json +` +}) +``` + +**Step 3: Build executionContext**: +```javascript +// After plan.json is generated by cli-lite-planning-agent +const plan = JSON.parse(Read(`${sessionFolder}/plan.json`)) + +// Load task files from .task/ directory (two-layer format) +const taskFiles = plan.task_ids.map(id => `${sessionFolder}/.task/${id}.json`) + +// Build executionContext (same structure as lite-plan) +executionContext = { + planObject: plan, + taskFiles: taskFiles, // Paths to .task/*.json files (two-layer format) + explorationsContext: null, // Multi-CLI doesn't use exploration files + explorationAngles: [], // No exploration angles + explorationManifest: null, // No manifest + clarificationContext: null, // Store user feedback from Phase 2 if exists + executionMethod: userSelection.execution_method, // From Phase 4 + codeReviewTool: userSelection.code_review_tool, // From Phase 4 + originalUserInput: taskDescription, + + // Optional: Task-level executor assignments + executorAssignments: null, // Could be enhanced in future + + session: { + id: sessionId, + folder: sessionFolder, + artifacts: { + explorations: [], // No explorations in multi-CLI workflow + explorations_manifest: null, + plan: `${sessionFolder}/plan.json`, + task_dir: plan.task_ids ? `${sessionFolder}/.task/` : null, + synthesis_rounds: Array.from({length: currentRound}, (_, i) => + `${sessionFolder}/rounds/${i+1}/synthesis.json` + ), + context_package: `${sessionFolder}/context-package.json` + } + } +} +``` + +**Step 4: Hand off to Execution**: +```javascript +// Skill handoff: Invoke workflow-lite-execute with in-memory context +Skill({ + skill: "workflow-lite-execute", + args: "--in-memory" +}) +// executionContext is passed via global variable to workflow-lite-execute (Mode 1: In-Memory Plan) +``` + +## Output File Structure + +``` +.workflow/.multi-cli-plan/{MCP-task-slug-YYYY-MM-DD}/ +├── session-state.json # Session tracking (orchestrator) +├── rounds/ +│ ├── 1/synthesis.json # Round 1 analysis (cli-discuss-agent) +│ ├── 2/synthesis.json # Round 2 analysis (cli-discuss-agent) +│ └── .../ +├── context-package.json # Extracted context for planning (orchestrator) +├── plan.json # Plan overview with task_ids[] (NO embedded tasks[]) +└── .task/ # Independent task files + ├── TASK-001.json # Task file following task-schema.json + ├── TASK-002.json + └── ... +``` + +## synthesis.json Schema + +```json +{ + "round": 1, + "solutions": [{ + "name": "Solution Name", + "source_cli": ["gemini", "codex"], + "feasibility": 0.85, + "effort": "low|medium|high", + "risk": "low|medium|high", + "summary": "Brief analysis summary", + "implementation_plan": { + "approach": "High-level technical approach", + "tasks": [ + {"id": "T1", "name": "Task", "depends_on": [], "files": [], "key_point": "..."} + ], + "execution_flow": "T1 → T2 → T3", + "milestones": ["Checkpoint 1", "Checkpoint 2"] + }, + "dependencies": {"internal": [], "external": []}, + "technical_concerns": ["Risk 1", "Blocker 2"] + }], + "convergence": { + "score": 0.85, + "new_insights": false, + "recommendation": "converged|continue|user_input_needed" + }, + "cross_verification": { + "agreements": [], + "disagreements": [], + "resolution": "..." + }, + "clarification_questions": [] +} +``` + +## TodoWrite Structure + +**Initialization**: +```javascript +TodoWrite({ todos: [ + { content: "Phase 1: Context Gathering", status: "in_progress", activeForm: "Gathering context" }, + { content: "Phase 2: Multi-CLI Discussion", status: "pending", activeForm: "Running discussion" }, + { content: "Phase 3: Present Options", status: "pending", activeForm: "Presenting options" }, + { content: "Phase 4: User Decision", status: "pending", activeForm: "Awaiting decision" }, + { content: "Phase 5: Plan Generation", status: "pending", activeForm: "Generating plan" } +]}) +``` + +## Error Handling + +| Error | Resolution | +|-------|------------| +| ACE search fails | Fall back to Glob/Grep for file discovery | +| Agent fails | Retry once, then present partial results | +| CLI timeout (in agent) | Agent uses fallback: gemini → codex → claude | +| No convergence | Present best options, flag uncertainty | +| synthesis.json parse error | Request agent retry | +| User cancels | Save session for later resumption | + +## Configuration + +| Flag | Default | Description | +|------|---------|-------------| +| `--max-rounds` | 3 | Maximum discussion rounds | +| `--tools` | gemini,codex | CLI tools for analysis | +| `--mode` | parallel | Execution mode: parallel or serial | +| `--auto-execute` | false | Auto-execute after approval | + +## Related Commands + +```bash +# Simpler single-round planning +/workflow-lite-plan "task description" + +# Issue-driven discovery +/issue:discover-by-prompt "find issues" + +# View session files +cat .workflow/.multi-cli-plan/{session-id}/plan.json +cat .workflow/.multi-cli-plan/{session-id}/rounds/1/synthesis.json +cat .workflow/.multi-cli-plan/{session-id}/context-package.json +``` + +## Next Phase + +Auto-continue via `Skill({ skill: "workflow-lite-execute", args: "--in-memory" })` with executionContext. diff --git a/.claude/skills/workflow-multi-cli-plan/phases/01-multi-cli-plan.md b/.claude/skills/workflow-multi-cli-plan/phases/01-multi-cli-plan.md deleted file mode 100644 index 40d9b269..00000000 --- a/.claude/skills/workflow-multi-cli-plan/phases/01-multi-cli-plan.md +++ /dev/null @@ -1,620 +0,0 @@ -# Phase 1: Multi-CLI Collaborative Planning - -Complete multi-CLI collaborative planning pipeline with ACE context gathering and iterative cross-verification. This phase document preserves the full content of the original `workflow-multi-cli-plan` command. - -## Auto Mode - -When `workflowPreferences.autoYes` is true: Auto-approve plan, use recommended solution and execution method (Agent, Skip review). - -# Multi-CLI Collaborative Planning Command - -## Quick Start - -```bash -# Basic usage -/workflow-multi-cli-plan "Implement user authentication" - -# With options -/workflow-multi-cli-plan "Add dark mode support" --max-rounds=3 -/workflow-multi-cli-plan "Refactor payment module" --tools=gemini,codex,claude -/workflow-multi-cli-plan "Fix memory leak" --mode=serial -``` - -**Context Source**: ACE semantic search + Multi-CLI analysis -**Output Directory**: `.workflow/.multi-cli-plan/{session-id}/` -**Default Max Rounds**: 3 (convergence may complete earlier) -**CLI Tools**: @cli-discuss-agent (analysis), @cli-lite-planning-agent (plan generation) -**Execution**: Auto-hands off to Phase 2 (lite-execute) after plan approval - -## What & Why - -### Core Concept - -Multi-CLI collaborative planning with **three-phase architecture**: ACE context gathering → Iterative multi-CLI discussion → Plan generation. Orchestrator delegates analysis to agents, only handles user decisions and session management. - -**Process**: -- **Phase 1**: ACE semantic search gathers codebase context -- **Phase 2**: cli-discuss-agent orchestrates Gemini/Codex/Claude for cross-verified analysis -- **Phase 3-5**: User decision → Plan generation → Execution handoff - -**vs Single-CLI Planning**: -- **Single**: One model perspective, potential blind spots -- **Multi-CLI**: Cross-verification catches inconsistencies, builds consensus on solutions - -### Value Proposition - -1. **Multi-Perspective Analysis**: Gemini + Codex + Claude analyze from different angles -2. **Cross-Verification**: Identify agreements/disagreements, build confidence -3. **User-Driven Decisions**: Every round ends with user decision point -4. **Iterative Convergence**: Progressive refinement until consensus reached - -### Orchestrator Boundary (CRITICAL) - -- **ONLY command** for multi-CLI collaborative planning -- Manages: Session state, user decisions, agent delegation, phase transitions -- Delegates: CLI execution to @cli-discuss-agent, plan generation to @cli-lite-planning-agent - -### Execution Flow - -``` -Phase 1: Context Gathering - └─ ACE semantic search, extract keywords, build context package - -Phase 2: Multi-CLI Discussion (Iterative, via @cli-discuss-agent) - ├─ Round N: Agent executes Gemini + Codex + Claude - ├─ Cross-verify findings, synthesize solutions - ├─ Write synthesis.json to rounds/{N}/ - └─ Loop until convergence or max rounds - -Phase 3: Present Options - └─ Display solutions with trade-offs from agent output - -Phase 4: User Decision - ├─ Select solution approach - ├─ Select execution method (Agent/Codex/Auto) - ├─ Select code review tool (Skip/Gemini/Codex/Agent) - └─ Route: - ├─ Approve → Phase 5 - ├─ Need More Analysis → Return to Phase 2 - └─ Cancel → Save session - -Phase 5: Plan Generation & Execution Handoff - ├─ Generate plan.json + .task/*.json (via @cli-lite-planning-agent, two-layer output) - ├─ Build executionContext with user selections and taskFiles - └─ Execute via Phase 2 (lite-execute) -``` - -### Agent Roles - -| Agent | Responsibility | -|-------|---------------| -| **Orchestrator** | Session management, ACE context, user decisions, phase transitions, executionContext assembly | -| **@cli-discuss-agent** | Multi-CLI execution (Gemini/Codex/Claude), cross-verification, solution synthesis, synthesis.json output | -| **@cli-lite-planning-agent** | Task decomposition, two-layer output: plan.json (overview with task_ids[]) + .task/*.json (task files) | - -## Core Responsibilities - -### Phase 1: Context Gathering - -**Session Initialization**: -```javascript -const sessionId = `MCP-${taskSlug}-${date}` -const sessionFolder = `.workflow/.multi-cli-plan/${sessionId}` -Bash(`mkdir -p ${sessionFolder}/rounds`) -``` - -**ACE Context Queries**: -```javascript -const aceQueries = [ - `Project architecture related to ${keywords}`, - `Existing implementations of ${keywords[0]}`, - `Code patterns for ${keywords} features`, - `Integration points for ${keywords[0]}` -] -// Execute via mcp__ace-tool__search_context -``` - -**Context Package** (passed to agent): -- `relevant_files[]` - Files identified by ACE -- `detected_patterns[]` - Code patterns found -- `architecture_insights` - Structure understanding - -### Phase 2: Agent Delegation - -**Core Principle**: Orchestrator only delegates and reads output - NO direct CLI execution. - -**⚠️ CRITICAL - CLI EXECUTION REQUIREMENT**: -- **MUST** execute CLI calls via `Bash` with `run_in_background: true` -- **MUST** wait for hook callback to receive complete results -- **MUST NOT** proceed with next phase until CLI execution fully completes -- Do NOT use `TaskOutput` polling during CLI execution - wait passively for results -- Minimize scope: Proceed only when 100% result available - -**Agent Invocation**: -```javascript -Agent({ - subagent_type: "cli-discuss-agent", - run_in_background: false, - description: `Discussion round ${currentRound}`, - prompt: ` -## Input Context -- task_description: ${taskDescription} -- round_number: ${currentRound} -- session: { id: "${sessionId}", folder: "${sessionFolder}" } -- ace_context: ${JSON.stringify(contextPackageage)} -- previous_rounds: ${JSON.stringify(analysisResults)} -- user_feedback: ${userFeedback || 'None'} -- cli_config: { tools: ["gemini", "codex"], mode: "parallel", fallback_chain: ["gemini", "codex", "claude"] } - -## Execution Process -1. Parse input context (handle JSON strings) -2. Check if ACE supplementary search needed -3. Build CLI prompts with context -4. Execute CLIs (parallel or serial per cli_config.mode) -5. Parse CLI outputs, handle failures with fallback -6. Perform cross-verification between CLI results -7. Synthesize solutions, calculate scores -8. Calculate convergence, generate clarification questions -9. Write synthesis.json - -## Output -Write: ${sessionFolder}/rounds/${currentRound}/synthesis.json - -## Completion Checklist -- [ ] All configured CLI tools executed (or fallback triggered) -- [ ] Cross-verification completed with agreements/disagreements -- [ ] 2-3 solutions generated with file:line references -- [ ] Convergence score calculated (0.0-1.0) -- [ ] synthesis.json written with all Primary Fields -` -}) -``` - -**Read Agent Output**: -```javascript -const synthesis = JSON.parse(Read(`${sessionFolder}/rounds/${round}/synthesis.json`)) -// Access top-level fields: solutions, convergence, cross_verification, clarification_questions -``` - -**Convergence Decision**: -```javascript -if (synthesis.convergence.recommendation === 'converged') { - // Proceed to Phase 3 -} else if (synthesis.convergence.recommendation === 'user_input_needed') { - // Collect user feedback, return to Phase 2 -} else { - // Continue to next round if new_insights && round < maxRounds -} -``` - -### Phase 3: Present Options - -**Display from Agent Output** (no processing): -```javascript -console.log(` -## Solution Options - -${synthesis.solutions.map((s, i) => ` -**Option ${i+1}: ${s.name}** -Source: ${s.source_cli.join(' + ')} -Effort: ${s.effort} | Risk: ${s.risk} - -Pros: ${s.pros.join(', ')} -Cons: ${s.cons.join(', ')} - -Files: ${s.affected_files.slice(0,3).map(f => `${f.file}:${f.line}`).join(', ')} -`).join('\n')} - -## Cross-Verification -Agreements: ${synthesis.cross_verification.agreements.length} -Disagreements: ${synthesis.cross_verification.disagreements.length} -`) -``` - -### Phase 4: User Decision - -**Decision Options**: -```javascript -AskUserQuestion({ - questions: [ - { - question: "Which solution approach?", - header: "Solution", - multiSelect: false, - options: solutions.map((s, i) => ({ - label: `Option ${i+1}: ${s.name}`, - description: `${s.effort} effort, ${s.risk} risk` - })).concat([ - { label: "Need More Analysis", description: "Return to Phase 2" } - ]) - }, - { - question: "Execution method:", - header: "Execution", - multiSelect: false, - options: [ - { label: "Agent", description: "@code-developer agent" }, - { label: "Codex", description: "codex CLI tool" }, - { label: "Auto", description: "Auto-select based on complexity" } - ] - }, - { - question: "Code review after execution?", - header: "Review", - multiSelect: false, - options: [ - { label: "Skip", description: "No review" }, - { label: "Gemini Review", description: "Gemini CLI tool" }, - { label: "Codex Review", description: "codex review --uncommitted" }, - { label: "Agent Review", description: "Current agent review" } - ] - } - ] -}) -``` - -**Routing**: -- Approve + execution method → Phase 5 -- Need More Analysis → Phase 2 with feedback -- Cancel → Save session for resumption - -**TodoWrite Update (Phase 4 Decision)**: -```javascript -const executionLabel = userSelection.execution_method // "Agent" / "Codex" / "Auto" - -TodoWrite({ todos: [ - { content: "Phase 1: Context Gathering", status: "completed", activeForm: "Gathering context" }, - { content: "Phase 2: Multi-CLI Discussion", status: "completed", activeForm: "Running discussion" }, - { content: "Phase 3: Present Options", status: "completed", activeForm: "Presenting options" }, - { content: `Phase 4: User Decision [${executionLabel}]`, status: "completed", activeForm: "Decision recorded" }, - { content: `Phase 5: Plan Generation [${executionLabel}]`, status: "in_progress", activeForm: `Generating plan [${executionLabel}]` } -]}) -``` - -### Phase 5: Plan Generation & Execution Handoff - -**Step 1: Build Context-Package** (Orchestrator responsibility): -```javascript -// Extract key information from user decision and synthesis -const contextPackage = { - // Core solution details - solution: { - name: selectedSolution.name, - source_cli: selectedSolution.source_cli, - feasibility: selectedSolution.feasibility, - effort: selectedSolution.effort, - risk: selectedSolution.risk, - summary: selectedSolution.summary - }, - // Implementation plan (tasks, flow, milestones) - implementation_plan: selectedSolution.implementation_plan, - // Dependencies - dependencies: selectedSolution.dependencies || { internal: [], external: [] }, - // Technical concerns - technical_concerns: selectedSolution.technical_concerns || [], - // Consensus from cross-verification - consensus: { - agreements: synthesis.cross_verification.agreements, - resolved_conflicts: synthesis.cross_verification.resolution - }, - // User constraints (from Phase 4 feedback) - constraints: userConstraints || [], - // Task context - task_description: taskDescription, - session_id: sessionId -} - -// Write context-package for traceability -Write(`${sessionFolder}/context-package.json`, JSON.stringify(contextPackage, null, 2)) -``` - -**Context-Package Schema**: - -| Field | Type | Description | -|-------|------|-------------| -| `solution` | object | User-selected solution from synthesis | -| `solution.name` | string | Solution identifier | -| `solution.feasibility` | number | Viability score (0-1) | -| `solution.summary` | string | Brief analysis summary | -| `implementation_plan` | object | Task breakdown with flow and dependencies | -| `implementation_plan.approach` | string | High-level technical strategy | -| `implementation_plan.tasks[]` | array | Discrete tasks with id, name, depends_on, files | -| `implementation_plan.execution_flow` | string | Task sequence (e.g., "T1 → T2 → T3") | -| `implementation_plan.milestones` | string[] | Key checkpoints | -| `dependencies` | object | Module and package dependencies | -| `technical_concerns` | string[] | Risks and blockers | -| `consensus` | object | Cross-verified agreements from multi-CLI | -| `constraints` | string[] | User-specified constraints from Phase 4 | - -```json -{ - "solution": { - "name": "Strategy Pattern Refactoring", - "source_cli": ["gemini", "codex"], - "feasibility": 0.88, - "effort": "medium", - "risk": "low", - "summary": "Extract payment gateway interface, implement strategy pattern for multi-gateway support" - }, - "implementation_plan": { - "approach": "Define interface → Create concrete strategies → Implement factory → Migrate existing code", - "tasks": [ - {"id": "T1", "name": "Define PaymentGateway interface", "depends_on": [], "files": [{"file": "src/types/payment.ts", "line": 1, "action": "create"}], "key_point": "Include all existing Stripe methods"}, - {"id": "T2", "name": "Implement StripeGateway", "depends_on": ["T1"], "files": [{"file": "src/payment/stripe.ts", "line": 1, "action": "create"}], "key_point": "Wrap existing logic"}, - {"id": "T3", "name": "Create GatewayFactory", "depends_on": ["T1"], "files": [{"file": "src/payment/factory.ts", "line": 1, "action": "create"}], "key_point": null}, - {"id": "T4", "name": "Migrate processor to use factory", "depends_on": ["T2", "T3"], "files": [{"file": "src/payment/processor.ts", "line": 45, "action": "modify"}], "key_point": "Backward compatible"} - ], - "execution_flow": "T1 → (T2 | T3) → T4", - "milestones": ["Interface defined", "Gateway implementations complete", "Migration done"] - }, - "dependencies": { - "internal": ["@/lib/payment-gateway", "@/types/payment"], - "external": ["stripe@^14.0.0"] - }, - "technical_concerns": ["Existing tests must pass", "No breaking API changes"], - "consensus": { - "agreements": ["Use strategy pattern", "Keep existing API"], - "resolved_conflicts": "Factory over DI for simpler integration" - }, - "constraints": ["backward compatible", "no breaking changes to PaymentResult type"], - "task_description": "Refactor payment processing for multi-gateway support", - "session_id": "MCP-payment-refactor-2026-01-14" -} -``` - -**Step 2: Invoke Planning Agent**: -```javascript -Agent({ - subagent_type: "cli-lite-planning-agent", - run_in_background: false, - description: "Generate implementation plan", - prompt: ` -## Schema Reference -Execute: cat ~/.ccw/workflows/cli-templates/schemas/plan-overview-base-schema.json -Execute: cat ~/.ccw/workflows/cli-templates/schemas/task-schema.json - -## Output Format: Two-Layer Structure -- plan.json: Overview with task_ids[] referencing .task/ files (NO tasks[] array) -- .task/TASK-*.json: Independent task files following task-schema.json - -plan.json required: summary, approach, task_ids, task_count, _metadata (with plan_type) -Task files required: id, title, description, depends_on, convergence (with criteria[]) -Task fields: files[].change (not modification_points), convergence.criteria (not acceptance), test (not verification) - -## Context-Package (from orchestrator) -${JSON.stringify(contextPackage, null, 2)} - -## Execution Process -1. Read plan-overview-base-schema.json + task-schema.json for output structure -2. Read project-tech.json and specs/*.md -3. Parse context-package fields: - - solution: name, feasibility, summary - - implementation_plan: tasks[], execution_flow, milestones - - dependencies: internal[], external[] - - technical_concerns: risks/blockers - - consensus: agreements, resolved_conflicts - - constraints: user requirements -4. Use implementation_plan.tasks[] as task foundation -5. Preserve task dependencies (depends_on) and execution_flow -6. Expand tasks with convergence.criteria (testable completion conditions) -7. Create .task/ directory and write individual TASK-*.json files -8. Generate plan.json with task_ids[] referencing .task/ files - -## Output -- ${sessionFolder}/plan.json (overview with task_ids[]) -- ${sessionFolder}/.task/TASK-*.json (independent task files) - -## Completion Checklist -- [ ] plan.json has task_ids[] and task_count (NO embedded tasks[]) -- [ ] .task/*.json files preserve task dependencies from implementation_plan -- [ ] Task execution order follows execution_flow -- [ ] Key_points reflected in task descriptions -- [ ] User constraints applied to implementation -- [ ] convergence.criteria are testable -- [ ] plan.json follows plan-overview-base-schema.json -- [ ] Task files follow task-schema.json -` -}) -``` - -**Step 3: Build executionContext**: -```javascript -// After plan.json is generated by cli-lite-planning-agent -const plan = JSON.parse(Read(`${sessionFolder}/plan.json`)) - -// Load task files from .task/ directory (two-layer format) -const taskFiles = plan.task_ids.map(id => `${sessionFolder}/.task/${id}.json`) - -// Build executionContext (same structure as lite-plan) -executionContext = { - planObject: plan, - taskFiles: taskFiles, // Paths to .task/*.json files (two-layer format) - explorationsContext: null, // Multi-CLI doesn't use exploration files - explorationAngles: [], // No exploration angles - explorationManifest: null, // No manifest - clarificationContext: null, // Store user feedback from Phase 2 if exists - executionMethod: userSelection.execution_method, // From Phase 4 - codeReviewTool: userSelection.code_review_tool, // From Phase 4 - originalUserInput: taskDescription, - - // Optional: Task-level executor assignments - executorAssignments: null, // Could be enhanced in future - - session: { - id: sessionId, - folder: sessionFolder, - artifacts: { - explorations: [], // No explorations in multi-CLI workflow - explorations_manifest: null, - plan: `${sessionFolder}/plan.json`, - task_dir: plan.task_ids ? `${sessionFolder}/.task/` : null, - synthesis_rounds: Array.from({length: currentRound}, (_, i) => - `${sessionFolder}/rounds/${i+1}/synthesis.json` - ), - context_package: `${sessionFolder}/context-package.json` - } - } -} -``` - -**Step 4: Hand off to Execution**: -```javascript -// Skill handoff: Invoke workflow-lite-execute with in-memory context -Skill({ - skill: "workflow-lite-execute", - args: "--in-memory" -}) -// executionContext is passed via global variable to workflow-lite-execute (Mode 1: In-Memory Plan) -``` - -## Output File Structure - -``` -.workflow/.multi-cli-plan/{MCP-task-slug-YYYY-MM-DD}/ -├── session-state.json # Session tracking (orchestrator) -├── rounds/ -│ ├── 1/synthesis.json # Round 1 analysis (cli-discuss-agent) -│ ├── 2/synthesis.json # Round 2 analysis (cli-discuss-agent) -│ └── .../ -├── context-package.json # Extracted context for planning (orchestrator) -├── plan.json # Plan overview with task_ids[] (NO embedded tasks[]) -└── .task/ # Independent task files - ├── TASK-001.json # Task file following task-schema.json - ├── TASK-002.json - └── ... -``` - -**File Producers**: - -| File | Producer | Content | -|------|----------|---------| -| `session-state.json` | Orchestrator | Session metadata, rounds, decisions | -| `rounds/*/synthesis.json` | cli-discuss-agent | Solutions, convergence, cross-verification | -| `context-package.json` | Orchestrator | Extracted solution, dependencies, consensus for planning | -| `plan.json` | cli-lite-planning-agent | Plan overview with task_ids[] referencing .task/ files | -| `.task/*.json` | cli-lite-planning-agent | Independent task files following task-schema.json | - -## synthesis.json Schema - -```json -{ - "round": 1, - "solutions": [{ - "name": "Solution Name", - "source_cli": ["gemini", "codex"], - "feasibility": 0.85, - "effort": "low|medium|high", - "risk": "low|medium|high", - "summary": "Brief analysis summary", - "implementation_plan": { - "approach": "High-level technical approach", - "tasks": [ - {"id": "T1", "name": "Task", "depends_on": [], "files": [], "key_point": "..."} - ], - "execution_flow": "T1 → T2 → T3", - "milestones": ["Checkpoint 1", "Checkpoint 2"] - }, - "dependencies": {"internal": [], "external": []}, - "technical_concerns": ["Risk 1", "Blocker 2"] - }], - "convergence": { - "score": 0.85, - "new_insights": false, - "recommendation": "converged|continue|user_input_needed" - }, - "cross_verification": { - "agreements": [], - "disagreements": [], - "resolution": "..." - }, - "clarification_questions": [] -} -``` - -**Key Planning Fields**: - -| Field | Purpose | -|-------|---------| -| `feasibility` | Viability score (0-1) | -| `implementation_plan.tasks[]` | Discrete tasks with dependencies | -| `implementation_plan.execution_flow` | Task sequence visualization | -| `implementation_plan.milestones` | Key checkpoints | -| `technical_concerns` | Risks and blockers | - -**Note**: Solutions ranked by internal scoring (array order = priority) - -## TodoWrite Structure - -**Initialization**: -```javascript -TodoWrite({ todos: [ - { content: "Phase 1: Context Gathering", status: "in_progress", activeForm: "Gathering context" }, - { content: "Phase 2: Multi-CLI Discussion", status: "pending", activeForm: "Running discussion" }, - { content: "Phase 3: Present Options", status: "pending", activeForm: "Presenting options" }, - { content: "Phase 4: User Decision", status: "pending", activeForm: "Awaiting decision" }, - { content: "Phase 5: Plan Generation", status: "pending", activeForm: "Generating plan" } -]}) -``` - -**During Discussion Rounds**: -```javascript -TodoWrite({ todos: [ - { content: "Phase 1: Context Gathering", status: "completed", activeForm: "Gathering context" }, - { content: "Phase 2: Multi-CLI Discussion", status: "in_progress", activeForm: "Running discussion" }, - { content: " → Round 1: Initial analysis", status: "completed", activeForm: "Analyzing" }, - { content: " → Round 2: Deep verification", status: "in_progress", activeForm: "Verifying" }, - { content: "Phase 3: Present Options", status: "pending", activeForm: "Presenting options" }, - // ... -]}) -``` - -## Error Handling - -| Error | Resolution | -|-------|------------| -| ACE search fails | Fall back to Glob/Grep for file discovery | -| Agent fails | Retry once, then present partial results | -| CLI timeout (in agent) | Agent uses fallback: gemini → codex → claude | -| No convergence | Present best options, flag uncertainty | -| synthesis.json parse error | Request agent retry | -| User cancels | Save session for later resumption | - -## Configuration - -| Flag | Default | Description | -|------|---------|-------------| -| `--max-rounds` | 3 | Maximum discussion rounds | -| `--tools` | gemini,codex | CLI tools for analysis | -| `--mode` | parallel | Execution mode: parallel or serial | -| `--auto-execute` | false | Auto-execute after approval | - -## Best Practices - -1. **Be Specific**: Detailed task descriptions improve ACE context quality -2. **Provide Feedback**: Use clarification rounds to refine requirements -3. **Trust Cross-Verification**: Multi-CLI consensus indicates high confidence -4. **Review Trade-offs**: Consider pros/cons before selecting solution -5. **Check synthesis.json**: Review agent output for detailed analysis -6. **Iterate When Needed**: Don't hesitate to request more analysis - -## Related Commands - -```bash -# Simpler single-round planning -/workflow-lite-planex "task description" - -# Issue-driven discovery -/issue:discover-by-prompt "find issues" - -# View session files -cat .workflow/.multi-cli-plan/{session-id}/plan.json -cat .workflow/.multi-cli-plan/{session-id}/rounds/1/synthesis.json -cat .workflow/.multi-cli-plan/{session-id}/context-package.json - -# Direct execution (if you have plan.json) -# Use workflow-lite-planex or workflow-multi-cli-plan (execution is integrated) -``` - -## Next Phase - -Return to orchestrator, then auto-continue via `Skill({ skill: "workflow-lite-execute", args: "--in-memory" })` with executionContext. diff --git a/.claude/skills/workflow-skill-designer/SKILL.md b/.claude/skills/workflow-skill-designer/SKILL.md index aef8d4f1..188dca1f 100644 --- a/.claude/skills/workflow-skill-designer/SKILL.md +++ b/.claude/skills/workflow-skill-designer/SKILL.md @@ -141,7 +141,7 @@ Read("phases/02-lite-execute.md") // Execute with executionContext (Mode 1) // WRONG: Skill routing (unnecessary round-trip) -Skill(skill="workflow-lite-planex", args="--in-memory") +Skill(skill="workflow-lite-plan", args="--in-memory") ``` ### Pattern 8: Phase File Hygiene diff --git a/.claude/skills/workflow-skill-designer/phases/03-phase-design.md b/.claude/skills/workflow-skill-designer/phases/03-phase-design.md index 1ded9b43..6de35938 100644 --- a/.claude/skills/workflow-skill-designer/phases/03-phase-design.md +++ b/.claude/skills/workflow-skill-designer/phases/03-phase-design.md @@ -60,7 +60,7 @@ Read("phases/02-lite-execute.md") // Execute with executionContext (Mode 1) // WRONG: Skill routing (unnecessary round-trip) -Skill(skill="workflow-lite-planex", args="--in-memory") +Skill(skill="workflow-lite-plan", args="--in-memory") ``` ### Content Restriction Enforcement diff --git a/.codex/agents/cli-explore-agent.md b/.codex/agents/cli-explore-agent.md index 5859d16a..cb414f5e 100644 --- a/.codex/agents/cli-explore-agent.md +++ b/.codex/agents/cli-explore-agent.md @@ -204,7 +204,7 @@ Brief summary: ## Post-Exploration: Exploration Notes (Generated by Orchestrator) -**Note**: This section is executed by the orchestrator (workflow-lite-planex) after all cli-explore-agents complete, NOT by this agent. +**Note**: This section is executed by the orchestrator (workflow-lite-plan) after all cli-explore-agents complete, NOT by this agent. **Trigger**: After all exploration-{angle}.json files are generated diff --git a/.codex/skills/brainstorm-with-file/SKILL.md b/.codex/skills/brainstorm-with-file/SKILL.md index e2c0805a..db5a52e1 100644 --- a/.codex/skills/brainstorm-with-file/SKILL.md +++ b/.codex/skills/brainstorm-with-file/SKILL.md @@ -800,7 +800,7 @@ Offer user follow-up actions based on brainstorming results. | Option | Purpose | Action | |--------|---------|--------| -| **创建实施计划** | Plan implementation of top idea | Launch `workflow-lite-planex` | +| **创建实施计划** | Plan implementation of top idea | Launch `workflow-lite-plan` | | **创建Issue** | Track top ideas for later | Launch `issue:new` with ideas | | **深入分析** | Analyze top idea in detail | Launch `workflow:analyze-with-file` | | **导出分享** | Generate shareable report | Create formatted report document | diff --git a/.codex/skills/csv-wave-pipeline/SKILL.md b/.codex/skills/csv-wave-pipeline/SKILL.md index 7bd3c067..fabd85ae 100644 --- a/.codex/skills/csv-wave-pipeline/SKILL.md +++ b/.codex/skills/csv-wave-pipeline/SKILL.md @@ -903,4 +903,4 @@ Wave 3 agents: | Linear pipeline (A→B→C) | `$csv-wave-pipeline -c 1` — 3 waves, serial, full context | | Diamond dependency (A→B,C→D) | `$csv-wave-pipeline` — 3 waves, B+C concurrent in wave 2 | | Complex requirement, unclear tasks | Use `$roadmap-with-file` first for planning, then feed issues here | -| Single complex task | Use `$workflow-lite-planex` instead | +| Single complex task | Use `$workflow-lite-plan` instead | diff --git a/.codex/skills/roadmap-with-file/SKILL.md b/.codex/skills/roadmap-with-file/SKILL.md index 7b22ee73..29d7f060 100644 --- a/.codex/skills/roadmap-with-file/SKILL.md +++ b/.codex/skills/roadmap-with-file/SKILL.md @@ -896,7 +896,7 @@ ${selectedMode === 'progressive' ? `**Progressive Mode**: | Quick task breakdown, immediate execution | `$lite-plan` | | Collaborative multi-agent planning | `$collaborative-plan-with-file` | | Full specification documents | `$spec-generator` | -| Code implementation from existing plan | `$workflow-lite-planex` | +| Code implementation from existing plan | `$workflow-lite-plan` | --- diff --git a/.codex/skills/workflow-lite-planex/SKILL.md b/.codex/skills/workflow-lite-planex/SKILL.md index 83a6cdaf..5ef264ef 100644 --- a/.codex/skills/workflow-lite-planex/SKILL.md +++ b/.codex/skills/workflow-lite-planex/SKILL.md @@ -1,5 +1,5 @@ --- -name: workflow-lite-planex +name: workflow-lite-plan description: Explore-first wave pipeline. Decomposes requirement into exploration angles, runs wave exploration via spawn_agents_on_csv, synthesizes findings into execution tasks with cross-phase context linking (E*→T*), then wave-executes via spawn_agents_on_csv. argument-hint: "[-y|--yes] [-c|--concurrency N] [--continue] \"requirement description\"" allowed-tools: spawn_agents_on_csv, Read, Write, Edit, Bash, Glob, Grep, AskUserQuestion @@ -14,10 +14,10 @@ When `--yes` or `-y`: Auto-confirm decomposition, skip interactive validation, u ## Usage ```bash -$workflow-lite-planex "Implement user authentication with OAuth, JWT, and 2FA" -$workflow-lite-planex -c 4 "Refactor payment module with Stripe and PayPal" -$workflow-lite-planex -y "Build notification system with email and SMS" -$workflow-lite-planex --continue "auth-20260228" +$workflow-lite-plan "Implement user authentication with OAuth, JWT, and 2FA" +$workflow-lite-plan -c 4 "Refactor payment module with Stripe and PayPal" +$workflow-lite-plan -y "Build notification system with email and SMS" +$workflow-lite-plan --continue "auth-20260228" ``` **Flags**: @@ -304,7 +304,7 @@ REQUIREMENT: ${requirement}" --tool gemini --mode analysis --rule planning-break }) if (answer.Validation === "Modify") { - console.log(`Edit: ${sessionFolder}/explore.csv\nResume: $workflow-lite-planex --continue`) + console.log(`Edit: ${sessionFolder}/explore.csv\nResume: $workflow-lite-plan --continue`) return } else if (answer.Validation === "Cancel") { return @@ -599,7 +599,7 @@ ${wt.map(t => ` - [${t.id}] ${t.title} (scope: ${t.scope}, from: ${t.context_fr }) if (answer.Confirm === "Modify") { - console.log(`Edit: ${sessionFolder}/tasks.csv\nResume: $workflow-lite-planex --continue`) + console.log(`Edit: ${sessionFolder}/tasks.csv\nResume: $workflow-lite-plan --continue`) return } else if (answer.Confirm === "Cancel") { return @@ -1134,8 +1134,8 @@ All agents across all phases share `discoveries.ndjson`. This eliminates redunda | Scenario | Recommended Approach | |----------|---------------------| -| Complex feature (unclear architecture) | `$workflow-lite-planex` — explore first, then plan | -| Simple known-pattern task | `$workflow-lite-planex` — skip exploration, direct execution | -| Independent parallel tasks | `$workflow-lite-planex -c 8` — single wave, max parallelism | -| Diamond dependency (A→B,C→D) | `$workflow-lite-planex` — 3 waves with context propagation | -| Unknown codebase | `$workflow-lite-planex` — exploration phase is essential | +| Complex feature (unclear architecture) | `$workflow-lite-plan` — explore first, then plan | +| Simple known-pattern task | `$workflow-lite-plan` — skip exploration, direct execution | +| Independent parallel tasks | `$workflow-lite-plan -c 8` — single wave, max parallelism | +| Diamond dependency (A→B,C→D) | `$workflow-lite-plan` — 3 waves with context propagation | +| Unknown codebase | `$workflow-lite-plan` — exploration phase is essential | diff --git a/README.md b/README.md index 21962efe..035b7c35 100644 --- a/README.md +++ b/README.md @@ -93,7 +93,7 @@ CCW uses two types of invocations: | Type | Format | Examples | |------|--------|----------| -| **Skills** | Trigger phrase (no slash) | `workflow-lite-planex`, `brainstorm`, `workflow-plan` | +| **Skills** | Trigger phrase (no slash) | `workflow-lite-plan`, `brainstorm`, `workflow-plan` | | **Commands** | Slash command | `/ccw`, `/workflow/session:start`, `/issue/new` | ### Choose Your Workflow Skill @@ -101,7 +101,7 @@ CCW uses two types of invocations:
- + @@ -114,7 +114,7 @@ CCW uses two types of invocations: ```bash # Skill triggers (no slash - just describe what you want) -workflow-lite-planex "Add JWT authentication" +workflow-lite-plan "Add JWT authentication" workflow-plan "Implement payment gateway integration" workflow-execute @@ -278,7 +278,7 @@ ccw upgrade -a # Upgrade all installations ``` ┌─────────────────────────────────────────────────────────────────┐ │ Workflow Skills │ -│ 📝 workflow-lite-planex / workflow-multi-cli-plan (lightweight) │ +│ 📝 workflow-lite-plan / workflow-multi-cli-plan (lightweight) │ │ 📊 workflow-plan / workflow-tdd-plan (session-based) │ │ 🧪 workflow-test-fix / workflow-test-fix │ │ 🧠 brainstorm (multi-role analysis) │ @@ -322,7 +322,7 @@ Claude-Code-Workflow/ │ │ ├── memory/ # Memory commands (prepare, style-skill-memory) │ │ └── workflow/ # Workflow commands (session, ui-design, etc.) │ └── skills/ # 37 modular skills -│ ├── workflow-lite-planex/ +│ ├── workflow-lite-plan/ │ ├── workflow-plan/ │ ├── workflow-tdd-plan/ │ ├── workflow-test-fix/ diff --git a/README_CN.md b/README_CN.md index 697ac2fb..ed9f71c8 100644 --- a/README_CN.md +++ b/README_CN.md @@ -93,7 +93,7 @@ CCW 使用两种调用方式： | 类型 | 格式 | 示例 | |------|------|------| -| **Skills** | 触发短语（无斜杠） | `workflow-lite-planex`, `brainstorm`, `workflow-plan` | +| **Skills** | 触发短语（无斜杠） | `workflow-lite-plan`, `brainstorm`, `workflow-plan` | | **Commands** | 斜杠命令 | `/ccw`, `/workflow/session:start`, `/issue/new` | ### 选择工作流 Skill @@ -101,7 +101,7 @@ CCW 使用两种调用方式：
Skill TriggerUse Case
workflow-lite-planexLightweight planning, single-module features
workflow-lite-planLightweight planning, single-module features (hands off to lite-execute)
workflow-multi-cli-planMulti-CLI collaborative analysis
workflow-planFull planning with session persistence
workflow-tdd-planTest-driven development
- + @@ -114,7 +114,7 @@ CCW 使用两种调用方式： ```bash # Skill 触发（无斜杠 - 直接描述你想做什么） -workflow-lite-planex "添加 JWT 认证" +workflow-lite-plan "添加 JWT 认证" workflow-plan "实现支付网关集成" workflow-execute @@ -278,7 +278,7 @@ ccw upgrade -a # 升级所有安装 ``` ┌─────────────────────────────────────────────────────────────────┐ │ 工作流 Skills │ -│ 📝 workflow-lite-planex / workflow-multi-cli-plan (轻量级) │ +│ 📝 workflow-lite-plan / workflow-multi-cli-plan (轻量级) │ │ 📊 workflow-plan / workflow-tdd-plan (会话式) │ │ 🧪 workflow-test-fix / workflow-test-fix │ │ 🧠 brainstorm (多角色分析) │ @@ -322,7 +322,7 @@ Claude-Code-Workflow/ │ │ ├── memory/ # 内存命令 (prepare, style-skill-memory) │ │ └── workflow/ # 工作流命令 (session, ui-design 等) │ └── skills/ # 37 个模块化技能 -│ ├── workflow-lite-planex/ +│ ├── workflow-lite-plan/ │ ├── workflow-plan/ │ ├── workflow-tdd-plan/ │ ├── workflow-test-fix/ diff --git a/WORKFLOW_GUIDE.md b/WORKFLOW_GUIDE.md index 1b1b7c63..a6398d75 100644 --- a/WORKFLOW_GUIDE.md +++ b/WORKFLOW_GUIDE.md @@ -21,7 +21,7 @@ CCW uses two types of invocations: | Type | Format | Examples | |------|--------|----------| -| **Skills** | Trigger phrase (no slash) | `workflow-lite-planex`, `brainstorm`, `workflow-plan` | +| **Skills** | Trigger phrase (no slash) | `workflow-lite-plan`, `brainstorm`, `workflow-plan` | | **Commands** | Slash command | `/ccw`, `/workflow/session:start`, `/issue/new` | --- @@ -32,7 +32,7 @@ CCW uses two types of invocations: | Skill Trigger | Purpose | Phases | |---------------|---------|--------| -| `workflow-lite-planex` | Lightweight planning with exploration (includes execution) | 5 phases | +| `workflow-lite-plan` | Lightweight planning with exploration (Skill handoff to lite-execute) | 5 phases | **5-Phase Interactive Workflow**: ``` @@ -231,7 +231,7 @@ Phase 6: Next cycle | Skill | Trigger | |-------|---------| -| workflow-lite-planex | `workflow-lite-planex` | +| workflow-lite-plan | `workflow-lite-plan` | | workflow-multi-cli-plan | `workflow-multi-cli-plan` | | workflow-plan | `workflow-plan`, `workflow-plan-verify`, `workflow:replan` | | workflow-execute | `workflow-execute` | @@ -292,10 +292,10 @@ New System ─┼────────────┼───── Start │ ├─ Is it a quick fix or config change? - │ └─> Yes: workflow-lite-planex + │ └─> Yes: workflow-lite-plan │ ├─ Is it a single module feature? - │ └─> Yes: workflow-lite-planex + │ └─> Yes: workflow-lite-plan │ ├─ Does it need multi-CLI analysis? │ └─> Yes: workflow-multi-cli-plan @@ -347,7 +347,7 @@ Start | Skill | When to Use | |-------|-------------| -| `workflow-lite-planex` | Quick fixes, single features | +| `workflow-lite-plan` | Quick fixes, single features | | `workflow-plan` | Multi-module development | | `brainstorm` | Architecture, new features | | `workflow-execute` | Execute planned work | diff --git a/WORKFLOW_GUIDE_CN.md b/WORKFLOW_GUIDE_CN.md index e0e4c6d2..acc28d74 100644 --- a/WORKFLOW_GUIDE_CN.md +++ b/WORKFLOW_GUIDE_CN.md @@ -22,7 +22,7 @@ CCW 使用两种调用方式： | 类型 | 格式 | 示例 | |------|------|------| -| **Skills** | 触发短语（无斜杠） | `workflow-lite-planex`, `brainstorm`, `workflow-plan` | +| **Skills** | 触发短语（无斜杠） | `workflow-lite-plan`, `brainstorm`, `workflow-plan` | | **Commands** | 斜杠命令 | `/ccw`, `/workflow/session:start`, `/issue/new` | --- @@ -33,7 +33,7 @@ CCW 使用两种调用方式： | Skill 触发词 | 用途 | 阶段 | |--------------|------|------| -| `workflow-lite-planex` | 轻量规划与探索（包含执行） | 5 阶段 | +| `workflow-lite-plan` | 轻量规划与探索（Skill 交接给 lite-execute） | 5 阶段 | **5 阶段交互式工作流**： ``` @@ -232,7 +232,7 @@ CCW 使用两种调用方式： | Skill | 触发词 | |-------|--------| -| workflow-lite-planex | `workflow-lite-planex` | +| workflow-lite-plan | `workflow-lite-plan` | | workflow-multi-cli-plan | `workflow-multi-cli-plan` | | workflow-plan | `workflow-plan`, `workflow-plan-verify`, `workflow:replan` | | workflow-execute | `workflow-execute` | @@ -293,10 +293,10 @@ CCW 使用两种调用方式： 开始 │ ├─ 是快速修复或配置变更？ - │ └─> 是：workflow-lite-planex + │ └─> 是：workflow-lite-plan │ ├─ 是单模块功能？ - │ └─> 是：workflow-lite-planex + │ └─> 是：workflow-lite-plan │ ├─ 需要多 CLI 分析？ │ └─> 是：workflow-multi-cli-plan @@ -348,7 +348,7 @@ CCW 使用两种调用方式： | Skill | 何时使用 | |-------|----------| -| `workflow-lite-planex` | 快速修复、单功能 | +| `workflow-lite-plan` | 快速修复、单功能 | | `workflow-plan` | 多模块开发 | | `brainstorm` | 架构、新功能 | | `workflow-execute` | 执行已规划的工作 | diff --git a/ccw/frontend/src/components/shared/JsonCardView.tsx b/ccw/frontend/src/components/shared/JsonCardView.tsx index 15a4fc9f..2317322b 100644 --- a/ccw/frontend/src/components/shared/JsonCardView.tsx +++ b/ccw/frontend/src/components/shared/JsonCardView.tsx @@ -87,12 +87,15 @@ function PrimitiveValue({ value }: { value: unknown }) { return {String(value)}; } -function ArrayView({ items }: { items: unknown[] }) { +function ArrayView({ items, displayName = 'items' }: { items: unknown[]; displayName?: string }) { const [expanded, setExpanded] = useState(true); if (items.length === 0) { return ( -
Empty list
+
+ + No {displayName} entries. +
); } @@ -154,7 +157,7 @@ function ObjectView({ data, depth = 0 }: { data: Record; depth? ))} ); -} + function CardItem({ label, value, depth = 0 }: CardItemProps) { const formattedLabel = formatLabel(label); @@ -176,7 +179,7 @@ function CardItem({ label, value, depth = 0 }: CardItemProps) { return (
{formattedLabel}
- +
); } diff --git a/ccw/src/tools/command-registry.test.ts b/ccw/src/tools/command-registry.test.ts index 00466e3e..637c0629 100644 --- a/ccw/src/tools/command-registry.test.ts +++ b/ccw/src/tools/command-registry.test.ts @@ -225,7 +225,7 @@ invalid yaml content without colons expect(result).toEqual({ name: 'lite-plan', - command: '/workflow-lite-planex', + command: '/workflow-lite-plan', description: 'Quick planning for simple features', argumentHint: '"feature description"', allowedTools: ['Task(*)', 'Read(*)', 'Write(*)', 'Bash(*)'], @@ -239,7 +239,7 @@ invalid yaml content without colons mockReadFileSync.mockReturnValue(sampleLitePlanYaml); const registry = new CommandRegistry(cmdDir); - const result = registry.getCommand('/workflow-lite-planex'); + const result = registry.getCommand('/workflow-lite-plan'); expect(result?.name).toBe('lite-plan'); }); @@ -330,7 +330,7 @@ description: Minimal command const result = registry.getCommands(['lite-plan', 'execute', 'nonexistent']); expect(result.size).toBe(2); - expect(result.has('/workflow-lite-planex')).toBe(true); + expect(result.has('/workflow-lite-plan')).toBe(true); expect(result.has('/workflow-execute')).toBe(true); }); @@ -362,7 +362,7 @@ description: Minimal command const result = registry.getAllCommandsSummary(); expect(result.size).toBe(3); - expect(result.get('/workflow-lite-planex')).toEqual({ + expect(result.get('/workflow-lite-plan')).toEqual({ name: 'lite-plan', description: 'Quick planning for simple features' }); @@ -483,9 +483,9 @@ allowed-tools: Task(*) const json = registry.toJSON(); - expect(json['/workflow-lite-planex']).toEqual({ + expect(json['/workflow-lite-plan']).toEqual({ name: 'lite-plan', - command: '/workflow-lite-planex', + command: '/workflow-lite-plan', description: 'Quick planning for simple features', argumentHint: '"feature description"', allowedTools: ['Task(*)', 'Read(*)', 'Write(*)', 'Bash(*)'], @@ -508,7 +508,7 @@ allowed-tools: Task(*) const json = registry.toJSON(); expect(Object.keys(json).length).toBe(1); - expect(json['/workflow-lite-planex']).toBeDefined(); + expect(json['/workflow-lite-plan']).toBeDefined(); expect(json['/workflow-execute']).toBeUndefined(); }); }); diff --git a/ccw/src/tools/command-registry.ts b/ccw/src/tools/command-registry.ts index eba61d0a..0a2a070a 100644 --- a/ccw/src/tools/command-registry.ts +++ b/ccw/src/tools/command-registry.ts @@ -118,7 +118,7 @@ export class CommandRegistry { /** * Get single command metadata - * @param commandName Command name (e.g., "lite-plan" or "/workflow-lite-planex") + * @param commandName Command name (e.g., "lite-plan" or "/workflow-lite-plan") * @returns Command metadata or null */ public getCommand(commandName: string): CommandMetadata | null { diff --git a/docs-site/commands/claude/index.md b/docs-site/commands/claude/index.md index 7bd8f5c4..1f57d1eb 100644 --- a/docs-site/commands/claude/index.md +++ b/docs-site/commands/claude/index.md @@ -29,7 +29,7 @@ | 命令 | 功能 | 难度 | | --- | --- | --- | -| [`/workflow-lite-planex`](./workflow.md#lite-plan) | 轻量级交互式规划工作流 | Intermediate | +| [`/workflow-lite-plan`](./workflow.md#lite-plan) | 轻量级交互式规划工作流 | Intermediate | | [`/workflow:lite-fix`](./workflow.md#lite-fix) | 轻量级 Bug 诊断和修复 | Intermediate | | [`/workflow-plan`](./workflow.md#plan) | 5 阶段规划工作流 | Intermediate | | [`/workflow-execute`](./workflow.md#execute) | 协调代理执行工作流任务 | Intermediate | diff --git a/docs/COMMAND_SPEC.md b/docs/COMMAND_SPEC.md index 0a4a8963..f14384f4 100644 --- a/docs/COMMAND_SPEC.md +++ b/docs/COMMAND_SPEC.md @@ -45,9 +45,9 @@ High-level orchestrators for complex, multi-phase development processes. /workflow-plan "Create a simple Express API that returns Hello World" ``` -### **/workflow-lite-planex** ⚡ NEW +### **/workflow-lite-plan** ⚡ NEW -- **Syntax**: `/workflow-lite-planex [--tool claude|gemini|qwen|codex] [-e|--explore] "task description"|file.md` +- **Syntax**: `/workflow-lite-plan [--tool claude|gemini|qwen|codex] [-e|--explore] "task description"|file.md` - **Parameters**: - `--tool` (Optional, String): Preset CLI tool for execution (claude|gemini|qwen|codex). If not provided, user selects during confirmation. - `-e, --explore` (Optional, Flag): Force code exploration phase (overrides auto-detection logic). @@ -74,13 +74,13 @@ High-level orchestrators for complex, multi-phase development processes. - **Example**: ```bash # Basic usage with auto-detection - /workflow-lite-planex "Add JWT authentication to user login" + /workflow-lite-plan "Add JWT authentication to user login" # Force code exploration - /workflow-lite-planex -e "Refactor logging module for better performance" + /workflow-lite-plan -e "Refactor logging module for better performance" # Basic usage - /workflow-lite-planex "Add unit tests for auth service" + /workflow-lite-plan "Add unit tests for auth service" ``` ### **/workflow-execute** @@ -202,7 +202,7 @@ CLI tool configuration commands. /cli:cli-init ``` -> **Note**: For analysis, planning, and bug fixing, use workflow commands (`/workflow-lite-planex`, `/workflow:debug-with-file`) or semantic invocation through natural language. Claude will automatically use appropriate CLI tools (Gemini/Qwen/Codex) with templates as needed. +> **Note**: For analysis, planning, and bug fixing, use workflow commands (`/workflow-lite-plan`, `/workflow:debug-with-file`) or semantic invocation through natural language. Claude will automatically use appropriate CLI tools (Gemini/Qwen/Codex) with templates as needed. --- diff --git a/docs/cli/commands.md b/docs/cli/commands.md index e6b39f30..d79b4646 100644 --- a/docs/cli/commands.md +++ b/docs/cli/commands.md @@ -31,7 +31,7 @@ Complete reference for all **43 CCW commands** organized by category, with **7 w - `-y, --yes` - Skip all confirmations **Mapped Skills**: -- workflow-lite-planex, workflow-plan, workflow-execute, workflow-tdd-plan +- workflow-lite-plan, workflow-plan, workflow-execute, workflow-tdd-plan - workflow-test-fix, workflow-multi-cli-plan, review-cycle, brainstorm - team-planex, team-iterdev, team-lifecycle, team-issue - team-testing, team-quality-assurance, team-brainstorm, team-uidesign diff --git a/docs/commands/claude/core-orchestration.md b/docs/commands/claude/core-orchestration.md index ffaf92b9..113bdd4f 100644 --- a/docs/commands/claude/core-orchestration.md +++ b/docs/commands/claude/core-orchestration.md @@ -143,7 +143,7 @@ Both commands support the `--yes` flag for auto mode: | Skill | Function | |-------|----------| -| `workflow-lite-planex` | Lightweight planning workflow | +| `workflow-lite-plan` | Lightweight planning workflow | | `workflow-plan` | Full planning workflow | | `workflow-execute` | Execution workflow | | `workflow-tdd-plan` | TDD workflow | diff --git a/docs/commands/claude/index.md b/docs/commands/claude/index.md index 90bc3091..29c00903 100644 --- a/docs/commands/claude/index.md +++ b/docs/commands/claude/index.md @@ -30,7 +30,7 @@ | Command | Function | Difficulty | |---------|----------|------------| -| [`/workflow-lite-planex`](./workflow.md#lite-plan) | Lightweight interactive planning workflow | Intermediate | +| [`/workflow-lite-plan`](./workflow.md#lite-plan) | Lightweight interactive planning workflow | Intermediate | | [`/workflow-plan`](./workflow.md#plan) | 5-phase planning workflow | Intermediate | | [`/workflow-execute`](./workflow.md#execute) | Coordinate agent execution of workflow tasks | Intermediate | | [`/workflow:replan`](./workflow.md#replan) | Interactive workflow replanning | Intermediate | diff --git a/docs/commands/claude/workflow.md b/docs/commands/claude/workflow.md index 34467428..ae1fd8a5 100644 --- a/docs/commands/claude/workflow.md +++ b/docs/commands/claude/workflow.md @@ -10,7 +10,7 @@ | Command | Function | Syntax | |---------|----------|--------| -| [`lite-plan`](#lite-plan) | Lightweight interactive planning workflow | `/workflow-lite-planex [-y] [-e] "task"` | +| [`lite-plan`](#lite-plan) | Lightweight interactive planning workflow | `/workflow-lite-plan [-y] [-e] "task"` | ### Standard Workflows @@ -70,7 +70,7 @@ **Syntax**: ```bash -/workflow-lite-planex [-y|--yes] [-e|--explore] "task description" | file.md +/workflow-lite-plan [-y|--yes] [-e|--explore] "task description" | file.md ``` **Options**: @@ -79,10 +79,10 @@ **Examples**: ```bash # Basic planning -/workflow-lite-planex "add user avatar feature" +/workflow-lite-plan "add user avatar feature" # With exploration -/workflow-lite-planex -e "refactor authentication module" +/workflow-lite-plan -e "refactor authentication module" ``` ### plan diff --git a/docs/reference/commands-skills.md b/docs/reference/commands-skills.md index 9a803764..9b5be5a3 100644 --- a/docs/reference/commands-skills.md +++ b/docs/reference/commands-skills.md @@ -43,7 +43,7 @@ | Category | Skill | Internal Pipeline | Use Case | |----------|-------|-------------------|----------| -| **Workflow** | workflow-lite-planex | explore → plan → confirm → execute | Quick features, bug fixes | +| **Workflow** | workflow-lite-plan | explore → plan → confirm → execute | Quick features, bug fixes | | **Workflow** | workflow-plan | session → context → convention → gen → verify/replan | Complex feature planning | | **Workflow** | workflow-execute | session discovery → task processing → commit | Execute pre-generated plans | | **Workflow** | workflow-tdd-plan | 6-phase TDD plan → verify | TDD development | @@ -81,7 +81,7 @@ | Skill | Internal Pipeline | |-------|-------------------| -| workflow-lite-planex | explore → plan → confirm → execute | +| workflow-lite-plan | explore → plan → confirm → execute | | workflow-plan | session → context → convention → gen → verify/replan | | workflow-execute | session discovery → task processing → commit | | workflow-tdd-plan | 6-phase TDD plan → verify | @@ -357,16 +357,16 @@ | Task Type | Skill Chain | |-----------|-------------| -| bugfix | workflow-lite-planex → workflow-test-fix | -| bugfix-hotfix | workflow-lite-planex | -| feature | workflow-lite-planex → workflow-test-fix | +| bugfix | workflow-lite-plan → workflow-test-fix | +| bugfix-hotfix | workflow-lite-plan | +| feature | workflow-lite-plan → workflow-test-fix | | feature-complex | workflow-plan → workflow-execute → workflow-test-fix | | refactor | workflow:refactor-cycle | | tdd | workflow-tdd-plan → workflow-execute | | test | workflow-test-fix | | test-fix | workflow-test-fix | | review | review-cycle | -| docs | workflow-lite-planex | +| docs | workflow-lite-plan | **6-Phase Execution**: 1. Load Tasks @@ -606,7 +606,7 @@ | Skill | Internal Pipeline | Description | |-------|-------------------|-------------| -| workflow-lite-planex | explore → plan → confirm → execute | Lightweight merged-mode planning | +| workflow-lite-plan | explore → plan → confirm → execute | Lightweight merged-mode planning | | workflow-plan | session → context → convention → gen → verify/replan | Full planning with architecture design | | workflow-execute | session discovery → task processing → commit | Execute from planning session | | workflow-tdd-plan | 6-phase TDD plan → verify | TDD workflow planning | @@ -716,7 +716,7 @@ Examples: ### Skill Invocation (from code) ```javascript -Skill({ skill: "workflow-lite-planex", args: '"task description"' }) +Skill({ skill: "workflow-lite-plan", args: '"task description"' }) Skill({ skill: "brainstorm", args: '"topic or question"' }) Skill({ skill: "review-cycle", args: '--session="WFS-xxx"' }) ``` diff --git a/docs/skill-team-comparison.md b/docs/skill-team-comparison.md index 727a607f..c3998b1c 100644 --- a/docs/skill-team-comparison.md +++ b/docs/skill-team-comparison.md @@ -21,7 +21,7 @@ | 命令 | 类型 | 输出 | 适用场景 | 特点 | |------|------|------|----------|------| | **workflow-plan** | 4阶段规划 | IMPL_PLAN.md, task JSONs, TODO_LIST.md | 标准功能开发 | 完整规划流程，支持冲突检测，可选验证 | -| **workflow-lite-planex** | 轻量规划 | task JSONs | 快速任务 | 精简流程，直接执行，无验证阶段 | +| **workflow-lite-plan** | 轻量规划 | task JSONs | 快速任务 | 精简流程，直接执行，无验证阶段 | | **workflow-tdd-plan** | TDD规划 | IMPL_PLAN.md (含Red-Green-Refactor) | 测试驱动开发 | 强制TDD结构，测试先行 | | **brainstorm** | 头脑风暴 | guidance-specification.md, role分析, feature-specs | 需求探索 | 多角色分析，角色扮演，创意生成 | | **issue:plan** | Issue规划 | solution JSON per issue | Issue驱动开发 | 批量规划，自动绑定，冲突检测 | @@ -39,7 +39,7 @@ ``` ┌─────────────────┬───────────────────┬───────────────────┬───────────────────┐ -│ │ workflow-plan │ workflow-lite-planex│ issue:plan │ +│ │ workflow-plan │ workflow-lite-plan│ issue:plan │ ├─────────────────┼───────────────────┼───────────────────┼───────────────────┤ │ 复杂度 │ 高 (4-6阶段) │ 低 (1-2阶段) │ 中 (3阶段) │ │ 验证阶段 │ ✓ (Phase 5) │ ✗ │ ✗ │ @@ -61,7 +61,7 @@ | 命令 | 类型 | 执行方式 | 适用场景 | 特点 | |------|------|----------|----------|------| | **workflow-execute** | 任务执行器 | code-developer agent | 规划后执行 | 会话发现，并行任务，进度跟踪 | -| **workflow-lite-planex** (执行模式) | 轻量执行 | code-developer / CLI | 快速实现 | 内置执行，无会话 | +| **workflow-lite-plan** (执行模式) | 轻量执行 | code-developer / CLI | 快速实现 | 内置执行，无会话 | | **review-code** | 代码审查 | read-only | 质量检查 | 多维度审查，自动修复建议 | ### Team 执行 Skill @@ -188,7 +188,7 @@ if (task_count > 3) → Codex | 任务类型 | 推荐命令 | 备选命令 | |----------|----------|----------| | **新功能开发** | workflow-plan → workflow-execute | team-lifecycle | -| **快速修复** | workflow-lite-planex | issue:plan → issue:execute | +| **快速修复** | workflow-lite-plan | issue:plan → issue:execute | | **TDD开发** | workflow-tdd-plan → workflow-execute | - | | **需求探索** | brainstorm | team-brainstorm | | **Issue处理** | issue:plan → issue:queue → issue:execute | team-issue | @@ -201,7 +201,7 @@ if (task_count > 3) → Codex | 规模 | 推荐命令 | 原因 | |------|----------|------| -| **单人快速** | workflow-lite-planex | 轻量，直接执行 | +| **单人快速** | workflow-lite-plan | 轻量，直接执行 | | **单人完整** | workflow-plan → workflow-execute | 完整流程，有验证 | | **多人协作** | team-coordinate | 动态角色，灵活分工 | | **专项团队** | team-* (按领域) | 领域专家角色 | @@ -210,7 +210,7 @@ if (task_count > 3) → Codex ``` 复杂度低 (1-2任务) -└─ workflow-lite-planex (推荐) +└─ workflow-lite-plan (推荐) └─ issue:plan (Issue驱动) 复杂度中 (3-10任务) @@ -258,7 +258,7 @@ tdd-plan plan issue plan brainstorm | 命令 | 调用方式 | |------|----------| | workflow-plan | `Skill(skill="workflow-plan", args="任务描述")` | -| workflow-lite-planex | `Skill(skill="workflow-lite-planex", args="任务描述")` | +| workflow-lite-plan | `Skill(skill="workflow-lite-plan", args="任务描述")` | | workflow-tdd-plan | `Skill(skill="workflow-tdd-plan", args="TDD任务描述")` | | brainstorm | `Skill(skill="brainstorm", args="主题 --count 3")` | | issue:plan | `/issue:plan GH-123,GH-124` | @@ -300,7 +300,7 @@ tdd-plan plan issue plan brainstorm |------|------|--------| | **规划** | workflow-plan | 6阶段 | | **执行** | workflow-execute | 6阶段 | -| **轻量** | workflow-lite-planex | 2阶段 | +| **轻量** | workflow-lite-plan | 2阶段 | | **TDD** | workflow-tdd-plan | 7阶段 | | **测试修复** | workflow-test-fix | 4阶段 | | **多CLI** | workflow-multi-cli-plan | - | diff --git a/docs/skills/claude-index.md b/docs/skills/claude-index.md index ecefa5fe..296f2c5f 100644 --- a/docs/skills/claude-index.md +++ b/docs/skills/claude-index.md @@ -76,7 +76,7 @@ Claude Code Workflow supports two team architecture models: | Level | Name | Workflow | Use Case | |-------|------|----------|----------| -| Level 1 | Lite-Lite-Lite | lite-plan | Super simple quick tasks | +| Level 1 | Lite-Lite-Lite | lite-plan | Skill handoff to lite-execute | | Level 2 | Rapid | plan → execute | Bug fixes, simple features | | Level 2.5 | Rapid-to-Issue | plan → issue:new | From rapid planning to Issue | | Level 3 | Coupled | plan → execute | Complex features (plan+execute+review+test) | @@ -181,7 +181,7 @@ memory/ ```bash # Quick task -/workflow-lite-planex "Fix login bug" +/workflow-lite-plan "Fix login bug" # Full development /workflow-plan "Add user notifications" @@ -234,7 +234,7 @@ memory/ - Test coverage → `team-testing` 2. **Workflow Selection**: - - Super simple → `workflow-lite-planex` + - Super simple → `workflow-lite-plan` - Complex features → `workflow-plan` → `workflow-execute` - TDD → `workflow-tdd-plan` - Test fixes → `workflow-test-fix` diff --git a/docs/skills/claude-workflow.md b/docs/skills/claude-workflow.md index ebe166ad..69c83a4e 100644 --- a/docs/skills/claude-workflow.md +++ b/docs/skills/claude-workflow.md @@ -19,14 +19,14 @@ |-------|----------|---------| | `workflow-plan` | Unified planning skill (4-stage workflow) | `/workflow-plan` | | `workflow-execute` | Agent-coordinated execution | `/workflow-execute` | -| `workflow-lite-planex` | Lightweight quick planning | `/workflow-lite-planex` | +| `workflow-lite-plan` | Lightweight quick planning | `/workflow-lite-plan` | | `workflow-multi-cli-plan` | Multi-CLI collaborative planning | `/workflow-multi-cli-plan` | | `workflow-tdd-plan` | TDD workflow | `/workflow-tdd-plan` | | `workflow-test-fix` | Test-fix workflow | `/workflow-test-fix` | | `workflow-skill-designer` | Skill design workflow | `/workflow-skill-designer` | | `team-arch-opt` | Architecture optimization | `/team-arch-opt` | -> **New in 7.2.1**: `team-arch-opt` skill added for architecture analysis and optimization. `workflow-lite-planex` renamed from `workflow-lite-plan`. +> **New in 7.2.1**: `team-arch-opt` skill added for architecture analysis and optimization. `workflow-lite-plan` renamed from `workflow-lite-plan`. ## Skills Details @@ -185,13 +185,13 @@ Phase 5: Completion --- -### workflow-lite-planex +### workflow-lite-plan **One-Liner**: Lightweight quick planning — Quick planning and execution for super simple tasks **Trigger**: ```shell -/workflow-lite-planex +/workflow-lite-plan ``` **Features**: @@ -358,7 +358,7 @@ Wave 2: Issue 6-10 → Parallel planning → Parallel execution ## Best Practices 1. **Choose the right workflow**: - - Super simple tasks → `workflow-lite-planex` + - Super simple tasks → `workflow-lite-plan` - Complex features → `workflow-plan` → `workflow-execute` - TDD development → `workflow-tdd-plan` - Test fixes → `workflow-test-fix` diff --git a/docs/skills/core-skills.md b/docs/skills/core-skills.md index 7fa94d54..df771264 100644 --- a/docs/skills/core-skills.md +++ b/docs/skills/core-skills.md @@ -679,11 +679,11 @@ Skill(skill="workflow-plan") --- -### workflow-lite-planex +### workflow-lite-plan **Purpose**: Lightweight planning and execution skill -**Triggers**: `workflow-lite-planex` +**Triggers**: `workflow-lite-plan` **Description**: Unified planning and execution skill (Phase 1: plan, Phase 2: execute) with prompt enhancement. @@ -696,7 +696,7 @@ Skill(skill="workflow-plan") **Artifacts**: LITE_PLAN.md, execution results ```bash -Skill(skill="workflow-lite-planex") +Skill(skill="workflow-lite-plan") ``` --- @@ -851,7 +851,7 @@ Skill(skill="review-cycle") **Use Case**: Quick iterations and rapid prototyping ```bash -Skill(skill="workflow-lite-planex") +Skill(skill="workflow-lite-plan") Skill(skill="workflow-execute") ``` @@ -1039,7 +1039,7 @@ Skill(skill="skill-tuning") | Level | Skills | |-------|--------| | Meta Skills | skill-generator, skill-tuning, workflow-skill-designer | -| Orchestrators | workflow-plan, workflow-lite-planex, workflow-multi-cli-plan | +| Orchestrators | workflow-plan, workflow-lite-plan, workflow-multi-cli-plan | | Executors | workflow-execute | | Team Leads | team-lifecycle (v5) | @@ -1085,7 +1085,7 @@ Quick reference for skill triggers: | `manage issue` | issue-manage | | `workflow-plan`, `workflow-plan-verify`, `workflow:replan` | workflow-plan | | `workflow-execute` | workflow-execute | -| `workflow-lite-planex` | workflow-lite-planex | +| `workflow-lite-plan` | workflow-lite-plan | | `workflow-multi-cli-plan`, `workflow:multi-cli-plan` | workflow-multi-cli-plan | | `workflow-tdd-plan` | workflow-tdd-plan | | `workflow-test-fix`, `test fix workflow` | workflow-test-fix | diff --git a/docs/skills/index.md b/docs/skills/index.md index 852de1f4..937d1c14 100644 --- a/docs/skills/index.md +++ b/docs/skills/index.md @@ -56,7 +56,7 @@ Skills are reusable, domain-specific capabilities that CCW can execute. Each ski | Skill | Triggers | Description | |-------|----------|-------------| | [workflow-plan](./core-skills.md#workflow-plan) | `workflow-plan`, `workflow-plan-verify`, `workflow:replan` | 4-phase planning with verification | -| [workflow-lite-planex](./core-skills.md#workflow-lite-planex) | `workflow-lite-planex` | Lightweight planning | +| [workflow-lite-plan](./core-skills.md#workflow-lite-plan) | `workflow-lite-plan` | Lightweight planning | | [workflow-multi-cli-plan](./core-skills.md#workflow-multi-cli-plan) | `workflow-multi-cli-plan`, `workflow:multi-cli-plan` | Multi-CLI collaborative planning | | [workflow-execute](./core-skills.md#workflow-execute) | `workflow-execute` | Task execution coordination | | [workflow-tdd-plan](./core-skills.md#workflow-tdd-plan) | `workflow-tdd-plan` | TDD with Red-Green-Refactor | @@ -79,7 +79,7 @@ Skill(skill="review-cycle") #### Quick Iteration ```bash -Skill(skill="workflow-lite-planex") +Skill(skill="workflow-lite-plan") Skill(skill="workflow-execute") ``` @@ -203,7 +203,7 @@ Skill(skill="my-custom-skill", args="input") # Step 3: Execute with team lifecycle Skill(skill="team-lifecycle-v4", args="Build user dashboard") # Or use quick iteration: -# Skill(skill="workflow-lite-planex") +# Skill(skill="workflow-lite-plan") # Step 4: Review and refine Skill(skill="review-code") @@ -267,7 +267,7 @@ ccw review-cycle --max-iterations 3 ### Tips for Best Results -1. **Start Small**: Begin with `workflow-lite-planex` for simple tasks +1. **Start Small**: Begin with `workflow-lite-plan` for simple tasks 2. **Use Memory**: Capture insights with `memory:capture` for future reference 3. **Verify Plans**: Always review generated plans before execution 4. **Iterate**: Use `review-cycle` for continuous improvement diff --git a/docs/skills/reference.md b/docs/skills/reference.md index 460f8ffe..72bffe68 100644 --- a/docs/skills/reference.md +++ b/docs/skills/reference.md @@ -28,7 +28,7 @@ Quick reference guide for all **33 CCW built-in skills**. | Skill | Trigger | Purpose | |-------|---------|---------| | **workflow-plan** | `workflow-plan`, `workflow-plan-verify`, `workflow:replan` | 4-phase planning workflow with verification and interactive replanning | -| **workflow-lite-planex** | `workflow-lite-planex` | Lightweight planning and execution skill | +| **workflow-lite-plan** | `workflow-lite-plan` | Lightweight planning and execution skill | | **workflow-multi-cli-plan** | `workflow-multi-cli-plan`, `workflow:multi-cli-plan` | Multi-CLI collaborative planning with ACE context engine | | **workflow-execute** | `workflow-execute` | Coordinate agent execution for workflow tasks | | **workflow-tdd-plan** | `workflow-tdd-plan`, `workflow-tdd-verify` | TDD workflow with Red-Green-Refactor task chain | @@ -103,7 +103,7 @@ team lifecycle | `review code`, `code review`, `审查代码` | review-code | | `workflow:review-cycle` | review-cycle | | `workflow-plan` | workflow-plan | -| `workflow-lite-planex` | workflow-lite-planex | +| `workflow-lite-plan` | workflow-lite-plan | | `workflow-multi-cli-plan`, `workflow:multi-cli-plan` | workflow-multi-cli-plan | | `workflow-execute` | workflow-execute | | `workflow-tdd-plan` | workflow-tdd-plan | @@ -163,7 +163,7 @@ The latest team-lifecycle (v5) uses the team-worker agent with dynamic role assi | Generator-Critic Loop | team-iterdev | | Wave Pipeline | team-planex | | Red-Green-Refactor | workflow-tdd-plan | -| Pure Orchestrator | workflow-plan, workflow-lite-planex | +| Pure Orchestrator | workflow-plan, workflow-lite-plan | | Progressive Phase Loading | workflow-plan, workflow-tdd-plan, team-lifecycle | ::: info See Also diff --git a/docs/workflows/comparison-table.md b/docs/workflows/comparison-table.md index 3bb211bd..c7ebb57c 100644 --- a/docs/workflows/comparison-table.md +++ b/docs/workflows/comparison-table.md @@ -6,7 +6,7 @@ | Workflow | Best For | Level | Self-Contained | |----------|----------|-------|----------------| -| workflow-lite-planex | Quick tasks, bug fixes | 2 (Lightweight) | YES | +| workflow-lite-plan | Quick tasks, bug fixes | 2 (Lightweight) | YES | | workflow-plan → workflow-execute | Complex features | 3-4 (Standard) | NO (requires execute) | | workflow-tdd-plan → workflow-execute | TDD development | 3 (Standard) | NO (requires execute) | | workflow-test-fix | Test generation/fix | 3 (Standard) | YES | @@ -31,7 +31,7 @@ | Workflow | Invocation | Pipeline | Use Case | Level | Self-Contained | Auto-Chains To | |----------|------------|----------|----------|-------|----------------|----------------| | **Plan+Execute Workflows** | -| workflow-lite-planex | `/ccw "task"` (auto for low/medium complexity) | explore → plan → confirm → execute | Quick features, bug fixes, simple tasks | 2 (Lightweight) | YES | workflow-test-fix | +| workflow-lite-plan | `/ccw "task"` (auto for low/medium complexity) | explore → plan → confirm → execute | Quick features, bug fixes, simple tasks | 2 (Lightweight) | YES | workflow-test-fix | | workflow-plan | `/ccw "complex feature"` (high complexity) | session → context → convention → gen → verify/replan | Complex feature planning, formal verification | 3-4 (Standard) | NO | workflow-execute | | workflow-execute | `/workflow-execute` (after plan) | session discovery → task processing → commit | Execute pre-generated plans | 3 (Standard) | YES | review-cycle (optional) | | workflow-multi-cli-plan | `/ccw "multi-cli plan: ..."` | ACE context → CLI discussion → plan → execute | Multi-perspective planning | 3 (Standard) | YES | (internal handoff) | @@ -43,7 +43,7 @@ | brainstorm-with-file | `/ccw "brainstorm: ..."` | brainstorm + documented artifacts | Documented ideation with session | 4 (Full) | NO | workflow-plan → execute | | collaborative-plan-with-file | `/ccw "collaborative plan: ..."` | understanding → parallel agents → plan-note.md | Multi-agent collaborative planning | 3 (Standard) | NO | unified-execute-with-file | | **Analysis Workflows** | -| analyze-with-file | `/ccw "analyze: ..."` | multi-CLI analysis → discussion.md | Deep understanding, architecture exploration | 3 (Standard) | NO | workflow-lite-planex | +| analyze-with-file | `/ccw "analyze: ..."` | multi-CLI analysis → discussion.md | Deep understanding, architecture exploration | 3 (Standard) | NO | workflow-lite-plan | | debug-with-file | `/ccw "debug: ..."` | hypothesis-driven iteration → debug.log | Systematic debugging | 3 (Standard) | YES | (standalone) | | **Review Workflows** | | review-cycle | `/ccw "review code"` | discovery → analysis → aggregation → deep-dive → completion | Code review, quality gates | 3 (Standard) | YES | fix mode (if findings) | @@ -67,7 +67,7 @@ | Level | Workflows | Characteristics | |-------|-----------|-----------------| -| **2 (Lightweight)** | workflow-lite-planex, docs | Quick execution, minimal phases | +| **2 (Lightweight)** | workflow-lite-plan, docs | Quick execution, minimal phases | | **2.5 (Bridge)** | issue pipeline, rapid-to-issue | Bridge to issue workflow | | **3 (Standard)** | workflow-plan, workflow-execute, workflow-tdd-plan, workflow-test-fix, review-cycle, debug-with-file, analyze-with-file, workflow-multi-cli-plan | Full planning/execution, multi-phase | | **4 (Full)** | brainstorm, spec-generator, brainstorm-with-file, roadmap-with-file | Complete exploration, specification | @@ -80,13 +80,13 @@ | Source Workflow | Auto-Chains To | Condition | |-----------------|---------------|-----------| -| workflow-lite-planex | workflow-test-fix | Default (unless skip-tests) | +| workflow-lite-plan | workflow-test-fix | Default (unless skip-tests) | | workflow-plan | workflow-execute | After plan confirmation | | workflow-execute | review-cycle | User choice via Phase 6 | | workflow-tdd-plan | workflow-execute | After TDD plan validation | | brainstorm | workflow-plan | Auto-chain for formal planning | | brainstorm-with-file | workflow-plan → workflow-execute | Auto | -| analyze-with-file | workflow-lite-planex | Auto | +| analyze-with-file | workflow-lite-plan | Auto | | debug-with-file | (none) | Standalone | | collaborative-plan-with-file | unified-execute-with-file | Auto | | roadmap-with-file | team-planex | Auto | @@ -99,7 +99,7 @@ | Workflow | Self-Contained | Notes | |----------|---------------|-------| -| workflow-lite-planex | YES | Complete plan + execute | +| workflow-lite-plan | YES | Complete plan + execute | | workflow-plan | NO | Requires workflow-execute | | workflow-execute | YES | Complete execution | | workflow-tdd-plan | NO | Requires workflow-execute | diff --git a/docs/workflows/examples.md b/docs/workflows/examples.md index 6b70a3c9..b3b8ce4e 100644 --- a/docs/workflows/examples.md +++ b/docs/workflows/examples.md @@ -7,7 +7,7 @@ This page provides practical examples of CCW workflow artifacts with sensitive i ## Example 1: Lite Plan Output ### plan.json -This is an output from `workflow-lite-planex` command. +This is an output from `workflow-lite-plan` command. ```json { diff --git a/docs/zh/cli/commands.md b/docs/zh/cli/commands.md index 157782ad..bbc0c71f 100644 --- a/docs/zh/cli/commands.md +++ b/docs/zh/cli/commands.md @@ -31,7 +31,7 @@ - `-y, --yes` - 跳过所有确认 **映射技能**： -- workflow-lite-planex, workflow-plan, workflow-execute, workflow-tdd-plan +- workflow-lite-plan, workflow-plan, workflow-execute, workflow-tdd-plan - workflow-test-fix, workflow-multi-cli-plan, review-cycle, brainstorm - team-planex, team-iterdev, team-lifecycle, team-issue - team-testing, team-quality-assurance, team-brainstorm, team-uidesign diff --git a/docs/zh/commands/claude/core-orchestration.md b/docs/zh/commands/claude/core-orchestration.md index ee30c51e..7bd01a85 100644 --- a/docs/zh/commands/claude/core-orchestration.md +++ b/docs/zh/commands/claude/core-orchestration.md @@ -23,14 +23,14 @@ | 单元类型 | Skill | 说明 | |---------|-------|------| -| 轻量 Plan+Execute | `workflow-lite-planex` | 内部完成 plan→execute | +| 轻量 Plan+Execute | `workflow-lite-plan` | 内部完成 plan→execute | | 标准 Planning | `workflow-plan` → `workflow-execute` | plan 和 execute 是独立 Skill | | TDD Planning | `workflow-tdd-plan` → `workflow-execute` | tdd-plan 和 execute 是独立 Skill | | 规格驱动 | `spec-generator` → `workflow-plan` → `workflow-execute` | 规格文档驱动完整开发 | | 测试流水线 | `workflow-test-fix` | 内部完成 gen→cycle | | 代码审查 | `review-cycle` | 内部完成 review→fix | -| 分析→规划 | `workflow:analyze-with-file` → `workflow-lite-planex` | 协作分析产物自动传递给 lite-plan | -| 头脑风暴→规划 | `workflow:brainstorm-with-file` → `workflow-lite-planex` | 头脑风暴产物自动传递给 lite-plan | +| 分析→规划 | `workflow:analyze-with-file` → `workflow-lite-plan` | 协作分析产物自动传递给 lite-plan | +| 头脑风暴→规划 | `workflow:brainstorm-with-file` → `workflow-lite-plan` | 头脑风暴产物自动传递给 lite-plan | | 协作规划 | `workflow:collaborative-plan-with-file` → `workflow:unified-execute-with-file` | 多 agent 协作规划→通用执行 | | 需求路线图 | `workflow:roadmap-with-file` → `team-planex` | 需求拆解→issue 创建→wave pipeline 执行 | | 集成测试循环 | `workflow:integration-test-cycle` | 自迭代集成测试闭环 | @@ -109,12 +109,12 @@ graph TD **With-File 自动链式机制**: -当 `analyze-with-file` 或 `brainstorm-with-file` 完成时，其产物（discussion.md / brainstorm.md）**自动传递**给 `workflow-lite-planex` 作为上下文输入。 +当 `analyze-with-file` 或 `brainstorm-with-file` 完成时，其产物（discussion.md / brainstorm.md）**自动传递**给 `workflow-lite-plan` 作为上下文输入。 | 工作流 | 自动链目标 | 产物传递 | |--------|-----------|---------| -| analyze-with-file | → workflow-lite-planex | discussion.md | -| brainstorm-with-file | → workflow-lite-planex | brainstorm.md | +| analyze-with-file | → workflow-lite-plan | discussion.md | +| brainstorm-with-file | → workflow-lite-plan | brainstorm.md | **Cycle 工作流自迭代模式**: @@ -371,7 +371,7 @@ Task: | Skill | 包含操作 | | --- | --- | -| `workflow-lite-planex` | lite-plan (Phase 1: 规划 → Phase 2: 执行) | +| `workflow-lite-plan` | lite-plan (Phase 1: 规划 → Phase 2: 执行) | | `workflow-plan` | plan, plan-verify, replan | | `workflow-execute` | execute | | `workflow-tdd-plan` | tdd-plan, tdd-verify | diff --git a/docs/zh/commands/claude/index.md b/docs/zh/commands/claude/index.md index 8096e3a5..3b52df22 100644 --- a/docs/zh/commands/claude/index.md +++ b/docs/zh/commands/claude/index.md @@ -30,7 +30,7 @@ | 命令 | 功能 | 难度 | | --- | --- | --- | -| [`/workflow-lite-planex`](./workflow.md#lite-plan) | 轻量级交互式规划工作流 | Intermediate | +| [`/workflow-lite-plan`](./workflow.md#lite-plan) | 轻量级交互式规划工作流 | Intermediate | | [`/workflow-plan`](./workflow.md#plan) | 5 阶段规划工作流 | Intermediate | | [`/workflow-execute`](./workflow.md#execute) | 协调代理执行工作流任务 | Intermediate | | [`/workflow:replan`](./workflow.md#replan) | 交互式工作流重新规划 | Intermediate | diff --git a/docs/zh/commands/claude/workflow.md b/docs/zh/commands/claude/workflow.md index 8620c27d..128534f5 100644 --- a/docs/zh/commands/claude/workflow.md +++ b/docs/zh/commands/claude/workflow.md @@ -10,7 +10,7 @@ | 命令 | 功能 | 语法 | | --- | --- | --- | -| [`lite-plan`](#lite-plan) | 轻量级交互式规划工作流 | `/workflow-lite-planex [-y] [-e] "任务"` | +| [`lite-plan`](#lite-plan) | 轻量级交互式规划工作流 | `/workflow-lite-plan [-y] [-e] "任务"` | ### 标准工作流 @@ -70,7 +70,7 @@ **语法**: ```bash -/workflow-lite-planex [-y|--yes] [-e|--explore] "任务描述" | file.md +/workflow-lite-plan [-y|--yes] [-e|--explore] "任务描述" | file.md ``` **选项**: @@ -79,10 +79,10 @@ **示例**: ```bash # 基础规划 -/workflow-lite-planex "添加用户头像功能" +/workflow-lite-plan "添加用户头像功能" # 带探索 -/workflow-lite-planex -e "重构认证模块" +/workflow-lite-plan -e "重构认证模块" ``` ### plan diff --git a/docs/zh/reference/commands-skills.md b/docs/zh/reference/commands-skills.md index 5caa89e0..61a7dffe 100644 --- a/docs/zh/reference/commands-skills.md +++ b/docs/zh/reference/commands-skills.md @@ -43,7 +43,7 @@ | 类别 | 技能 | 内部流水线 | 用例 | |----------|-------|-------------------|----------| -| **Workflow** | workflow-lite-planex | explore → plan → confirm → execute | 快速功能、Bug 修复 | +| **Workflow** | workflow-lite-plan | explore → plan → confirm → execute | 快速功能、Bug 修复 | | **Workflow** | workflow-plan | session → context → convention → gen → verify/replan | 复杂功能规划 | | **Workflow** | workflow-execute | session discovery → task processing → commit | 执行预生成的计划 | | **Workflow** | workflow-tdd-plan | 6阶段 TDD plan → verify | TDD 开发 | @@ -81,7 +81,7 @@ | 技能 | 内部流水线 | |-------|-------------------| -| workflow-lite-planex | explore → plan → confirm → execute | +| workflow-lite-plan | explore → plan → confirm → execute | | workflow-plan | session → context → convention → gen → verify/replan | | workflow-execute | session discovery → task processing → commit | | workflow-tdd-plan | 6阶段 TDD plan → verify | @@ -357,16 +357,16 @@ | 任务类型 | 技能链 | |-----------|-------------| -| bugfix | workflow-lite-planex → workflow-test-fix | -| bugfix-hotfix | workflow-lite-planex | -| feature | workflow-lite-planex → workflow-test-fix | +| bugfix | workflow-lite-plan → workflow-test-fix | +| bugfix-hotfix | workflow-lite-plan | +| feature | workflow-lite-plan → workflow-test-fix | | feature-complex | workflow-plan → workflow-execute → workflow-test-fix | | refactor | workflow:refactor-cycle | | tdd | workflow-tdd-plan → workflow-execute | | test | workflow-test-fix | | test-fix | workflow-test-fix | | review | review-cycle | -| docs | workflow-lite-planex | +| docs | workflow-lite-plan | **6阶段执行**: 1. 加载任务 @@ -606,7 +606,7 @@ | 技能 | 内部流水线 | 描述 | |-------|-------------------|-------------| -| workflow-lite-planex | explore → plan → confirm → execute | 轻量级合并模式规划 | +| workflow-lite-plan | explore → plan → confirm → execute | 轻量级合并模式规划 | | workflow-plan | session → context → convention → gen → verify/replan | 带架构设计的完整规划 | | workflow-execute | session discovery → task processing → commit | 从规划会话执行 | | workflow-tdd-plan | 6阶段 TDD plan → verify | TDD 工作流规划 | @@ -716,7 +716,7 @@ ### 技能调用 (从代码) ```javascript -Skill({ skill: "workflow-lite-planex", args: '"任务描述"' }) +Skill({ skill: "workflow-lite-plan", args: '"任务描述"' }) Skill({ skill: "brainstorm", args: '"主题或问题"' }) Skill({ skill: "review-cycle", args: '--session="WFS-xxx"' }) ``` diff --git a/docs/zh/skills/claude-index.md b/docs/zh/skills/claude-index.md index 54e60e24..c32efc92 100644 --- a/docs/zh/skills/claude-index.md +++ b/docs/zh/skills/claude-index.md @@ -176,7 +176,7 @@ memory/ ```bash # 快速任务 -/workflow-lite-planex "Fix login bug" +/workflow-lite-plan "Fix login bug" # 完整开发 /workflow-plan "Add user notifications" @@ -229,7 +229,7 @@ memory/ - 测试覆盖 → `team-testing` 2. **工作流选择**: - - 超简单 → `workflow-lite-planex` + - 超简单 → `workflow-lite-plan` - 复杂功能 → `workflow-plan` → `workflow-execute` - TDD → `workflow-tdd-plan` - 测试修复 → `workflow-test-fix` diff --git a/docs/zh/skills/claude-workflow.md b/docs/zh/skills/claude-workflow.md index 355b43b5..16961b00 100644 --- a/docs/zh/skills/claude-workflow.md +++ b/docs/zh/skills/claude-workflow.md @@ -19,7 +19,7 @@ | --- | --- | --- | | `workflow-plan` | 统一规划技能（4 阶段工作流） | `/workflow-plan` | | `workflow-execute` | 代理协调执行 | `/workflow-execute` | -| `workflow-lite-planex` | 轻量级快速规划 | `/workflow-lite-planex` | +| `workflow-lite-plan` | 轻量级快速规划 | `/workflow-lite-plan` | | `workflow-multi-cli-plan` | 多 CLI 协作规划 | `/workflow-multi-cli-plan` | | `workflow-tdd-plan` | TDD 工作流 | `/workflow-tdd-plan` | | `workflow-test-fix` | 测试修复工作流 | `/workflow-test-fix` | @@ -182,13 +182,13 @@ Phase 5: 完成 --- -### workflow-lite-planex +### workflow-lite-plan **一句话定位**: 轻量级快速规划 — 超简单任务的快速规划和执行 **触发**: ```shell -/workflow-lite-planex +/workflow-lite-plan ``` **功能**: @@ -331,7 +331,7 @@ Wave 2: Issue 6-10 → 并行规划 → 并行执行 ## 最佳实践 1. **选择合适的工作流**: - - 超简单任务 → `workflow-lite-planex` + - 超简单任务 → `workflow-lite-plan` - 复杂功能 → `workflow-plan` → `workflow-execute` - TDD 开发 → `workflow-tdd-plan` - 测试修复 → `workflow-test-fix` diff --git a/docs/zh/skills/core-skills.md b/docs/zh/skills/core-skills.md index fd5b47ae..0a32bd11 100644 --- a/docs/zh/skills/core-skills.md +++ b/docs/zh/skills/core-skills.md @@ -679,11 +679,11 @@ Skill(skill="workflow-plan") --- -### workflow-lite-planex +### workflow-lite-plan **用途**：轻量级规划和执行技能 -**触发器**：`workflow-lite-planex` +**触发器**：`workflow-lite-plan` **说明**：统一的规划和执行技能（Phase 1: 规划，Phase 2: 执行），带提示增强。 @@ -696,7 +696,7 @@ Skill(skill="workflow-plan") **产物**：LITE_PLAN.md、执行结果 ```bash -Skill(skill="workflow-lite-planex") +Skill(skill="workflow-lite-plan") ``` --- @@ -851,7 +851,7 @@ Skill(skill="review-cycle") **使用场景**：快速迭代和快速原型 ```bash -Skill(skill="workflow-lite-planex") +Skill(skill="workflow-lite-plan") Skill(skill="workflow-execute") ``` @@ -1039,7 +1039,7 @@ Skill(skill="skill-tuning") | 层级 | 技能 | |------|------| | 元技能 | skill-generator、skill-tuning、workflow-skill-designer | -| 编排器 | workflow-plan、workflow-lite-planex、workflow-multi-cli-plan | +| 编排器 | workflow-plan、workflow-lite-plan、workflow-multi-cli-plan | | 执行器 | workflow-execute | | 团队负责人 | team-lifecycle (v5) | @@ -1085,7 +1085,7 @@ Skill(skill="skill-tuning") | `manage issue` | issue-manage | | `workflow-plan`、`workflow-plan-verify`、`workflow:replan` | workflow-plan | | `workflow-execute` | workflow-execute | -| `workflow-lite-planex` | workflow-lite-planex | +| `workflow-lite-plan` | workflow-lite-plan | | `workflow-multi-cli-plan`、`workflow:multi-cli-plan` | workflow-multi-cli-plan | | `workflow-tdd-plan` | workflow-tdd-plan | | `workflow-test-fix`、`test fix workflow` | workflow-test-fix | diff --git a/docs/zh/skills/index.md b/docs/zh/skills/index.md index 5644954f..f21af67f 100644 --- a/docs/zh/skills/index.md +++ b/docs/zh/skills/index.md @@ -56,7 +56,7 @@ Skills 是 CCW 可执行的、可复用的、领域特定的能力。每个技 | 技能 | 触发器 | 说明 | |------|--------|------| | [workflow-plan](./core-skills.md#workflow-plan) | `workflow-plan`, `workflow-plan-verify`, `workflow:replan` | 4 阶段规划带验证 | -| [workflow-lite-planex](./core-skills.md#workflow-lite-planex) | `workflow-lite-planex` | 轻量级规划 | +| [workflow-lite-plan](./core-skills.md#workflow-lite-plan) | `workflow-lite-plan` | 轻量级规划 | | [workflow-multi-cli-plan](./core-skills.md#workflow-multi-cli-plan) | `workflow-multi-cli-plan`, `workflow:multi-cli-plan` | 多 CLI 协作规划 | | [workflow-execute](./core-skills.md#workflow-execute) | `workflow-execute` | 任务执行协调 | | [workflow-tdd-plan](./core-skills.md#workflow-tdd-plan) | `workflow-tdd-plan` | TDD 红-绿-重构 | @@ -79,7 +79,7 @@ Skill(skill="review-cycle") #### 快速迭代 ```bash -Skill(skill="workflow-lite-planex") +Skill(skill="workflow-lite-plan") Skill(skill="workflow-execute") ``` @@ -203,7 +203,7 @@ Skill(skill="my-custom-skill", args="input") # 步骤 3：团队执行 Skill(skill="team-lifecycle-v4", args="Build user dashboard") # 或使用快速迭代: -# Skill(skill="workflow-lite-planex") +# Skill(skill="workflow-lite-plan") # 步骤 4：审查和优化 Skill(skill="review-code") @@ -267,7 +267,7 @@ Skill(skill="review-cycle", args="--max-iterations 3") ### 最佳效果提示 -1. **从小开始**：简单任务使用 `workflow-lite-planex` +1. **从小开始**：简单任务使用 `workflow-lite-plan` 2. **使用记忆**：用 `memory:capture` 捕获见解供将来参考 3. **验证计划**：执行前始终审查生成的计划 4. **迭代**：使用 `review-cycle` 持续改进 diff --git a/docs/zh/skills/reference.md b/docs/zh/skills/reference.md index f4f49d5a..9f66f352 100644 --- a/docs/zh/skills/reference.md +++ b/docs/zh/skills/reference.md @@ -28,7 +28,7 @@ | 技能 | 触发器 | 用途 | |------|--------|------| | **workflow-plan** | `workflow-plan`、`workflow-plan-verify`、`workflow:replan` | 4 阶段规划工作流，带验证和交互式重新规划 | -| **workflow-lite-planex** | `workflow-lite-planex` | 轻量级规划和执行技能 | +| **workflow-lite-plan** | `workflow-lite-plan` | 轻量级规划和执行技能 | | **workflow-multi-cli-plan** | `workflow-multi-cli-plan`、`workflow:multi-cli-plan` | 多 CLI 协作规划，带 ACE 上下文引擎 | | **workflow-execute** | `workflow-execute` | 协调工作流任务的代理执行 | | **workflow-tdd-plan** | `workflow-tdd-plan`、`workflow-tdd-verify` | TDD 工作流，带红-绿-重构任务链 | @@ -103,7 +103,7 @@ team lifecycle | `review code`、`code review`、`审查代码` | review-code | | `workflow:review-cycle` | review-cycle | | `workflow-plan` | workflow-plan | -| `workflow-lite-planex` | workflow-lite-planex | +| `workflow-lite-plan` | workflow-lite-plan | | `workflow-multi-cli-plan`、`workflow:multi-cli-plan` | workflow-multi-cli-plan | | `workflow-execute` | workflow-execute | | `workflow-tdd-plan` | workflow-tdd-plan | @@ -163,7 +163,7 @@ team lifecycle | Generator-Critic Loop | team-iterdev | | Wave Pipeline | team-planex | | Red-Green-Refactor | workflow-tdd-plan | -| Pure Orchestrator | workflow-plan、workflow-lite-planex | +| Pure Orchestrator | workflow-plan、workflow-lite-plan | | Progressive Phase Loading | workflow-plan、workflow-tdd-plan、team-lifecycle | ::: info 参见 diff --git a/docs/zh/workflows/comparison-table.md b/docs/zh/workflows/comparison-table.md index c12c9b13..721a482d 100644 --- a/docs/zh/workflows/comparison-table.md +++ b/docs/zh/workflows/comparison-table.md @@ -6,7 +6,7 @@ | 工作流 | 最佳用途 | 级别 | 自包含 | |----------|----------|-------|----------------| -| workflow-lite-planex | 快速任务、Bug 修复 | 2 (轻量级) | 是 | +| workflow-lite-plan | 快速任务、Bug 修复 | 2 (轻量级) | 是 | | workflow-plan → workflow-execute | 复杂功能 | 3-4 (标准) | 否 (需要 execute) | | workflow-tdd-plan → workflow-execute | TDD 开发 | 3 (标准) | 否 (需要 execute) | | workflow-test-fix | 测试生成/修复 | 3 (标准) | 是 | @@ -31,7 +31,7 @@ | 工作流 | 调用方式 | 流水线 | 用例 | 级别 | 自包含 | 自动链式到 | |----------|------------|----------|----------|-------|----------------|----------------| | **Plan+Execute 工作流** | -| workflow-lite-planex | `/ccw "任务"` (低/中复杂度自动选择) | explore → plan → confirm → execute | 快速功能、Bug 修复、简单任务 | 2 (轻量级) | 是 | workflow-test-fix | +| workflow-lite-plan | `/ccw "任务"` (低/中复杂度自动选择) | explore → plan → confirm → execute | 快速功能、Bug 修复、简单任务 | 2 (轻量级) | 是 | workflow-test-fix | | workflow-plan | `/ccw "复杂功能"` (高复杂度) | session → context → convention → gen → verify/replan | 复杂功能规划、正式验证 | 3-4 (标准) | 否 | workflow-execute | | workflow-execute | `/workflow-execute` (plan 之后) | session discovery → task processing → commit | 执行预生成的计划 | 3 (标准) | 是 | review-cycle (可选) | | workflow-multi-cli-plan | `/ccw "multi-cli plan: ..."` | ACE context → CLI discussion → plan → execute | 多视角规划 | 3 (标准) | 是 | (内部交接) | @@ -43,7 +43,7 @@ | brainstorm-with-file | `/ccw "brainstorm: ..."` | brainstorm + documented artifacts | 带会话文档的创意构思 | 4 (完整) | 否 | workflow-plan → execute | | collaborative-plan-with-file | `/ccw "collaborative plan: ..."` | understanding → parallel agents → plan-note.md | 多代理协作规划 | 3 (标准) | 否 | unified-execute-with-file | | **分析工作流** | -| analyze-with-file | `/ccw "analyze: ..."` | multi-CLI analysis → discussion.md | 深度理解、架构探索 | 3 (标准) | 否 | workflow-lite-planex | +| analyze-with-file | `/ccw "analyze: ..."` | multi-CLI analysis → discussion.md | 深度理解、架构探索 | 3 (标准) | 否 | workflow-lite-plan | | debug-with-file | `/ccw "debug: ..."` | hypothesis-driven iteration → debug.log | 系统化调试 | 3 (标准) | 是 | (独立) | | **审查工作流** | | review-cycle | `/ccw "review code"` | discovery → analysis → aggregation → deep-dive → completion | 代码审查、质量门禁 | 3 (标准) | 是 | fix mode (如有发现) | @@ -67,7 +67,7 @@ | 级别 | 工作流 | 特点 | |-------|-----------|-----------------| -| **2 (轻量级)** | workflow-lite-planex, docs | 快速执行、最少阶段 | +| **2 (轻量级)** | workflow-lite-plan, docs | 快速执行、最少阶段 | | **2.5 (桥接)** | issue pipeline, rapid-to-issue | 桥接到 Issue 工作流 | | **3 (标准)** | workflow-plan, workflow-execute, workflow-tdd-plan, workflow-test-fix, review-cycle, debug-with-file, analyze-with-file, workflow-multi-cli-plan | 完整规划/执行、多阶段 | | **4 (完整)** | brainstorm, spec-generator, brainstorm-with-file, roadmap-with-file | 完整探索、规格化 | @@ -80,13 +80,13 @@ | 源工作流 | 自动链式到 | 条件 | |-----------------|---------------|-----------| -| workflow-lite-planex | workflow-test-fix | 默认 (除非 skip-tests) | +| workflow-lite-plan | workflow-test-fix | 默认 (除非 skip-tests) | | workflow-plan | workflow-execute | 计划确认后 | | workflow-execute | review-cycle | 用户通过 Phase 6 选择 | | workflow-tdd-plan | workflow-execute | TDD 计划验证后 | | brainstorm | workflow-plan | 自动链式到正式规划 | | brainstorm-with-file | workflow-plan → workflow-execute | 自动 | -| analyze-with-file | workflow-lite-planex | 自动 | +| analyze-with-file | workflow-lite-plan | 自动 | | debug-with-file | (无) | 独立 | | collaborative-plan-with-file | unified-execute-with-file | 自动 | | roadmap-with-file | team-planex | 自动 | @@ -99,7 +99,7 @@ | 工作流 | 自包含 | 说明 | |----------|---------------|-------| -| workflow-lite-planex | 是 | 完整 plan + execute | +| workflow-lite-plan | 是 | 完整 plan + execute | | workflow-plan | 否 | 需要 workflow-execute | | workflow-execute | 是 | 完整执行 | | workflow-tdd-plan | 否 | 需要 workflow-execute |
Skill 触发词使用场景
workflow-lite-planex轻量规划、单模块功能
workflow-lite-plan轻量规划、单模块功能（Skill 交接给 lite-execute）
workflow-multi-cli-plan多 CLI 协同分析
workflow-plan完整规划与会话持久化
workflow-tdd-plan测试驱动开发