catlog22/Claude-Code-Workflow
1
0
Fork 0
mirror of https://github.com/catlog22/Claude-Code-Workflow.git synced 2026-03-19 18:58:47 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: apply Pattern 10 to all team skills — @ strong refs + workspace resolution

Browse Source 
- SKILL.md: coordinator entry uses `@roles/coordinator/role.md` strong reference
- coordinator/role.md: command delegations use `@commands/xxx.md` prefix
- coordinator Phase 2: resolve project_root + skill_root via `Bash pwd` before TeamCreate
- Worker Spawn Template: role_spec uses absolute path from session skill_root
- skills_lib/team-skill-designer: document Pattern 10 + add quality checks

Covers 17 team skills: team-lifecycle-v4, team-frontend, team-ultra-analyze,
team-ux-improve, team-arch-opt, team-brainstorm, team-review, team-uidesign,
team-issue, team-iterdev, team-perf-opt, team-planex, team-quality-assurance,
team-testing, team-tech-debt, team-coordinate, team-roadmap-dev, team-frontend-debug

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
catlog22
2026-03-18 16:01:43 +08:00
parent 398601f885
commit b91bdcdfa4
35 changed files with 307 additions and 237 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
.claude/skills/team-arch-opt/SKILL.md
View File

@@ -44,7 +44,7 @@ Skill(skill="team-arch-opt", args="task description")
Parse `$ARGUMENTS`: Parse `$ARGUMENTS`:
- Has `--role <name>` → Read `roles/<name>/role.md`, execute Phase 2-4 - Has `--role <name>` → Read `roles/<name>/role.md`, execute Phase 2-4
- No `--role` → Read `roles/coordinator/role.md`, execute entry router - No `--role` → `@roles/coordinator/role.md`, execute entry router
## Shared Constants ## Shared Constants
@@ -66,14 +66,14 @@ Agent({
run_in_background: true, run_in_background: true,
prompt: `## Role Assignment prompt: `## Role Assignment
role: <role> role: <role>
role_spec: ~ or <project>/.claude/skills/team-arch-opt/roles/<role>/role.md role_spec: <skill_root>/roles/<role>/role.md
session: <session-folder> session: <session-folder>
session_id: <session-id> session_id: <session-id>
team_name: arch-opt team_name: arch-opt
requirement: <task-description> requirement: <task-description>
inner_loop: <true|false> inner_loop: <true|false>
Read role_spec file to load Phase 2-4 domain instructions. Read role_spec file (@<skill_root>/roles/<role>/role.md) to load Phase 2-4 domain instructions.
Execute built-in Phase 1 (task discovery) -> role Phase 2-4 -> built-in Phase 5 (report).` Execute built-in Phase 1 (task discovery) -> role Phase 2-4 -> built-in Phase 5 (report).`
}) })
``` ```

21
.claude/skills/team-arch-opt/roles/coordinator/role.md
View File

@@ -46,7 +46,7 @@ When coordinator needs to execute a specific phase:
| Interrupted session | Active session in .workflow/.team/TAO-* | -> Phase 0 | | Interrupted session | Active session in .workflow/.team/TAO-* | -> Phase 0 |
| New session | None of above | -> Phase 1 | | New session | None of above | -> Phase 1 |
For callback/check/resume/consensus/adapt/complete: load commands/monitor.md, execute handler, STOP. For callback/check/resume/consensus/adapt/complete: load @commands/monitor.md, execute handler, STOP.
## Phase 0: Session Resume Check ## Phase 0: Session Resume Check
@@ -81,11 +81,14 @@ TEXT-LEVEL ONLY. No source code reading.
## Phase 2: Create Team + Initialize Session ## Phase 2: Create Team + Initialize Session
1. Generate session ID: `TAO-<slug>-<date>` 1. Resolve workspace paths (MUST do first):
2. Create session folder structure - `project_root` = result of `Bash({ command: "pwd" })`
3. TeamCreate with team name `arch-opt` - `skill_root` = `<project_root>/.claude/skills/team-arch-opt`
4. Write session.json with parallel_mode, max_branches, branches, independent_targets, fix_cycles 2. Generate session ID: `TAO-<slug>-<date>`
5. Initialize meta.json via team_msg state_update: 3. Create session folder structure
4. TeamCreate with team name `arch-opt`
5. Write session.json with parallel_mode, max_branches, branches, independent_targets, fix_cycles
6. Initialize meta.json via team_msg state_update:
``` ```
mcp__ccw-tools__team_msg({ mcp__ccw-tools__team_msg({
operation: "log", session_id: "<id>", from: "coordinator", operation: "log", session_id: "<id>", from: "coordinator",
@@ -93,11 +96,11 @@ TEXT-LEVEL ONLY. No source code reading.
data: { pipeline_mode: "<mode>", pipeline_stages: ["analyzer","designer","refactorer","validator","reviewer"], team_name: "arch-opt" } data: { pipeline_mode: "<mode>", pipeline_stages: ["analyzer","designer","refactorer","validator","reviewer"], team_name: "arch-opt" }
}) })
``` ```
6. Write session.json 7. Write session.json
## Phase 3: Create Task Chain ## Phase 3: Create Task Chain
Delegate to commands/dispatch.md: Delegate to @commands/dispatch.md:
1. Read dependency graph and parallel mode from session.json 1. Read dependency graph and parallel mode from session.json
2. Topological sort tasks 2. Topological sort tasks
3. Create tasks via TaskCreate with blockedBy 3. Create tasks via TaskCreate with blockedBy
@@ -105,7 +108,7 @@ Delegate to commands/dispatch.md:
## Phase 4: Spawn-and-Stop ## Phase 4: Spawn-and-Stop
Delegate to commands/monitor.md#handleSpawnNext: Delegate to @commands/monitor.md#handleSpawnNext:
1. Find ready tasks (pending + blockedBy resolved) 1. Find ready tasks (pending + blockedBy resolved)
2. Spawn team-worker agents (see SKILL.md Spawn Template) 2. Spawn team-worker agents (see SKILL.md Spawn Template)
3. Output status summary 3. Output status summary

10
.claude/skills/team-brainstorm/SKILL.md
View File

@@ -43,7 +43,7 @@ Skill(skill="team-brainstorm", args="topic description")
Parse `$ARGUMENTS`: Parse `$ARGUMENTS`:
- Has `--role <name>` → Read `roles/<name>/role.md`, execute Phase 2-4 - Has `--role <name>` → Read `roles/<name>/role.md`, execute Phase 2-4
- No `--role` → Read `roles/coordinator/role.md`, execute entry router - No `--role` → `@roles/coordinator/role.md`, execute entry router
## Shared Constants ## Shared Constants
@@ -65,14 +65,14 @@ Agent({
run_in_background: true, run_in_background: true,
prompt: `## Role Assignment prompt: `## Role Assignment
role: <role> role: <role>
role_spec: ~ or <project>/.claude/skills/team-brainstorm/roles/<role>/role.md role_spec: <skill_root>/roles/<role>/role.md
session: <session-folder> session: <session-folder>
session_id: <session-id> session_id: <session-id>
team_name: brainstorm team_name: brainstorm
requirement: <topic-description> requirement: <topic-description>
inner_loop: false inner_loop: false
Read role_spec file to load Phase 2-4 domain instructions. Read role_spec file (@<skill_root>/roles/<role>/role.md) to load Phase 2-4 domain instructions.
Execute built-in Phase 1 (task discovery) -> role Phase 2-4 -> built-in Phase 5 (report).` Execute built-in Phase 1 (task discovery) -> role Phase 2-4 -> built-in Phase 5 (report).`
}) })
``` ```
@@ -89,7 +89,7 @@ Agent({
run_in_background: true, run_in_background: true,
prompt: `## Role Assignment prompt: `## Role Assignment
role: ideator role: ideator
role_spec: ~ or <project>/.claude/skills/team-brainstorm/roles/ideator/role.md role_spec: <skill_root>/roles/ideator/role.md
session: <session-folder> session: <session-folder>
session_id: <session-id> session_id: <session-id>
team_name: brainstorm team_name: brainstorm
@@ -97,7 +97,7 @@ requirement: <topic-description>
agent_name: ideator-<N> agent_name: ideator-<N>
inner_loop: false inner_loop: false
Read role_spec file to load Phase 2-4 domain instructions. Read role_spec file (@<skill_root>/roles/ideator/role.md) to load Phase 2-4 domain instructions.
Execute built-in Phase 1 (task discovery, owner=ideator-<N>) -> role Phase 2-4 -> built-in Phase 5 (report).` Execute built-in Phase 1 (task discovery, owner=ideator-<N>) -> role Phase 2-4 -> built-in Phase 5 (report).`
}) })
``` ```

21
.claude/skills/team-brainstorm/roles/coordinator/role.md
View File

@@ -44,7 +44,7 @@ When coordinator needs to execute a specific phase:
| Interrupted session | Active session in .workflow/.team/BRS-* | -> Phase 0 | | Interrupted session | Active session in .workflow/.team/BRS-* | -> Phase 0 |
| New session | None of above | -> Phase 1 | | New session | None of above | -> Phase 1 |
For callback/check/resume/consensus/adapt/complete: load commands/monitor.md, execute handler, STOP. For callback/check/resume/consensus/adapt/complete: load @commands/monitor.md, execute handler, STOP.
## Phase 0: Session Resume Check ## Phase 0: Session Resume Check
@@ -78,11 +78,14 @@ TEXT-LEVEL ONLY. No source code reading.
## Phase 2: Create Team + Initialize Session ## Phase 2: Create Team + Initialize Session
1. Generate session ID: `BRS-<topic-slug>-<date>` 1. Resolve workspace paths (MUST do first):
2. Create session folder structure: ideas/, critiques/, synthesis/, evaluation/, wisdom/, .msg/ - `project_root` = result of `Bash({ command: "pwd" })`
3. TeamCreate with team name `brainstorm` - `skill_root` = `<project_root>/.claude/skills/team-brainstorm`
4. Write session.json with pipeline, angles, gc_round=0, max_gc_rounds=2 2. Generate session ID: `BRS-<topic-slug>-<date>`
5. Initialize meta.json via team_msg state_update: 3. Create session folder structure: ideas/, critiques/, synthesis/, evaluation/, wisdom/, .msg/
4. TeamCreate with team name `brainstorm`
5. Write session.json with pipeline, angles, gc_round=0, max_gc_rounds=2
6. Initialize meta.json via team_msg state_update:
``` ```
mcp__ccw-tools__team_msg({ mcp__ccw-tools__team_msg({
operation: "log", session_id: "<id>", from: "coordinator", operation: "log", session_id: "<id>", from: "coordinator",
@@ -90,18 +93,18 @@ TEXT-LEVEL ONLY. No source code reading.
data: { pipeline_mode: "<mode>", pipeline_stages: ["ideator","challenger","synthesizer","evaluator"], team_name: "brainstorm", topic: "<topic>", angles: [...], gc_round: 0 } data: { pipeline_mode: "<mode>", pipeline_stages: ["ideator","challenger","synthesizer","evaluator"], team_name: "brainstorm", topic: "<topic>", angles: [...], gc_round: 0 }
}) })
``` ```
6. Write session.json 7. Write session.json
## Phase 3: Create Task Chain ## Phase 3: Create Task Chain
Delegate to commands/dispatch.md: Delegate to @commands/dispatch.md:
1. Read pipeline mode and angles from session.json 1. Read pipeline mode and angles from session.json
2. Create tasks for selected pipeline with correct blockedBy 2. Create tasks for selected pipeline with correct blockedBy
3. Update session.json with task count 3. Update session.json with task count
## Phase 4: Spawn-and-Stop ## Phase 4: Spawn-and-Stop
Delegate to commands/monitor.md#handleSpawnNext: Delegate to @commands/monitor.md#handleSpawnNext:
1. Find ready tasks (pending + blockedBy resolved) 1. Find ready tasks (pending + blockedBy resolved)
2. Spawn team-worker agents (see SKILL.md Spawn Template) 2. Spawn team-worker agents (see SKILL.md Spawn Template)
3. Output status summary 3. Output status summary

32
.claude/skills/team-coordinate/roles/coordinator/role.md
View File

@@ -110,7 +110,7 @@ When coordinator is invoked, first detect the invocation type:
| Interrupted session | Active/paused session exists in `.workflow/.team/TC-*` | -> Phase 0 (Resume Check) | | Interrupted session | Active/paused session exists in `.workflow/.team/TC-*` | -> Phase 0 (Resume Check) |
| New session | None of above | -> Phase 1 (Task Analysis) | | New session | None of above | -> Phase 1 (Task Analysis) |
For callback/check/resume/adapt/complete: load `commands/monitor.md` and execute the appropriate handler, then STOP. For callback/check/resume/adapt/complete: load `@commands/monitor.md` and execute the appropriate handler, then STOP.
### Router Implementation ### Router Implementation
@@ -166,7 +166,7 @@ For callback/check/resume/adapt/complete: load `commands/monitor.md` and execute
- What deliverables are expected? (documents, code, analysis reports) - What deliverables are expected? (documents, code, analysis reports)
- Any constraints? (timeline, technology, style) - Any constraints? (timeline, technology, style)
3. **Delegate to `commands/analyze-task.md`**: 3. **Delegate to `@commands/analyze-task.md`**:
- Signal detection: scan keywords -> infer capabilities - Signal detection: scan keywords -> infer capabilities
- Artifact inference: each capability -> default output type (.md) - Artifact inference: each capability -> default output type (.md)
- Dependency graph: build DAG of work streams - Dependency graph: build DAG of work streams
@@ -203,15 +203,19 @@ Regardless of complexity score or role count, coordinator MUST:
**Workflow**: **Workflow**:
1. **Check `needs_research` flag** from task-analysis.json: 1. Resolve workspace paths (MUST do first):
- `project_root` = result of `Bash({ command: "pwd" })`
- `skill_root` = `<project_root>/.claude/skills/team-coordinate`
2. **Check `needs_research` flag** from task-analysis.json:
- If `true`: **Spawn researcher worker first** to gather codebase context - If `true`: **Spawn researcher worker first** to gather codebase context
- Wait for researcher callback - Wait for researcher callback
- Merge research findings into task context - Merge research findings into task context
- Update task-analysis.json with enriched context - Update task-analysis.json with enriched context
2. **Generate session ID**: `TC-<slug>-<date>` (slug from first 3 meaningful words of task) 3. **Generate session ID**: `TC-<slug>-<date>` (slug from first 3 meaningful words of task)
3. **Create session folder structure**: 4. **Create session folder structure**:
``` ```
.workflow/.team/<session-id>/ .workflow/.team/<session-id>/
+-- role-specs/ +-- role-specs/
@@ -222,11 +226,11 @@ Regardless of complexity score or role count, coordinator MUST:
+-- .msg/ +-- .msg/
``` ```
4. **Call TeamCreate** with team name derived from session ID 5. **Call TeamCreate** with team name derived from session ID
5. **Read `specs/role-spec-template.md`** for Behavioral Traits + Reference Patterns 6. **Read `specs/role-spec-template.md`** for Behavioral Traits + Reference Patterns
6. **For each role in task-analysis.json#roles**: 7. **For each role in task-analysis.json#roles**:
- Fill YAML frontmatter: role, prefix, inner_loop, additional_members, message_types - Fill YAML frontmatter: role, prefix, inner_loop, additional_members, message_types
- **Compose Phase 2-4 content** (NOT copy from template): - **Compose Phase 2-4 content** (NOT copy from template):
- Phase 2: Derive input sources and context loading steps from **task description + upstream dependencies** - Phase 2: Derive input sources and context loading steps from **task description + upstream dependencies**
@@ -235,14 +239,14 @@ Regardless of complexity score or role count, coordinator MUST:
- Reference Patterns may guide phase structure, but task description determines specific content - Reference Patterns may guide phase structure, but task description determines specific content
- Write generated role-spec to `<session>/role-specs/<role-name>.md` - Write generated role-spec to `<session>/role-specs/<role-name>.md`
7. **Register roles** in team-session.json#roles (with `role_spec` path instead of `role_file`) 8. **Register roles** in team-session.json#roles (with `role_spec` path instead of `role_file`)
8. **Initialize shared infrastructure**: 9. **Initialize shared infrastructure**:
- `wisdom/learnings.md`, `wisdom/decisions.md`, `wisdom/issues.md` (empty with headers) - `wisdom/learnings.md`, `wisdom/decisions.md`, `wisdom/issues.md` (empty with headers)
- `explorations/cache-index.json` (`{ "entries": [] }`) - `explorations/cache-index.json` (`{ "entries": [] }`)
- `discussions/` (empty directory) - `discussions/` (empty directory)
9. **Initialize pipeline metadata** via team_msg: 10. **Initialize pipeline metadata** via team_msg:
```typescript ```typescript
// 使用 team_msg 将 pipeline 元数据写入 .msg/meta.json // 使用 team_msg 将 pipeline 元数据写入 .msg/meta.json
// 注意: 此处为动态角色，执行时需将 <placeholders> 替换为 task-analysis.json 中生成的实际角色列表 // 注意: 此处为动态角色，执行时需将 <placeholders> 替换为 task-analysis.json 中生成的实际角色列表
@@ -261,7 +265,7 @@ mcp__ccw-tools__team_msg({
}) })
``` ```
10. **Write team-session.json** with: session_id, task_description, status="active", roles, pipeline (empty), active_workers=[], completion_action="interactive", created_at 11. **Write team-session.json** with: session_id, task_description, status="active", roles, pipeline (empty), active_workers=[], completion_action="interactive", created_at
**Success**: Session created, role-spec files generated, shared infrastructure initialized. **Success**: Session created, role-spec files generated, shared infrastructure initialized.
@@ -271,7 +275,7 @@ mcp__ccw-tools__team_msg({
**Objective**: Dispatch tasks based on dependency graph with proper dependencies. **Objective**: Dispatch tasks based on dependency graph with proper dependencies.
Delegate to `commands/dispatch.md` which creates the full task chain: Delegate to `@commands/dispatch.md` which creates the full task chain:
1. Reads dependency_graph from task-analysis.json 1. Reads dependency_graph from task-analysis.json
2. Topological sorts tasks 2. Topological sorts tasks
3. Creates tasks via TaskCreate with correct blockedBy 3. Creates tasks via TaskCreate with correct blockedBy
@@ -291,7 +295,7 @@ Delegate to `commands/dispatch.md` which creates the full task chain:
**Design**: Spawn-and-Stop + Callback pattern, with worker fast-advance. **Design**: Spawn-and-Stop + Callback pattern, with worker fast-advance.
**Workflow**: **Workflow**:
1. Load `commands/monitor.md` 1. Load `@commands/monitor.md`
2. Find tasks with: status=pending, blockedBy all resolved, owner assigned 2. Find tasks with: status=pending, blockedBy all resolved, owner assigned
3. For each ready task -> spawn team-worker (see SKILL.md Coordinator Spawn Template) 3. For each ready task -> spawn team-worker (see SKILL.md Coordinator Spawn Template)
4. Output status summary with execution graph 4. Output status summary with execution graph

20
.claude/skills/team-frontend-debug/SKILL.md
View File

@@ -54,7 +54,7 @@ Skill(skill="team-frontend-debug", args="feature list or bug description")
Parse `$ARGUMENTS`: Parse `$ARGUMENTS`:
- Has `--role <name>` → Read `roles/<name>/role.md`, execute Phase 2-4 - Has `--role <name>` → Read `roles/<name>/role.md`, execute Phase 2-4
- No `--role` → Read `roles/coordinator/role.md`, execute entry router - No `--role` → `@roles/coordinator/role.md`, execute entry router
## Shared Constants ## Shared Constants
@@ -63,6 +63,20 @@ Parse `$ARGUMENTS`:
- **CLI tools**: `ccw cli --mode analysis` (read-only), `ccw cli --mode write` (modifications) - **CLI tools**: `ccw cli --mode analysis` (read-only), `ccw cli --mode write` (modifications)
- **Message bus**: `mcp__ccw-tools__team_msg(session_id=<session-id>, ...)` - **Message bus**: `mcp__ccw-tools__team_msg(session_id=<session-id>, ...)`
## Workspace Resolution
Coordinator MUST resolve paths at Phase 2 before TeamCreate:
1. Run `Bash({ command: "pwd" })` → capture `project_root` (absolute path)
2. `skill_root = <project_root>/.claude/skills/team-frontend-debug`
3. Store in `team-session.json`:
```json
{ "project_root": "/abs/path/to/project", "skill_root": "/abs/path/to/skill" }
```
4. All worker `role_spec` values MUST use `<skill_root>/roles/<role>/role.md` (absolute)
This ensures workers spawned with `run_in_background: true` always receive an absolute, resolvable path regardless of their working directory.
## Chrome DevTools MCP Tools ## Chrome DevTools MCP Tools
All browser inspection operations use Chrome DevTools MCP. Reproducer and Verifier are primary consumers. All browser inspection operations use Chrome DevTools MCP. Reproducer and Verifier are primary consumers.
@@ -99,14 +113,14 @@ Agent({
run_in_background: true, run_in_background: true,
prompt: `## Role Assignment prompt: `## Role Assignment
role: <role> role: <role>
role_spec: ~ or <project>/.claude/skills/team-frontend-debug/roles/<role>/role.md role_spec: <skill_root>/roles/<role>/role.md
session: <session-folder> session: <session-folder>
session_id: <session-id> session_id: <session-id>
team_name: <team-name> team_name: <team-name>
requirement: <task-description> requirement: <task-description>
inner_loop: <true|false> inner_loop: <true|false>
Read role_spec file to load Phase 2-4 domain instructions. Read role_spec file (@<skill_root>/roles/<role>/role.md) to load Phase 2-4 domain instructions.
Execute built-in Phase 1 (task discovery) -> role Phase 2-4 -> built-in Phase 5 (report).` Execute built-in Phase 1 (task discovery) -> role Phase 2-4 -> built-in Phase 5 (report).`
}) })
``` ```

13
.claude/skills/team-frontend-debug/roles/coordinator/role.md
View File

@@ -67,14 +67,17 @@ TEXT-LEVEL ONLY. No source code reading.
- Test mode: base URL, feature list - Test mode: base URL, feature list
- Debug mode: bug description, URL, reproduction steps - Debug mode: bug description, URL, reproduction steps
3. Clarify if ambiguous (AskUserQuestion) 3. Clarify if ambiguous (AskUserQuestion)
4. Delegate to commands/analyze.md 4. Delegate to @commands/analyze.md
5. Output: task-analysis.json 5. Output: task-analysis.json
6. CRITICAL: Always proceed to Phase 2, never skip team workflow 6. CRITICAL: Always proceed to Phase 2, never skip team workflow
## Phase 2: Create Team + Initialize Session ## Phase 2: Create Team + Initialize Session
1. Generate session ID: TFD-<slug>-<date> 1. Resolve workspace paths (MUST do first):
2. Create session folder structure: - `project_root` = result of `Bash({ command: "pwd" })`
- `skill_root` = `<project_root>/.claude/skills/team-frontend-debug`
2. Generate session ID: TFD-<slug>-<date>
3. Create session folder structure:
``` ```
.workflow/.team/TFD-<slug>-<date>/ .workflow/.team/TFD-<slug>-<date>/
├── team-session.json ├── team-session.json
@@ -91,7 +94,7 @@ TEXT-LEVEL ONLY. No source code reading.
## Phase 3: Create Task Chain ## Phase 3: Create Task Chain
Delegate to commands/dispatch.md: Delegate to @commands/dispatch.md:
1. Read dependency graph from task-analysis.json 1. Read dependency graph from task-analysis.json
2. Read specs/pipelines.md for debug-pipeline task registry 2. Read specs/pipelines.md for debug-pipeline task registry
3. Topological sort tasks 3. Topological sort tasks
@@ -100,7 +103,7 @@ Delegate to commands/dispatch.md:
## Phase 4: Spawn-and-Stop ## Phase 4: Spawn-and-Stop
Delegate to commands/monitor.md#handleSpawnNext: Delegate to @commands/monitor.md#handleSpawnNext:
1. Find ready tasks (pending + blockedBy resolved) 1. Find ready tasks (pending + blockedBy resolved)
2. Spawn team-worker agents (see SKILL.md Spawn Template) 2. Spawn team-worker agents (see SKILL.md Spawn Template)
3. Output status summary 3. Output status summary

6
.claude/skills/team-frontend/SKILL.md
View File

@@ -44,7 +44,7 @@ Skill(skill="team-frontend", args="task description")
Parse `$ARGUMENTS`: Parse `$ARGUMENTS`:
- Has `--role <name>` → Read `roles/<name>/role.md`, execute Phase 2-4 - Has `--role <name>` → Read `roles/<name>/role.md`, execute Phase 2-4
- No `--role` → Read `roles/coordinator/role.md`, execute entry router - No `--role` → `@roles/coordinator/role.md`, execute entry router
## Shared Constants ## Shared Constants
@@ -66,14 +66,14 @@ Agent({
run_in_background: true, run_in_background: true,
prompt: `## Role Assignment prompt: `## Role Assignment
role: <role> role: <role>
role_spec: ~ or <project>/.claude/skills/team-frontend/roles/<role>/role.md role_spec: <skill_root>/roles/<role>/role.md
session: <session-folder> session: <session-folder>
session_id: <session-id> session_id: <session-id>
team_name: frontend team_name: frontend
requirement: <task-description> requirement: <task-description>
inner_loop: <true|false> inner_loop: <true|false>
Read role_spec file to load Phase 2-4 domain instructions. Read role_spec file (@<skill_root>/roles/<role>/role.md) to load Phase 2-4 domain instructions.
Execute built-in Phase 1 (task discovery) -> role Phase 2-4 -> built-in Phase 5 (report).` Execute built-in Phase 1 (task discovery) -> role Phase 2-4 -> built-in Phase 5 (report).`
}) })
``` ```

25
.claude/skills/team-frontend/roles/coordinator/role.md
View File

@@ -42,7 +42,7 @@ When coordinator needs to execute a command:
| Interrupted session | Active/paused session in .workflow/.team/FE-* | -> Phase 0 | | Interrupted session | Active/paused session in .workflow/.team/FE-* | -> Phase 0 |
| New session | None of above | -> Phase 1 | | New session | None of above | -> Phase 1 |
For callback/check/resume/complete: load commands/monitor.md, execute handler, STOP. For callback/check/resume/complete: load @commands/monitor.md, execute handler, STOP.
## Phase 0: Session Resume Check ## Phase 0: Session Resume Check
@@ -56,7 +56,7 @@ For callback/check/resume/complete: load commands/monitor.md, execute handler, S
TEXT-LEVEL ONLY. No source code reading. TEXT-LEVEL ONLY. No source code reading.
1. Parse task description from $ARGUMENTS 1. Parse task description from $ARGUMENTS
2. Delegate to commands/analyze.md -> produces task-analysis.json 2. Delegate to @commands/analyze.md -> produces task-analysis.json
3. Ask for missing parameters via AskUserQuestion: 3. Ask for missing parameters via AskUserQuestion:
**Scope Selection**: **Scope Selection**:
@@ -83,15 +83,18 @@ TEXT-LEVEL ONLY. No source code reading.
## Phase 2: Session & Team Setup ## Phase 2: Session & Team Setup
1. Generate session ID: `FE-<slug>-<YYYY-MM-DD>` 1. Resolve workspace paths (MUST do first):
2. Create session folder structure: - `project_root` = result of `Bash({ command: "pwd" })`
- `skill_root` = `<project_root>/.claude/skills/team-frontend`
3. Generate session ID: `FE-<slug>-<YYYY-MM-DD>`
4. Create session folder structure:
``` ```
mkdir -p .workflow/.team/<session-id>/{.msg,wisdom,analysis,architecture,qa,build} mkdir -p .workflow/.team/<session-id>/{.msg,wisdom,analysis,architecture,qa,build}
``` ```
3. TeamCreate with team name: `TeamCreate({ team_name: "frontend" })` 5. TeamCreate with team name: `TeamCreate({ team_name: "frontend" })`
4. Read specs/pipelines.md -> select pipeline based on scope 6. Read specs/pipelines.md -> select pipeline based on scope
5. Register roles in session state 7. Register roles in session state
6. Initialize meta.json with pipeline metadata: 8. Initialize meta.json with pipeline metadata:
```typescript ```typescript
mcp__ccw-tools__team_msg({ mcp__ccw-tools__team_msg({
operation: "log", session_id: "<id>", from: "coordinator", operation: "log", session_id: "<id>", from: "coordinator",
@@ -106,18 +109,18 @@ mcp__ccw-tools__team_msg({
} }
}) })
``` ```
7. Write session.json 9. Write session.json
## Phase 3: Task Chain Creation ## Phase 3: Task Chain Creation
Delegate to commands/dispatch.md: Delegate to @commands/dispatch.md:
1. Read specs/pipelines.md for selected pipeline task registry 1. Read specs/pipelines.md for selected pipeline task registry
2. Create tasks via TaskCreate with blockedBy 2. Create tasks via TaskCreate with blockedBy
3. Update session.json 3. Update session.json
## Phase 4: Spawn-and-Stop ## Phase 4: Spawn-and-Stop
Delegate to commands/monitor.md#handleSpawnNext: Delegate to @commands/monitor.md#handleSpawnNext:
1. Find ready tasks (pending + blockedBy resolved) 1. Find ready tasks (pending + blockedBy resolved)
2. Spawn team-worker agents (see SKILL.md Spawn Template) 2. Spawn team-worker agents (see SKILL.md Spawn Template)
3. Output status summary 3. Output status summary

10
.claude/skills/team-issue/SKILL.md
View File

@@ -44,7 +44,7 @@ Skill(skill="team-issue", args="<issue-ids> [--mode=<mode>]")
Parse `$ARGUMENTS`: Parse `$ARGUMENTS`:
- Has `--role <name>` → Read `roles/<name>/role.md`, execute Phase 2-4 - Has `--role <name>` → Read `roles/<name>/role.md`, execute Phase 2-4
- No `--role` → Read `roles/coordinator/role.md`, execute entry router - No `--role` → `@roles/coordinator/role.md`, execute entry router
## Shared Constants ## Shared Constants
@@ -67,14 +67,14 @@ Agent({
run_in_background: true, run_in_background: true,
prompt: `## Role Assignment prompt: `## Role Assignment
role: <role> role: <role>
role_spec: ~ or <project>/.claude/skills/team-issue/roles/<role>/role.md role_spec: <skill_root>/roles/<role>/role.md
session: <session-folder> session: <session-folder>
session_id: <session-id> session_id: <session-id>
team_name: issue team_name: issue
requirement: <task-description> requirement: <task-description>
inner_loop: false inner_loop: false
Read role_spec file to load Phase 2-4 domain instructions. Read role_spec file (@<skill_root>/roles/<role>/role.md) to load Phase 2-4 domain instructions.
Execute built-in Phase 1 (task discovery) -> role Phase 2-4 -> built-in Phase 5 (report).` Execute built-in Phase 1 (task discovery) -> role Phase 2-4 -> built-in Phase 5 (report).`
}) })
``` ```
@@ -89,7 +89,7 @@ Agent({
run_in_background: true, run_in_background: true,
prompt: `## Role Assignment prompt: `## Role Assignment
role: <role> role: <role>
role_spec: ~ or <project>/.claude/skills/team-issue/roles/<role>/role.md role_spec: <skill_root>/roles/<role>/role.md
session: <session-folder> session: <session-folder>
session_id: <session-id> session_id: <session-id>
team_name: issue team_name: issue
@@ -97,7 +97,7 @@ requirement: <task-description>
agent_name: <role>-<N> agent_name: <role>-<N>
inner_loop: false inner_loop: false
Read role_spec file to load Phase 2-4 domain instructions. Read role_spec file (@<skill_root>/roles/<role>/role.md) to load Phase 2-4 domain instructions.
Execute built-in Phase 1 (task discovery, owner=<role>-<N>) -> role Phase 2-4 -> built-in Phase 5 (report).` Execute built-in Phase 1 (task discovery, owner=<role>-<N>) -> role Phase 2-4 -> built-in Phase 5 (report).`
}) })
``` ```

21
.claude/skills/team-issue/roles/coordinator/role.md
View File

@@ -49,7 +49,7 @@ When coordinator needs to execute a specific phase:
| Interrupted session | Active session in .workflow/.team/TISL-* | -> Phase 0 | | Interrupted session | Active session in .workflow/.team/TISL-* | -> Phase 0 |
| New session | None of above | -> Phase 1 | | New session | None of above | -> Phase 1 |
For callback/check/resume/consensus/adapt/complete: load `commands/monitor.md`, execute handler, STOP. For callback/check/resume/consensus/adapt/complete: load `@commands/monitor.md`, execute handler, STOP.
## Phase 0: Session Resume Check ## Phase 0: Session Resume Check
@@ -95,14 +95,17 @@ TEXT-LEVEL ONLY. No source code reading.
## Phase 2: Create Team + Initialize Session ## Phase 2: Create Team + Initialize Session
1. Generate session ID: `TISL-<issue-slug>-<date>` 1. Resolve workspace paths (MUST do first):
2. Create session folder structure: - `project_root` = result of `Bash({ command: "pwd" })`
- `skill_root` = `<project_root>/.claude/skills/team-issue`
2. Generate session ID: `TISL-<issue-slug>-<date>`
3. Create session folder structure:
``` ```
Bash("mkdir -p .workflow/.team/TISL-<slug>-<date>/{explorations,solutions,audits,queue,builds,wisdom,.msg}") Bash("mkdir -p .workflow/.team/TISL-<slug>-<date>/{explorations,solutions,audits,queue,builds,wisdom,.msg}")
``` ```
3. TeamCreate with team name `issue` 4. TeamCreate with team name `issue`
4. Write session.json with pipeline_mode, issue_ids, execution_method, fix_cycles=0, max_fix_cycles=2 5. Write session.json with pipeline_mode, issue_ids, execution_method, fix_cycles=0, max_fix_cycles=2
5. Initialize meta.json via team_msg state_update: 6. Initialize meta.json via team_msg state_update:
``` ```
mcp__ccw-tools__team_msg({ mcp__ccw-tools__team_msg({
operation: "log", session_id: "<id>", from: "coordinator", operation: "log", session_id: "<id>", from: "coordinator",
@@ -110,18 +113,18 @@ TEXT-LEVEL ONLY. No source code reading.
data: { pipeline_mode: "<mode>", pipeline_stages: ["explorer","planner","reviewer","integrator","implementer"], team_name: "issue", issue_ids: [...], fix_cycles: 0 } data: { pipeline_mode: "<mode>", pipeline_stages: ["explorer","planner","reviewer","integrator","implementer"], team_name: "issue", issue_ids: [...], fix_cycles: 0 }
}) })
``` ```
6. Initialize wisdom files (learnings.md, decisions.md, conventions.md, issues.md) 7. Initialize wisdom files (learnings.md, decisions.md, conventions.md, issues.md)
## Phase 3: Create Task Chain ## Phase 3: Create Task Chain
Delegate to commands/dispatch.md: Delegate to @commands/dispatch.md:
1. Read pipeline mode and issue IDs from session.json 1. Read pipeline mode and issue IDs from session.json
2. Create tasks for selected pipeline with correct blockedBy 2. Create tasks for selected pipeline with correct blockedBy
3. Update session.json with task count 3. Update session.json with task count
## Phase 4: Spawn-and-Stop ## Phase 4: Spawn-and-Stop
Delegate to commands/monitor.md#handleSpawnNext: Delegate to @commands/monitor.md#handleSpawnNext:
1. Find ready tasks (pending + blockedBy resolved) 1. Find ready tasks (pending + blockedBy resolved)
2. Spawn team-worker agents (see SKILL.md Spawn Template) 2. Spawn team-worker agents (see SKILL.md Spawn Template)
3. Output status summary 3. Output status summary

6
.claude/skills/team-iterdev/SKILL.md
View File

@@ -44,7 +44,7 @@ Skill(skill="team-iterdev", args="task description")
Parse `$ARGUMENTS`: Parse `$ARGUMENTS`:
- Has `--role <name>` → Read `roles/<name>/role.md`, execute Phase 2-4 - Has `--role <name>` → Read `roles/<name>/role.md`, execute Phase 2-4
- No `--role` → Read `roles/coordinator/role.md`, execute entry router - No `--role` → `@roles/coordinator/role.md`, execute entry router
## Shared Constants ## Shared Constants
@@ -66,14 +66,14 @@ Agent({
run_in_background: true, run_in_background: true,
prompt: `## Role Assignment prompt: `## Role Assignment
role: <role> role: <role>
role_spec: ~ or <project>/.claude/skills/team-iterdev/roles/<role>/role.md role_spec: <skill_root>/roles/<role>/role.md
session: <session-folder> session: <session-folder>
session_id: <session-id> session_id: <session-id>
team_name: iterdev team_name: iterdev
requirement: <task-description> requirement: <task-description>
inner_loop: <true|false> inner_loop: <true|false>
Read role_spec file to load Phase 2-4 domain instructions. Read role_spec file (@<skill_root>/roles/<role>/role.md) to load Phase 2-4 domain instructions.
Execute built-in Phase 1 (task discovery) -> role Phase 2-4 -> built-in Phase 5 (report).` Execute built-in Phase 1 (task discovery) -> role Phase 2-4 -> built-in Phase 5 (report).`
}) })
``` ```

27
.claude/skills/team-iterdev/roles/coordinator/role.md
View File

@@ -43,7 +43,7 @@ When coordinator needs to execute a command:
| Interrupted session | Active/paused session in .workflow/.team/IDS-* | -> Phase 0 | | Interrupted session | Active/paused session in .workflow/.team/IDS-* | -> Phase 0 |
| New session | None of above | -> Phase 1 | | New session | None of above | -> Phase 1 |
For callback/check/resume/complete: load commands/monitor.md, execute handler, STOP. For callback/check/resume/complete: load @commands/monitor.md, execute handler, STOP.
## Phase 0: Session Resume Check ## Phase 0: Session Resume Check
@@ -57,7 +57,7 @@ For callback/check/resume/complete: load commands/monitor.md, execute handler, S
TEXT-LEVEL ONLY. No source code reading. TEXT-LEVEL ONLY. No source code reading.
1. Parse user task description from $ARGUMENTS 1. Parse user task description from $ARGUMENTS
2. Delegate to commands/analyze.md 2. Delegate to @commands/analyze.md
3. Assess complexity for pipeline selection: 3. Assess complexity for pipeline selection:
| Signal | Weight | | Signal | Weight |
@@ -80,17 +80,20 @@ TEXT-LEVEL ONLY. No source code reading.
## Phase 2: Session & Team Setup ## Phase 2: Session & Team Setup
1. Generate session ID: `IDS-<slug>-<YYYY-MM-DD>` 1. Resolve workspace paths (MUST do first):
2. Create session folder structure: - `project_root` = result of `Bash({ command: "pwd" })`
- `skill_root` = `<project_root>/.claude/skills/team-iterdev`
2. Generate session ID: `IDS-<slug>-<YYYY-MM-DD>`
3. Create session folder structure:
``` ```
mkdir -p .workflow/.team/<session-id>/{design,code,verify,review,wisdom} mkdir -p .workflow/.team/<session-id>/{design,code,verify,review,wisdom}
``` ```
3. Create team: `TeamCreate({ team_name: "iterdev" })` 4. Create team: `TeamCreate({ team_name: "iterdev" })`
4. Read specs/pipelines.md -> select pipeline based on complexity 5. Read specs/pipelines.md -> select pipeline based on complexity
5. Initialize wisdom directory (learnings.md, decisions.md, conventions.md, issues.md) 6. Initialize wisdom directory (learnings.md, decisions.md, conventions.md, issues.md)
6. Write session.json 7. Write session.json
7. Initialize task-ledger.json 8. Initialize task-ledger.json
8. Initialize meta.json with pipeline metadata: 9. Initialize meta.json with pipeline metadata:
```typescript ```typescript
mcp__ccw-tools__team_msg({ mcp__ccw-tools__team_msg({
operation: "log", session_id: "<id>", from: "coordinator", operation: "log", session_id: "<id>", from: "coordinator",
@@ -106,14 +109,14 @@ mcp__ccw-tools__team_msg({
## Phase 3: Task Chain Creation ## Phase 3: Task Chain Creation
Delegate to commands/dispatch.md: Delegate to @commands/dispatch.md:
1. Read specs/pipelines.md for selected pipeline task registry 1. Read specs/pipelines.md for selected pipeline task registry
2. Create tasks via TaskCreate with blockedBy 2. Create tasks via TaskCreate with blockedBy
3. Update task-ledger.json 3. Update task-ledger.json
## Phase 4: Spawn-and-Stop ## Phase 4: Spawn-and-Stop
Delegate to commands/monitor.md#handleSpawnNext: Delegate to @commands/monitor.md#handleSpawnNext:
1. Find ready tasks (pending + blockedBy resolved) 1. Find ready tasks (pending + blockedBy resolved)
2. Spawn team-worker agents (see SKILL.md Spawn Template) 2. Spawn team-worker agents (see SKILL.md Spawn Template)
3. Output status summary 3. Output status summary

10
.claude/skills/team-lifecycle-v4/SKILL.md
View File

@@ -49,7 +49,7 @@ Skill(skill="team-lifecycle-v4", args="task description")
Parse `$ARGUMENTS`: Parse `$ARGUMENTS`:
- Has `--role <name>` → Read `roles/<name>/role.md`, execute Phase 2-4 - Has `--role <name>` → Read `roles/<name>/role.md`, execute Phase 2-4
- No `--role` → Read `roles/coordinator/role.md`, execute entry router - No `--role` → `@roles/coordinator/role.md`, execute entry router
## Shared Constants ## Shared Constants
@@ -71,14 +71,14 @@ Agent({
run_in_background: true, run_in_background: true,
prompt: `## Role Assignment prompt: `## Role Assignment
role: <role> role: <role>
role_spec: ~ or <project>/.claude/skills/team-lifecycle-v4/roles/<role>/role.md role_spec: <skill_root>/roles/<role>/role.md
session: <session-folder> session: <session-folder>
session_id: <session-id> session_id: <session-id>
team_name: <team-name> team_name: <team-name>
requirement: <task-description> requirement: <task-description>
inner_loop: <true|false> inner_loop: <true|false>
Read role_spec file to load Phase 2-4 domain instructions. Read role_spec file (@<skill_root>/roles/<role>/role.md) to load Phase 2-4 domain instructions.
Execute built-in Phase 1 (task discovery) -> role Phase 2-4 -> built-in Phase 5 (report).` Execute built-in Phase 1 (task discovery) -> role Phase 2-4 -> built-in Phase 5 (report).`
}) })
``` ```
@@ -98,13 +98,13 @@ Agent({
run_in_background: true, run_in_background: true,
prompt: `## Role Assignment prompt: `## Role Assignment
role: supervisor role: supervisor
role_spec: ~ or <project>/.claude/skills/team-lifecycle-v4/roles/supervisor/role.md role_spec: <skill_root>/roles/supervisor/role.md
session: <session-folder> session: <session-folder>
session_id: <session-id> session_id: <session-id>
team_name: <team-name> team_name: <team-name>
requirement: <task-description> requirement: <task-description>
Read role_spec file to load checkpoint definitions. Read role_spec file (@<skill_root>/roles/supervisor/role.md) to load checkpoint definitions.
Init: load baseline context, report ready, go idle. Init: load baseline context, report ready, go idle.
Wake cycle: coordinator sends checkpoint requests via SendMessage.` Wake cycle: coordinator sends checkpoint requests via SendMessage.`
}) })

29
.claude/skills/team-lifecycle-v4/roles/coordinator/role.md
View File

@@ -43,7 +43,7 @@ When coordinator needs to execute a specific phase:
| Interrupted session | Active session in .workflow/.team/TLV4-* | -> Phase 0 | | Interrupted session | Active session in .workflow/.team/TLV4-* | -> Phase 0 |
| New session | None of above | -> Phase 1 | | New session | None of above | -> Phase 1 |
For callback/check/resume/adapt/complete: load commands/monitor.md, execute handler, STOP. For callback/check/resume/adapt/complete: load @commands/monitor.md, execute handler, STOP.
## Phase 0: Session Resume Check ## Phase 0: Session Resume Check
@@ -64,19 +64,22 @@ TEXT-LEVEL ONLY. No source code reading.
1. Parse task description 1. Parse task description
2. Clarify if ambiguous (AskUserQuestion: scope, deliverables, constraints) 2. Clarify if ambiguous (AskUserQuestion: scope, deliverables, constraints)
3. Delegate to commands/analyze.md 3. Delegate to @commands/analyze.md
4. Output: task-analysis.json 4. Output: task-analysis.json
5. CRITICAL: Always proceed to Phase 2, never skip team workflow 5. CRITICAL: Always proceed to Phase 2, never skip team workflow
## Phase 2: Create Team + Initialize Session ## Phase 2: Create Team + Initialize Session
1. Generate session ID: TLV4-<slug>-<date> 1. Resolve workspace paths (MUST do first):
2. Create session folder structure - `project_root` = result of `Bash({ command: "pwd" })`
3. TeamCreate with team name - `skill_root` = `<project_root>/.claude/skills/team-lifecycle-v4`
4. Read specs/pipelines.md -> select pipeline 2. Generate session ID: TLV4-<slug>-<date>
5. Register roles in team-session.json 3. Create session folder structure
6. Initialize shared infrastructure (wisdom/*.md, explorations/cache-index.json) 4. TeamCreate with team name
7. Initialize pipeline via team_msg state_update: 5. Read specs/pipelines.md -> select pipeline
6. Register roles in team-session.json
7. Initialize shared infrastructure (wisdom/*.md, explorations/cache-index.json)
8. Initialize pipeline via team_msg state_update:
``` ```
mcp__ccw-tools__team_msg({ mcp__ccw-tools__team_msg({
operation: "log", session_id: "<id>", from: "coordinator", operation: "log", session_id: "<id>", from: "coordinator",
@@ -84,15 +87,15 @@ TEXT-LEVEL ONLY. No source code reading.
data: { pipeline_mode: "<mode>", pipeline_stages: [...], team_name: "<name>" } data: { pipeline_mode: "<mode>", pipeline_stages: [...], team_name: "<name>" }
}) })
``` ```
8. Write team-session.json 9. Write team-session.json
9. Spawn resident supervisor (if pipeline has CHECKPOINT tasks AND `supervision !== false`): 10. Spawn resident supervisor (if pipeline has CHECKPOINT tasks AND `supervision !== false`):
- Use SKILL.md Supervisor Spawn Template (subagent_type: "team-supervisor") - Use SKILL.md Supervisor Spawn Template (subagent_type: "team-supervisor")
- Wait for "[supervisor] Ready" callback before proceeding to Phase 3 - Wait for "[supervisor] Ready" callback before proceeding to Phase 3
- Record supervisor in active_workers with `resident: true` flag - Record supervisor in active_workers with `resident: true` flag
## Phase 3: Create Task Chain ## Phase 3: Create Task Chain
Delegate to commands/dispatch.md: Delegate to @commands/dispatch.md:
1. Read dependency graph from task-analysis.json 1. Read dependency graph from task-analysis.json
2. Read specs/pipelines.md for selected pipeline's task registry 2. Read specs/pipelines.md for selected pipeline's task registry
3. Topological sort tasks 3. Topological sort tasks
@@ -101,7 +104,7 @@ Delegate to commands/dispatch.md:
## Phase 4: Spawn-and-Stop ## Phase 4: Spawn-and-Stop
Delegate to commands/monitor.md#handleSpawnNext: Delegate to @commands/monitor.md#handleSpawnNext:
1. Find ready tasks (pending + blockedBy resolved) 1. Find ready tasks (pending + blockedBy resolved)
2. Spawn team-worker agents (see SKILL.md Spawn Template) 2. Spawn team-worker agents (see SKILL.md Spawn Template)
3. Output status summary 3. Output status summary

6
.claude/skills/team-perf-opt/SKILL.md
View File

@@ -55,7 +55,7 @@ Pipeline (Independent mode):
Parse `$ARGUMENTS`: Parse `$ARGUMENTS`:
- Has `--role <name>` → Read `roles/<name>/role.md`, execute Phase 2-4 - Has `--role <name>` → Read `roles/<name>/role.md`, execute Phase 2-4
- No `--role` → Read `roles/coordinator/role.md`, execute entry router - No `--role` → `@roles/coordinator/role.md`, execute entry router
## Shared Constants ## Shared Constants
@@ -78,14 +78,14 @@ Agent({
run_in_background: true, run_in_background: true,
prompt: `## Role Assignment prompt: `## Role Assignment
role: <role> role: <role>
role_spec: ~ or <project>/.claude/skills/team-perf-opt/roles/<role>/role.md role_spec: <skill_root>/roles/<role>/role.md
session: <session-folder> session: <session-folder>
session_id: <session-id> session_id: <session-id>
team_name: perf-opt team_name: perf-opt
requirement: <task-description> requirement: <task-description>
inner_loop: <true|false> inner_loop: <true|false>
Read role_spec file to load Phase 2-4 domain instructions. Read role_spec file (@<skill_root>/roles/<role>/role.md) to load Phase 2-4 domain instructions.
Execute built-in Phase 1 (task discovery) -> role Phase 2-4 -> built-in Phase 5 (report).` Execute built-in Phase 1 (task discovery) -> role Phase 2-4 -> built-in Phase 5 (report).`
}) })
``` ```

19
.claude/skills/team-perf-opt/roles/coordinator/role.md
View File

@@ -54,7 +54,7 @@ When coordinator is invoked, detect invocation type:
| Interrupted session | Active/paused session exists | -> Phase 0 | | Interrupted session | Active/paused session exists | -> Phase 0 |
| New session | None of above | -> Phase 1 | | New session | None of above | -> Phase 1 |
For callback/check/resume/complete: load `commands/monitor.md` and execute matched handler, then STOP. For callback/check/resume/complete: load `@commands/monitor.md` and execute matched handler, then STOP.
### Router Implementation ### Router Implementation
@@ -94,16 +94,19 @@ Triggered when an active/paused session is detected on coordinator entry.
## Phase 2: Session & Team Setup ## Phase 2: Session & Team Setup
1. Create session directory with artifacts/, explorations/, wisdom/, discussions/ subdirs 1. Resolve workspace paths (MUST do first):
2. Write session.json with extended fields (parallel_mode, max_branches, branches, fix_cycles) - `project_root` = result of `Bash({ command: "pwd" })`
3. Initialize meta.json with pipeline metadata via team_msg - `skill_root` = `<project_root>/.claude/skills/team-perf-opt`
4. Call `TeamCreate({ team_name: "perf-opt" })` 2. Create session directory with artifacts/, explorations/, wisdom/, discussions/ subdirs
3. Write session.json with extended fields (parallel_mode, max_branches, branches, fix_cycles)
4. Initialize meta.json with pipeline metadata via team_msg
5. Call `TeamCreate({ team_name: "perf-opt" })`
--- ---
## Phase 3: Create Task Chain ## Phase 3: Create Task Chain
Execute `commands/dispatch.md` inline (Command Execution Protocol). Execute `@commands/dispatch.md` inline (Command Execution Protocol).
--- ---
@@ -112,14 +115,14 @@ Execute `commands/dispatch.md` inline (Command Execution Protocol).
### Initial Spawn ### Initial Spawn
Find first unblocked task and spawn its worker using SKILL.md Worker Spawn Template with: Find first unblocked task and spawn its worker using SKILL.md Worker Spawn Template with:
- `role_spec: ~ or <project>/.claude/skills/team-perf-opt/roles/<role>/role.md` - `role_spec: <skill_root>/roles/<role>/role.md`
- `team_name: perf-opt` - `team_name: perf-opt`
**STOP** after spawning. Wait for worker callback. **STOP** after spawning. Wait for worker callback.
### Coordination (via monitor.md handlers) ### Coordination (via monitor.md handlers)
All subsequent coordination handled by `commands/monitor.md`. All subsequent coordination handled by `@commands/monitor.md`.
--- ---

6
.claude/skills/team-planex/SKILL.md
View File

@@ -43,7 +43,7 @@ Skill(skill="team-planex", args="task description")
Parse `$ARGUMENTS`: Parse `$ARGUMENTS`:
- Has `--role <name>` → Read `roles/<name>/role.md`, execute Phase 2-4 - Has `--role <name>` → Read `roles/<name>/role.md`, execute Phase 2-4
- No `--role` → Read `roles/coordinator/role.md`, execute entry router - No `--role` → `@roles/coordinator/role.md`, execute entry router
## Shared Constants ## Shared Constants
@@ -65,7 +65,7 @@ Agent({
run_in_background: true, run_in_background: true,
prompt: `## Role Assignment prompt: `## Role Assignment
role: <role> role: <role>
role_spec: ~ or <project>/.claude/skills/team-planex/roles/<role>/role.md role_spec: <skill_root>/roles/<role>/role.md
session: <session-folder> session: <session-folder>
session_id: <session-id> session_id: <session-id>
team_name: planex team_name: planex
@@ -73,7 +73,7 @@ requirement: <task-description>
inner_loop: <true|false> inner_loop: <true|false>
execution_method: <codex|gemini> execution_method: <codex|gemini>
Read role_spec file to load Phase 2-4 domain instructions. Read role_spec file (@<skill_root>/roles/<role>/role.md) to load Phase 2-4 domain instructions.
Execute built-in Phase 1 (task discovery) -> role Phase 2-4 -> built-in Phase 5 (report).` Execute built-in Phase 1 (task discovery) -> role Phase 2-4 -> built-in Phase 5 (report).`
}) })
``` ```

23
.claude/skills/team-planex/roles/coordinator/role.md
View File

@@ -40,7 +40,7 @@ When coordinator needs to execute a command:
| Interrupted session | Active/paused session exists in `.workflow/.team/PEX-*` | -> Phase 0 | | Interrupted session | Active/paused session exists in `.workflow/.team/PEX-*` | -> Phase 0 |
| New session | None of above | -> Phase 1 | | New session | None of above | -> Phase 1 |
For callback/check/resume: load `commands/monitor.md` and execute the appropriate handler, then STOP. For callback/check/resume: load `@commands/monitor.md` and execute the appropriate handler, then STOP.
### handleAdd ### handleAdd
@@ -67,7 +67,7 @@ For callback/check/resume: load `commands/monitor.md` and execute the appropriat
TEXT-LEVEL ONLY. No source code reading. TEXT-LEVEL ONLY. No source code reading.
1. Delegate to commands/analyze.md -> produces task-analysis.json 1. Delegate to @commands/analyze.md -> produces task-analysis.json
2. Parse arguments: Extract input type (Issue IDs / --text / --plan) and optional flags (--exec, -y) 2. Parse arguments: Extract input type (Issue IDs / --text / --plan) and optional flags (--exec, -y)
3. Determine execution method (see specs/pipelines.md Selection Decision Table): 3. Determine execution method (see specs/pipelines.md Selection Decision Table):
- Explicit `--exec` flag -> use specified method - Explicit `--exec` flag -> use specified method
@@ -78,12 +78,15 @@ TEXT-LEVEL ONLY. No source code reading.
## Phase 2: Create Team + Initialize Session ## Phase 2: Create Team + Initialize Session
1. Generate session ID: `PEX-<slug>-<date>` 1. Resolve workspace paths (MUST do first):
2. Create session folder: `.workflow/.team/<session-id>/` - `project_root` = result of `Bash({ command: "pwd" })`
3. Create subdirectories: `artifacts/solutions/`, `wisdom/` - `skill_root` = `<project_root>/.claude/skills/team-planex`
4. Call `TeamCreate` with team name (default: "planex") 2. Generate session ID: `PEX-<slug>-<date>`
5. Initialize wisdom files (learnings.md, decisions.md, conventions.md, issues.md) 3. Create session folder: `.workflow/.team/<session-id>/`
6. Initialize meta.json with pipeline metadata: 4. Create subdirectories: `artifacts/solutions/`, `wisdom/`
5. Call `TeamCreate` with team name (default: "planex")
6. Initialize wisdom files (learnings.md, decisions.md, conventions.md, issues.md)
7. Initialize meta.json with pipeline metadata:
```typescript ```typescript
mcp__ccw-tools__team_msg({ mcp__ccw-tools__team_msg({
operation: "log", session_id: "<id>", from: "coordinator", operation: "log", session_id: "<id>", from: "coordinator",
@@ -101,14 +104,14 @@ mcp__ccw-tools__team_msg({
## Phase 3: Create Task Chain ## Phase 3: Create Task Chain
Delegate to `commands/dispatch.md`: Delegate to `@commands/dispatch.md`:
1. Read `roles/coordinator/commands/dispatch.md` 1. Read `roles/coordinator/commands/dispatch.md`
2. Execute its workflow to create PLAN-001 task 2. Execute its workflow to create PLAN-001 task
3. PLAN-001 contains input info + execution method in description 3. PLAN-001 contains input info + execution method in description
## Phase 4: Spawn-and-Stop ## Phase 4: Spawn-and-Stop
1. Load `commands/monitor.md` 1. Load `@commands/monitor.md`
2. Execute `handleSpawnNext` to find ready tasks and spawn planner worker 2. Execute `handleSpawnNext` to find ready tasks and spawn planner worker
3. Output status summary 3. Output status summary
4. STOP (idle, wait for worker callback) 4. STOP (idle, wait for worker callback)

6
.claude/skills/team-quality-assurance/SKILL.md
View File

@@ -45,7 +45,7 @@ Skill(skill="team-quality-assurance", args="task description")
Parse `$ARGUMENTS`: Parse `$ARGUMENTS`:
- Has `--role <name>` -> Read `roles/<name>/role.md`, execute Phase 2-4 - Has `--role <name>` -> Read `roles/<name>/role.md`, execute Phase 2-4
- No `--role` -> Read `roles/coordinator/role.md`, execute entry router - No `--role` -> `@roles/coordinator/role.md`, execute entry router
## Shared Constants ## Shared Constants
@@ -68,14 +68,14 @@ Agent({
run_in_background: true, run_in_background: true,
prompt: `## Role Assignment prompt: `## Role Assignment
role: <role> role: <role>
role_spec: ~ or <project>/.claude/skills/team-quality-assurance/roles/<role>/role.md role_spec: <skill_root>/roles/<role>/role.md
session: <session-folder> session: <session-folder>
session_id: <session-id> session_id: <session-id>
team_name: quality-assurance team_name: quality-assurance
requirement: <task-description> requirement: <task-description>
inner_loop: <true|false> inner_loop: <true|false>
Read role_spec file to load Phase 2-4 domain instructions. Read role_spec file (@<skill_root>/roles/<role>/role.md) to load Phase 2-4 domain instructions.
Execute built-in Phase 1 (task discovery) -> role Phase 2-4 -> built-in Phase 5 (report).` Execute built-in Phase 1 (task discovery) -> role Phase 2-4 -> built-in Phase 5 (report).`
}) })
``` ```

27
.claude/skills/team-quality-assurance/roles/coordinator/role.md
View File

@@ -43,7 +43,7 @@ When coordinator needs to execute a specific phase:
| Interrupted session | Active session in .workflow/.team/QA-* | -> Phase 0 | | Interrupted session | Active session in .workflow/.team/QA-* | -> Phase 0 |
| New session | None of above | -> Phase 1 | | New session | None of above | -> Phase 1 |
For callback/check/resume/adapt/complete: load commands/monitor.md, execute handler, STOP. For callback/check/resume/adapt/complete: load @commands/monitor.md, execute handler, STOP.
## Phase 0: Session Resume Check ## Phase 0: Session Resume Check
@@ -69,19 +69,22 @@ TEXT-LEVEL ONLY. No source code reading.
| No explicit flag and no keyword match | full (default) | | No explicit flag and no keyword match | full (default) |
3. Clarify if ambiguous (AskUserQuestion: scope, deliverables, constraints) 3. Clarify if ambiguous (AskUserQuestion: scope, deliverables, constraints)
4. Delegate to commands/analyze.md 4. Delegate to @commands/analyze.md
5. Output: task-analysis.json 5. Output: task-analysis.json
6. CRITICAL: Always proceed to Phase 2, never skip team workflow 6. CRITICAL: Always proceed to Phase 2, never skip team workflow
## Phase 2: Create Team + Initialize Session ## Phase 2: Create Team + Initialize Session
1. Generate session ID: QA-<slug>-<date> 1. Resolve workspace paths (MUST do first):
2. Create session folder structure - `project_root` = result of `Bash({ command: "pwd" })`
3. TeamCreate with team name "quality-assurance" - `skill_root` = `<project_root>/.claude/skills/team-quality-assurance`
4. Read specs/pipelines.md -> select pipeline based on mode 2. Generate session ID: QA-<slug>-<date>
5. Register roles in session.json 3. Create session folder structure
6. Initialize shared infrastructure (wisdom/*.md) 4. TeamCreate with team name "quality-assurance"
7. Initialize pipeline via team_msg state_update: 5. Read specs/pipelines.md -> select pipeline based on mode
6. Register roles in session.json
7. Initialize shared infrastructure (wisdom/*.md)
8. Initialize pipeline via team_msg state_update:
``` ```
mcp__ccw-tools__team_msg({ mcp__ccw-tools__team_msg({
operation: "log", session_id: "<id>", from: "coordinator", operation: "log", session_id: "<id>", from: "coordinator",
@@ -100,11 +103,11 @@ TEXT-LEVEL ONLY. No source code reading.
} }
}) })
``` ```
8. Write session.json 9. Write session.json
## Phase 3: Create Task Chain ## Phase 3: Create Task Chain
Delegate to commands/dispatch.md: Delegate to @commands/dispatch.md:
1. Read dependency graph from task-analysis.json 1. Read dependency graph from task-analysis.json
2. Read specs/pipelines.md for selected pipeline's task registry 2. Read specs/pipelines.md for selected pipeline's task registry
3. Topological sort tasks 3. Topological sort tasks
@@ -113,7 +116,7 @@ Delegate to commands/dispatch.md:
## Phase 4: Spawn-and-Stop ## Phase 4: Spawn-and-Stop
Delegate to commands/monitor.md#handleSpawnNext: Delegate to @commands/monitor.md#handleSpawnNext:
1. Find ready tasks (pending + blockedBy resolved) 1. Find ready tasks (pending + blockedBy resolved)
2. Spawn team-worker agents (see SKILL.md Spawn Template) 2. Spawn team-worker agents (see SKILL.md Spawn Template)
3. Output status summary 3. Output status summary

6
.claude/skills/team-review/SKILL.md
View File

@@ -43,7 +43,7 @@ Skill(skill="team-review", args="task description")
Parse `$ARGUMENTS`: Parse `$ARGUMENTS`:
- Has `--role <name>` -> Read `roles/<name>/role.md`, execute Phase 2-4 - Has `--role <name>` -> Read `roles/<name>/role.md`, execute Phase 2-4
- No `--role` -> Read `roles/coordinator/role.md`, execute entry router - No `--role` -> `@roles/coordinator/role.md`, execute entry router
## Shared Constants ## Shared Constants
@@ -66,14 +66,14 @@ Agent({
run_in_background: true, run_in_background: true,
prompt: `## Role Assignment prompt: `## Role Assignment
role: <role> role: <role>
role_spec: ~ or <project>/.claude/skills/team-review/roles/<role>/role.md role_spec: <skill_root>/roles/<role>/role.md
session: <session-folder> session: <session-folder>
session_id: <session-id> session_id: <session-id>
team_name: review team_name: review
requirement: <task-description> requirement: <task-description>
inner_loop: <true|false> inner_loop: <true|false>
Read role_spec file to load Phase 2-4 domain instructions. Read role_spec file (@<skill_root>/roles/<role>/role.md) to load Phase 2-4 domain instructions.
Execute built-in Phase 1 (task discovery) -> role Phase 2-4 -> built-in Phase 5 (report).` Execute built-in Phase 1 (task discovery) -> role Phase 2-4 -> built-in Phase 5 (report).`
}) })
``` ```

23
.claude/skills/team-review/roles/coordinator/role.md
View File

@@ -43,7 +43,7 @@ When coordinator needs to execute a specific phase:
| Interrupted session | Active session in .workflow/.team/RV-* | -> Phase 0 | | Interrupted session | Active session in .workflow/.team/RV-* | -> Phase 0 |
| New session | None of above | -> Phase 1 | | New session | None of above | -> Phase 1 |
For callback/check/resume/adapt/complete: load commands/monitor.md, execute handler, STOP. For callback/check/resume/adapt/complete: load @commands/monitor.md, execute handler, STOP.
## Phase 0: Session Resume Check ## Phase 0: Session Resume Check
@@ -67,17 +67,20 @@ TEXT-LEVEL ONLY. No source code reading.
2. Extract parameters: target, dimensions, auto-confirm flag 2. Extract parameters: target, dimensions, auto-confirm flag
3. Clarify if ambiguous (AskUserQuestion for target path) 3. Clarify if ambiguous (AskUserQuestion for target path)
4. Delegate to commands/analyze.md 4. Delegate to @commands/analyze.md
5. Output: task-analysis.json 5. Output: task-analysis.json
6. CRITICAL: Always proceed to Phase 2, never skip team workflow 6. CRITICAL: Always proceed to Phase 2, never skip team workflow
## Phase 2: Create Team + Initialize Session ## Phase 2: Create Team + Initialize Session
1. Generate session ID: RV-<slug>-<date> 1. Resolve workspace paths (MUST do first):
2. Create session folder structure (scan/, review/, fix/, wisdom/) - `project_root` = result of `Bash({ command: "pwd" })`
3. TeamCreate with team name "review" - `skill_root` = `<project_root>/.claude/skills/team-review`
4. Read specs/pipelines.md -> select pipeline based on mode 2. Generate session ID: RV-<slug>-<date>
5. Initialize pipeline via team_msg state_update: 3. Create session folder structure (scan/, review/, fix/, wisdom/)
4. TeamCreate with team name "review"
5. Read specs/pipelines.md -> select pipeline based on mode
6. Initialize pipeline via team_msg state_update:
``` ```
mcp__ccw-tools__team_msg({ mcp__ccw-tools__team_msg({
operation: "log", session_id: "<id>", from: "coordinator", operation: "log", session_id: "<id>", from: "coordinator",
@@ -92,18 +95,18 @@ TEXT-LEVEL ONLY. No source code reading.
} }
}) })
``` ```
6. Write session meta.json 7. Write session meta.json
## Phase 3: Create Task Chain ## Phase 3: Create Task Chain
Delegate to commands/dispatch.md: Delegate to @commands/dispatch.md:
1. Read specs/pipelines.md for selected pipeline's task registry 1. Read specs/pipelines.md for selected pipeline's task registry
2. Create tasks via TaskCreate with blockedBy 2. Create tasks via TaskCreate with blockedBy
3. Update session meta.json with pipeline.tasks_total 3. Update session meta.json with pipeline.tasks_total
## Phase 4: Spawn-and-Stop ## Phase 4: Spawn-and-Stop
Delegate to commands/monitor.md#handleSpawnNext: Delegate to @commands/monitor.md#handleSpawnNext:
1. Find ready tasks (pending + blockedBy resolved) 1. Find ready tasks (pending + blockedBy resolved)
2. Spawn team-worker agents (see SKILL.md Spawn Template) 2. Spawn team-worker agents (see SKILL.md Spawn Template)
3. Output status summary 3. Output status summary

6
.claude/skills/team-roadmap-dev/SKILL.md
View File

@@ -49,7 +49,7 @@ Multi-phase:
Parse `$ARGUMENTS`: Parse `$ARGUMENTS`:
- Has `--role <name>` → Read `roles/<name>/role.md`, execute Phase 2-4 - Has `--role <name>` → Read `roles/<name>/role.md`, execute Phase 2-4
- No `--role` → Read `roles/coordinator/role.md`, execute entry router - No `--role` → `@roles/coordinator/role.md`, execute entry router
## Shared Constants ## Shared Constants
@@ -72,14 +72,14 @@ Agent({
run_in_background: true, run_in_background: true,
prompt: `## Role Assignment prompt: `## Role Assignment
role: <role> role: <role>
role_spec: ~ or <project>/.claude/skills/team-roadmap-dev/roles/<role>/role.md role_spec: <skill_root>/roles/<role>/role.md
session: <session-folder> session: <session-folder>
session_id: <session-id> session_id: <session-id>
team_name: roadmap-dev team_name: roadmap-dev
requirement: <task-description> requirement: <task-description>
inner_loop: true inner_loop: true
Read role_spec file to load Phase 2-4 domain instructions. Read role_spec file (@<skill_root>/roles/<role>/role.md) to load Phase 2-4 domain instructions.
Execute built-in Phase 1 (task discovery) -> role Phase 2-4 -> built-in Phase 5 (report).` Execute built-in Phase 1 (task discovery) -> role Phase 2-4 -> built-in Phase 5 (report).`
}) })
``` ```

24
.claude/skills/team-roadmap-dev/roles/coordinator/role.md
View File

@@ -65,14 +65,14 @@ When coordinator is invoked, detect invocation type:
| Detection | Condition | Handler | | Detection | Condition | Handler |
|-----------|-----------|---------| |-----------|-----------|---------|
| Worker callback | Message contains role tag [planner], [executor], [verifier] | -> handleCallback | | Worker callback | Message contains role tag [planner], [executor], [verifier] | -> handleCallback |
| Resume mode | Arguments contain `--resume` | -> commands/resume.md: load session, re-enter monitor | | Resume mode | Arguments contain `--resume` | -> @commands/resume.md: load session, re-enter monitor |
| Status check | Arguments contain "check" or "status" | -> handleCheck | | Status check | Arguments contain "check" or "status" | -> handleCheck |
| Manual resume | Arguments contain "resume" or "continue" | -> handleResume | | Manual resume | Arguments contain "resume" or "continue" | -> handleResume |
| Pipeline complete | All tasks have status "completed" | -> handleComplete | | Pipeline complete | All tasks have status "completed" | -> handleComplete |
| Interrupted session | Active/paused session exists | -> Phase 0 (Session Resume Check) | | Interrupted session | Active/paused session exists | -> Phase 0 (Session Resume Check) |
| New session | None of above | -> Phase 1 (Init Prerequisites) | | New session | None of above | -> Phase 1 (Init Prerequisites) |
For callback/check/resume/complete: load `commands/monitor.md` and execute matched handler, then STOP. For callback/check/resume/complete: load `@commands/monitor.md` and execute matched handler, then STOP.
### Router Implementation ### Router Implementation
@@ -86,7 +86,7 @@ For callback/check/resume/complete: load `commands/monitor.md` and execute match
3. **Route to handler**: 3. **Route to handler**:
- For monitor handlers: Read `commands/monitor.md`, execute matched handler, STOP - For monitor handlers: Read `commands/monitor.md`, execute matched handler, STOP
- For --resume: Read `commands/resume.md`, execute resume flow - For --resume: Read `@commands/resume.md`, execute resume flow
- For Phase 0: Execute Session Resume Check - For Phase 0: Execute Session Resume Check
- For Phase 1: Execute Init Prerequisites below - For Phase 1: Execute Init Prerequisites below
@@ -160,7 +160,7 @@ Bash("ccw team log --session-id <session-id> --from coordinator --type <type> --
**Workflow**: **Workflow**:
1. Parse arguments for flags: `--resume`, `--yes`, task description 1. Parse arguments for flags: `--resume`, `--yes`, task description
2. If `--resume` present -> load commands/resume.md and execute resume flow 2. If `--resume` present -> load @commands/resume.md and execute resume flow
3. Ensure project-tech.json exists: 3. Ensure project-tech.json exists:
| Condition | Action | | Condition | Action |
@@ -178,7 +178,7 @@ Bash("ccw team log --session-id <session-id> --from coordinator --type <type> --
**Objective**: Discuss roadmap with user and generate phase plan. **Objective**: Discuss roadmap with user and generate phase plan.
Delegate to `commands/roadmap-discuss.md`: Delegate to `@commands/roadmap-discuss.md`:
| Step | Action | | Step | Action |
|------|--------| |------|--------|
@@ -198,9 +198,13 @@ Delegate to `commands/roadmap-discuss.md`:
**Workflow**: **Workflow**:
1. Call `TeamCreate({ team_name: "roadmap-dev" })` 1. Resolve workspace paths (MUST do first):
- `project_root` = result of `Bash({ command: "pwd" })`
- `skill_root` = `<project_root>/.claude/skills/team-roadmap-dev`
2. Initialize meta.json with pipeline metadata: 2. Call `TeamCreate({ team_name: "roadmap-dev" })`
3. Initialize meta.json with pipeline metadata:
```typescript ```typescript
// Use team_msg to write pipeline metadata to .msg/meta.json // Use team_msg to write pipeline metadata to .msg/meta.json
mcp__ccw-tools__team_msg({ mcp__ccw-tools__team_msg({
@@ -218,8 +222,8 @@ mcp__ccw-tools__team_msg({
}) })
``` ```
3. Spawn worker roles (see SKILL.md Coordinator Spawn Template) 4. Spawn worker roles (see SKILL.md Coordinator Spawn Template)
4. Load `commands/dispatch.md` for task chain creation 5. Load `@commands/dispatch.md` for task chain creation
| Step | Action | | Step | Action |
|------|--------| |------|--------|
@@ -242,7 +246,7 @@ mcp__ccw-tools__team_msg({
- User can use "check" / "resume" to manually advance - User can use "check" / "resume" to manually advance
- Coordinator does one operation per invocation, then STOPS - Coordinator does one operation per invocation, then STOPS
Delegate to `commands/monitor.md`: Delegate to `@commands/monitor.md`:
| Step | Action | | Step | Action |
|------|--------| |------|--------|

6
.claude/skills/team-tech-debt/SKILL.md
View File

@@ -45,7 +45,7 @@ Skill(skill="team-tech-debt", args="task description")
Parse `$ARGUMENTS`: Parse `$ARGUMENTS`:
- Has `--role <name>` → Read `roles/<name>/role.md`, execute Phase 2-4 - Has `--role <name>` → Read `roles/<name>/role.md`, execute Phase 2-4
- No `--role` → Read `roles/coordinator/role.md`, execute entry router - No `--role` → `@roles/coordinator/role.md`, execute entry router
## Shared Constants ## Shared Constants
@@ -68,14 +68,14 @@ Agent({
run_in_background: true, run_in_background: true,
prompt: `## Role Assignment prompt: `## Role Assignment
role: <role> role: <role>
role_spec: ~ or <project>/.claude/skills/team-tech-debt/roles/<role>/role.md role_spec: <skill_root>/roles/<role>/role.md
session: <session-folder> session: <session-folder>
session_id: <session-id> session_id: <session-id>
team_name: tech-debt team_name: tech-debt
requirement: <task-description> requirement: <task-description>
inner_loop: <true|false> inner_loop: <true|false>
Read role_spec file to load Phase 2-4 domain instructions. Read role_spec file (@<skill_root>/roles/<role>/role.md) to load Phase 2-4 domain instructions.
Execute built-in Phase 1 (task discovery) -> role Phase 2-4 -> built-in Phase 5 (report).` Execute built-in Phase 1 (task discovery) -> role Phase 2-4 -> built-in Phase 5 (report).`
}) })
``` ```

21
.claude/skills/team-tech-debt/roles/coordinator/role.md
View File

@@ -44,7 +44,7 @@ When coordinator needs to execute a command (analyze, dispatch, monitor):
| Interrupted session | Active/paused session exists in .workflow/.team/TD-* | -> Phase 0 | | Interrupted session | Active/paused session exists in .workflow/.team/TD-* | -> Phase 0 |
| New session | None of above | -> Phase 1 | | New session | None of above | -> Phase 1 |
For callback/check/resume/complete: load `commands/monitor.md`, execute matched handler, STOP. For callback/check/resume/complete: load `@commands/monitor.md`, execute matched handler, STOP.
## Phase 0: Session Resume Check ## Phase 0: Session Resume Check
@@ -70,19 +70,22 @@ TEXT-LEVEL ONLY. No source code reading.
3. Ask for missing parameters (skip if auto mode): 3. Ask for missing parameters (skip if auto mode):
- AskUserQuestion: Tech Debt Target (自定义 / 全项目扫描 / 完整治理 / 定向修复) - AskUserQuestion: Tech Debt Target (自定义 / 全项目扫描 / 完整治理 / 定向修复)
4. Store: mode, scope, focus, constraints 4. Store: mode, scope, focus, constraints
5. Delegate to commands/analyze.md -> output task-analysis context 5. Delegate to @commands/analyze.md -> output task-analysis context
## Phase 2: Create Team + Initialize Session ## Phase 2: Create Team + Initialize Session
1. Generate session ID: `TD-<slug>-<YYYY-MM-DD>` 1. Resolve workspace paths (MUST do first):
2. Create session folder structure (scan/, assessment/, plan/, fixes/, validation/, wisdom/) - `project_root` = result of `Bash({ command: "pwd" })`
3. Initialize .msg/meta.json via team_msg state_update with pipeline metadata - `skill_root` = `<project_root>/.claude/skills/team-tech-debt`
4. TeamCreate(team_name="tech-debt") 2. Generate session ID: `TD-<slug>-<YYYY-MM-DD>`
5. Do NOT spawn workers yet - deferred to Phase 4 3. Create session folder structure (scan/, assessment/, plan/, fixes/, validation/, wisdom/)
4. Initialize .msg/meta.json via team_msg state_update with pipeline metadata
5. TeamCreate(team_name="tech-debt")
6. Do NOT spawn workers yet - deferred to Phase 4
## Phase 3: Create Task Chain ## Phase 3: Create Task Chain
Delegate to commands/dispatch.md. Task chain by mode: Delegate to @commands/dispatch.md. Task chain by mode:
| Mode | Task Chain | | Mode | Task Chain |
|------|------------| |------|------------|
@@ -92,7 +95,7 @@ Delegate to commands/dispatch.md. Task chain by mode:
## Phase 4: Spawn-and-Stop ## Phase 4: Spawn-and-Stop
Delegate to commands/monitor.md#handleSpawnNext: Delegate to @commands/monitor.md#handleSpawnNext:
1. Find ready tasks (pending + blockedBy resolved) 1. Find ready tasks (pending + blockedBy resolved)
2. Spawn team-worker agents (see SKILL.md Spawn Template) 2. Spawn team-worker agents (see SKILL.md Spawn Template)
3. Output status summary 3. Output status summary

6
.claude/skills/team-testing/SKILL.md
View File

@@ -44,7 +44,7 @@ Skill(skill="team-testing", args="task description")
Parse `$ARGUMENTS`: Parse `$ARGUMENTS`:
- Has `--role <name>` -> Read `roles/<name>/role.md`, execute Phase 2-4 - Has `--role <name>` -> Read `roles/<name>/role.md`, execute Phase 2-4
- No `--role` -> Read `roles/coordinator/role.md`, execute entry router - No `--role` -> `@roles/coordinator/role.md`, execute entry router
## Shared Constants ## Shared Constants
@@ -67,14 +67,14 @@ Agent({
run_in_background: true, run_in_background: true,
prompt: `## Role Assignment prompt: `## Role Assignment
role: <role> role: <role>
role_spec: ~ or <project>/.claude/skills/team-testing/roles/<role>/role.md role_spec: <skill_root>/roles/<role>/role.md
session: <session-folder> session: <session-folder>
session_id: <session-id> session_id: <session-id>
team_name: testing team_name: testing
requirement: <task-description> requirement: <task-description>
inner_loop: <true|false> inner_loop: <true|false>
Read role_spec file to load Phase 2-4 domain instructions. Read role_spec file (@<skill_root>/roles/<role>/role.md) to load Phase 2-4 domain instructions.
Execute built-in Phase 1 (task discovery) -> role Phase 2-4 -> built-in Phase 5 (report).` Execute built-in Phase 1 (task discovery) -> role Phase 2-4 -> built-in Phase 5 (report).`
}) })
``` ```

23
.claude/skills/team-testing/roles/coordinator/role.md
View File

@@ -42,7 +42,7 @@ When coordinator needs to execute a specific phase:
| Interrupted session | Active session in .workflow/.team/TST-* | -> Phase 0 | | Interrupted session | Active session in .workflow/.team/TST-* | -> Phase 0 |
| New session | None of above | -> Phase 1 | | New session | None of above | -> Phase 1 |
For callback/check/resume/adapt/complete: load commands/monitor.md, execute handler, STOP. For callback/check/resume/adapt/complete: load @commands/monitor.md, execute handler, STOP.
## Phase 0: Session Resume Check ## Phase 0: Session Resume Check
@@ -69,17 +69,20 @@ TEXT-LEVEL ONLY. No source code reading.
| Otherwise | comprehensive | | Otherwise | comprehensive |
4. Clarify if ambiguous (AskUserQuestion for scope) 4. Clarify if ambiguous (AskUserQuestion for scope)
5. Delegate to commands/analyze.md 5. Delegate to @commands/analyze.md
6. Output: task-analysis.json 6. Output: task-analysis.json
7. CRITICAL: Always proceed to Phase 2, never skip team workflow 7. CRITICAL: Always proceed to Phase 2, never skip team workflow
## Phase 2: Create Team + Initialize Session ## Phase 2: Create Team + Initialize Session
1. Generate session ID: TST-<slug>-<date> 1. Resolve workspace paths (MUST do first):
2. Create session folder structure (strategy/, tests/L1-unit/, tests/L2-integration/, tests/L3-e2e/, results/, analysis/, wisdom/) - `project_root` = result of `Bash({ command: "pwd" })`
3. TeamCreate with team name "testing" - `skill_root` = `<project_root>/.claude/skills/team-testing`
4. Read specs/pipelines.md -> select pipeline based on mode 2. Generate session ID: TST-<slug>-<date>
5. Initialize pipeline via team_msg state_update: 3. Create session folder structure (strategy/, tests/L1-unit/, tests/L2-integration/, tests/L3-e2e/, results/, analysis/, wisdom/)
4. TeamCreate with team name "testing"
5. Read specs/pipelines.md -> select pipeline based on mode
6. Initialize pipeline via team_msg state_update:
``` ```
mcp__ccw-tools__team_msg({ mcp__ccw-tools__team_msg({
operation: "log", session_id: "<id>", from: "coordinator", operation: "log", session_id: "<id>", from: "coordinator",
@@ -93,11 +96,11 @@ TEXT-LEVEL ONLY. No source code reading.
} }
}) })
``` ```
6. Write session.json 7. Write session.json
## Phase 3: Create Task Chain ## Phase 3: Create Task Chain
Delegate to commands/dispatch.md: Delegate to @commands/dispatch.md:
1. Read specs/pipelines.md for selected pipeline's task registry 1. Read specs/pipelines.md for selected pipeline's task registry
2. Topological sort tasks 2. Topological sort tasks
3. Create tasks via TaskCreate with blockedBy 3. Create tasks via TaskCreate with blockedBy
@@ -105,7 +108,7 @@ Delegate to commands/dispatch.md:
## Phase 4: Spawn-and-Stop ## Phase 4: Spawn-and-Stop
Delegate to commands/monitor.md#handleSpawnNext: Delegate to @commands/monitor.md#handleSpawnNext:
1. Find ready tasks (pending + blockedBy resolved) 1. Find ready tasks (pending + blockedBy resolved)
2. Spawn team-worker agents (see SKILL.md Spawn Template) 2. Spawn team-worker agents (see SKILL.md Spawn Template)
3. Output status summary 3. Output status summary

6
.claude/skills/team-uidesign/SKILL.md
View File

@@ -44,7 +44,7 @@ Skill(skill="team-uidesign", args="task description")
Parse `$ARGUMENTS`: Parse `$ARGUMENTS`:
- Has `--role <name>` → Read `roles/<name>/role.md`, execute Phase 2-4 - Has `--role <name>` → Read `roles/<name>/role.md`, execute Phase 2-4
- No `--role` → Read `roles/coordinator/role.md`, execute entry router - No `--role` → `@roles/coordinator/role.md`, execute entry router
## Shared Constants ## Shared Constants
@@ -67,14 +67,14 @@ Agent({
run_in_background: true, run_in_background: true,
prompt: `## Role Assignment prompt: `## Role Assignment
role: <role> role: <role>
role_spec: ~ or <project>/.claude/skills/team-uidesign/roles/<role>/role.md role_spec: <skill_root>/roles/<role>/role.md
session: <session-folder> session: <session-folder>
session_id: <session-id> session_id: <session-id>
team_name: uidesign team_name: uidesign
requirement: <task-description> requirement: <task-description>
inner_loop: false inner_loop: false
Read role_spec file to load Phase 2-4 domain instructions. Read role_spec file (@<skill_root>/roles/<role>/role.md) to load Phase 2-4 domain instructions.
Execute built-in Phase 1 (task discovery) -> role Phase 2-4 -> built-in Phase 5 (report).` Execute built-in Phase 1 (task discovery) -> role Phase 2-4 -> built-in Phase 5 (report).`
}) })
``` ```

21
.claude/skills/team-uidesign/roles/coordinator/role.md
View File

@@ -45,7 +45,7 @@ When coordinator needs to execute a command (analyze, dispatch, monitor):
| Interrupted session | Active/paused session exists in .workflow/.team/UDS-* | -> Phase 0 | | Interrupted session | Active/paused session exists in .workflow/.team/UDS-* | -> Phase 0 |
| New session | None of above | -> Phase 1 | | New session | None of above | -> Phase 1 |
For callback/check/resume/adapt/complete: load `commands/monitor.md`, execute matched handler, STOP. For callback/check/resume/adapt/complete: load `@commands/monitor.md`, execute matched handler, STOP.
## Phase 0: Session Resume Check ## Phase 0: Session Resume Check
@@ -84,13 +84,16 @@ TEXT-LEVEL ONLY. No source code reading.
] ]
}) })
``` ```
4. Delegate to `commands/analyze.md` -> output scope context 4. Delegate to `@commands/analyze.md` -> output scope context
5. Record: pipeline_mode, industry, complexity 5. Record: pipeline_mode, industry, complexity
## Phase 2: Create Team + Initialize Session ## Phase 2: Create Team + Initialize Session
1. Generate session ID: `UDS-<slug>-<YYYY-MM-DD>` 1. Resolve workspace paths (MUST do first):
2. Create session folder structure: - `project_root` = result of `Bash({ command: "pwd" })`
- `skill_root` = `<project_root>/.claude/skills/team-uidesign`
2. Generate session ID: `UDS-<slug>-<YYYY-MM-DD>`
3. Create session folder structure:
``` ```
.workflow/.team/UDS-<slug>-<date>/research/ .workflow/.team/UDS-<slug>-<date>/research/
.workflow/.team/UDS-<slug>-<date>/design/component-specs/ .workflow/.team/UDS-<slug>-<date>/design/component-specs/
@@ -101,13 +104,13 @@ TEXT-LEVEL ONLY. No source code reading.
.workflow/.team/UDS-<slug>-<date>/wisdom/ .workflow/.team/UDS-<slug>-<date>/wisdom/
.workflow/.team/UDS-<slug>-<date>/.msg/ .workflow/.team/UDS-<slug>-<date>/.msg/
``` ```
3. Initialize `.msg/meta.json` via team_msg state_update with pipeline metadata 4. Initialize `.msg/meta.json` via team_msg state_update with pipeline metadata
4. TeamCreate(team_name="uidesign") 5. TeamCreate(team_name="uidesign")
5. Do NOT spawn workers yet - deferred to Phase 4 6. Do NOT spawn workers yet - deferred to Phase 4
## Phase 3: Create Task Chain ## Phase 3: Create Task Chain
Delegate to `commands/dispatch.md`. Task chains by mode: Delegate to `@commands/dispatch.md`. Task chains by mode:
| Mode | Task Chain | | Mode | Task Chain |
|------|------------| |------|------------|
@@ -117,7 +120,7 @@ Delegate to `commands/dispatch.md`. Task chains by mode:
## Phase 4: Spawn-and-Stop ## Phase 4: Spawn-and-Stop
Delegate to `commands/monitor.md#handleSpawnNext`: Delegate to `@commands/monitor.md#handleSpawnNext`:
1. Find ready tasks (pending + blockedBy resolved) 1. Find ready tasks (pending + blockedBy resolved)
2. Spawn team-worker agents (see SKILL.md Spawn Template) 2. Spawn team-worker agents (see SKILL.md Spawn Template)
3. Output status summary 3. Output status summary

6
.claude/skills/team-ultra-analyze/SKILL.md
View File

@@ -52,7 +52,7 @@ Pipeline (Quick mode):
Parse `$ARGUMENTS`: Parse `$ARGUMENTS`:
- Has `--role <name>` → Read `roles/<name>/role.md`, execute Phase 2-4 - Has `--role <name>` → Read `roles/<name>/role.md`, execute Phase 2-4
- No `--role` → Read `roles/coordinator/role.md`, execute entry router - No `--role` → `@roles/coordinator/role.md`, execute entry router
## Shared Constants ## Shared Constants
@@ -75,7 +75,7 @@ Agent({
run_in_background: true, run_in_background: true,
prompt: `## Role Assignment prompt: `## Role Assignment
role: <role> role: <role>
role_spec: ~ or <project>/.claude/skills/team-ultra-analyze/roles/<role>/role.md role_spec: <skill_root>/roles/<role>/role.md
session: <session-folder> session: <session-folder>
session_id: <session-id> session_id: <session-id>
team_name: ultra-analyze team_name: ultra-analyze
@@ -83,7 +83,7 @@ requirement: <topic-description>
agent_name: <agent-name> agent_name: <agent-name>
inner_loop: false inner_loop: false
Read role_spec file to load Phase 2-4 domain instructions. Read role_spec file (@<skill_root>/roles/<role>/role.md) to load Phase 2-4 domain instructions.
Execute built-in Phase 1 (task discovery, owner=<agent-name>) -> role Phase 2-4 -> built-in Phase 5 (report).` Execute built-in Phase 1 (task discovery, owner=<agent-name>) -> role Phase 2-4 -> built-in Phase 5 (report).`
}) })
``` ```

21
.claude/skills/team-ultra-analyze/roles/coordinator/role.md
View File

@@ -51,7 +51,7 @@ When coordinator is invoked, detect invocation type:
| Interrupted session | Active/paused session exists | -> Phase 0 | | Interrupted session | Active/paused session exists | -> Phase 0 |
| New session | None of above | -> Phase 1 | | New session | None of above | -> Phase 1 |
For callback/check/resume/complete: load `commands/monitor.md` and execute matched handler, then STOP. For callback/check/resume/complete: load `@commands/monitor.md` and execute matched handler, then STOP.
### Router Implementation ### Router Implementation
@@ -95,15 +95,18 @@ TEXT-LEVEL ONLY. No source code reading.
1. Parse user task description from $ARGUMENTS 1. Parse user task description from $ARGUMENTS
2. Extract explicit settings: `--mode`, scope, focus areas 2. Extract explicit settings: `--mode`, scope, focus areas
3. Delegate to `commands/analyze.md` for signal detection and pipeline mode selection 3. Delegate to `@commands/analyze.md` for signal detection and pipeline mode selection
4. **Interactive clarification** (non-auto mode): AskUserQuestion for focus, perspectives, depth. 4. **Interactive clarification** (non-auto mode): AskUserQuestion for focus, perspectives, depth.
--- ---
## Phase 2: Create Team + Initialize Session ## Phase 2: Create Team + Initialize Session
1. Generate session ID: `UAN-{slug}-{YYYY-MM-DD}` 1. Resolve workspace paths (MUST do first):
2. Create session folder structure: - `project_root` = result of `Bash({ command: "pwd" })`
- `skill_root` = `<project_root>/.claude/skills/team-ultra-analyze`
3. Generate session ID: `UAN-{slug}-{YYYY-MM-DD}`
4. Create session folder structure:
``` ```
.workflow/.team/UAN-{slug}-{date}/ .workflow/.team/UAN-{slug}-{date}/
@@ -117,8 +120,8 @@ TEXT-LEVEL ONLY. No source code reading.
+-- learnings.md, decisions.md, conventions.md, issues.md +-- learnings.md, decisions.md, conventions.md, issues.md
``` ```
3. Write session.json with mode, requirement, timestamp 5. Write session.json with mode, requirement, timestamp
4. Initialize .msg/meta.json with pipeline metadata via team_msg: 6. Initialize .msg/meta.json with pipeline metadata via team_msg:
```typescript ```typescript
mcp__ccw-tools__team_msg({ mcp__ccw-tools__team_msg({
operation: "log", operation: "log",
@@ -134,13 +137,13 @@ mcp__ccw-tools__team_msg({
} }
}) })
``` ```
5. Call `TeamCreate({ team_name: "ultra-analyze" })` 7. Call `TeamCreate({ team_name: "ultra-analyze" })`
--- ---
## Phase 3: Create Task Chain ## Phase 3: Create Task Chain
Execute `commands/dispatch.md` inline (Command Execution Protocol): Execute `@commands/dispatch.md` inline (Command Execution Protocol):
1. Read `roles/coordinator/commands/dispatch.md` 1. Read `roles/coordinator/commands/dispatch.md`
2. Follow dispatch Phase 2 -> Phase 3 -> Phase 4 2. Follow dispatch Phase 2 -> Phase 3 -> Phase 4
3. Result: all pipeline tasks created with correct blockedBy dependencies 3. Result: all pipeline tasks created with correct blockedBy dependencies
@@ -152,7 +155,7 @@ Execute `commands/dispatch.md` inline (Command Execution Protocol):
### Initial Spawn ### Initial Spawn
Find first unblocked tasks and spawn their workers. Use SKILL.md Worker Spawn Template with: Find first unblocked tasks and spawn their workers. Use SKILL.md Worker Spawn Template with:
- `role_spec: ~ or <project>/.claude/skills/team-ultra-analyze/roles/<role>/role.md` - `role_spec: <skill_root>/roles/<role>/role.md`
- `team_name: ultra-analyze` - `team_name: ultra-analyze`
- `inner_loop: false` - `inner_loop: false`

6
.claude/skills/team-ux-improve/SKILL.md
View File

@@ -53,7 +53,7 @@ Skill(skill="team-ux-improve", args="<project-path> [--framework react|vue]")
Parse `$ARGUMENTS`: Parse `$ARGUMENTS`:
- Has `--role <name>` → Read `roles/<name>/role.md`, execute Phase 2-4 - Has `--role <name>` → Read `roles/<name>/role.md`, execute Phase 2-4
- No `--role` → Read `roles/coordinator/role.md`, execute entry router - No `--role` → `@roles/coordinator/role.md`, execute entry router
## Shared Constants ## Shared Constants
@@ -76,14 +76,14 @@ Agent({
run_in_background: true, run_in_background: true,
prompt: `## Role Assignment prompt: `## Role Assignment
role: <role> role: <role>
role_spec: ~ or <project>/.claude/skills/team-ux-improve/roles/<role>/role.md role_spec: <skill_root>/roles/<role>/role.md
session: <session-folder> session: <session-folder>
session_id: <session-id> session_id: <session-id>
team_name: ux-improve team_name: ux-improve
requirement: <task-description> requirement: <task-description>
inner_loop: <true|false> inner_loop: <true|false>
Read role_spec file to load Phase 2-4 domain instructions. Read role_spec file (@<skill_root>/roles/<role>/role.md) to load Phase 2-4 domain instructions.
Execute built-in Phase 1 (task discovery) -> role Phase 2-4 -> built-in Phase 5 (report).` Execute built-in Phase 1 (task discovery) -> role Phase 2-4 -> built-in Phase 5 (report).`
}) })
``` ```

25
.claude/skills/team-ux-improve/roles/coordinator/role.md
View File

@@ -45,7 +45,7 @@ When coordinator needs to execute a command (analyze, dispatch, monitor):
| Interrupted session | Active/paused session exists in .workflow/.team/ux-improve-* | -> Phase 0 | | Interrupted session | Active/paused session exists in .workflow/.team/ux-improve-* | -> Phase 0 |
| New session | None of above | -> Phase 1 | | New session | None of above | -> Phase 1 |
For callback/check/resume/adapt/complete: load `commands/monitor.md`, execute matched handler, STOP. For callback/check/resume/adapt/complete: load `@commands/monitor.md`, execute matched handler, STOP.
## Phase 0: Session Resume Check ## Phase 0: Session Resume Check
@@ -62,13 +62,16 @@ TEXT-LEVEL ONLY. No source code reading.
- `<project-path>` (required) - `<project-path>` (required)
- `--framework react|vue` (optional, auto-detect if omitted) - `--framework react|vue` (optional, auto-detect if omitted)
2. If project path missing -> AskUserQuestion for path 2. If project path missing -> AskUserQuestion for path
3. Delegate to `commands/analyze.md` -> output scope context 3. Delegate to `@commands/analyze.md` -> output scope context
4. Store: project_path, framework, pipeline_mode, issue_signals 4. Store: project_path, framework, pipeline_mode, issue_signals
## Phase 2: Create Team + Initialize Session ## Phase 2: Create Team + Initialize Session
1. Generate session ID: `ux-improve-<timestamp>` 1. Resolve workspace paths (MUST do first):
2. Create session folder structure: - `project_root` = result of `Bash({ command: "pwd" })`
- `skill_root` = `<project_root>/.claude/skills/team-ux-improve`
2. Generate session ID: `ux-improve-<timestamp>`
3. Create session folder structure:
``` ```
.workflow/.team/ux-improve-<timestamp>/ .workflow/.team/ux-improve-<timestamp>/
├── .msg/ ├── .msg/
@@ -76,20 +79,20 @@ TEXT-LEVEL ONLY. No source code reading.
├── explorations/ ├── explorations/
└── wisdom/contributions/ └── wisdom/contributions/
``` ```
3. **Wisdom Initialization**: Copy `~ or <project>/.claude/skills/team-ux-improve/wisdom/` to `<session>/wisdom/` 4. **Wisdom Initialization**: Copy `<skill_root>/wisdom/` to `<session>/wisdom/`
4. Initialize `.msg/meta.json` via team_msg state_update with pipeline metadata 5. Initialize `.msg/meta.json` via team_msg state_update with pipeline metadata
5. TeamCreate(team_name="ux-improve") 6. TeamCreate(team_name="ux-improve")
6. Do NOT spawn workers yet - deferred to Phase 4 7. Do NOT spawn workers yet - deferred to Phase 4
## Phase 3: Create Task Chain ## Phase 3: Create Task Chain
Delegate to `commands/dispatch.md`. Standard pipeline: Delegate to `@commands/dispatch.md`. Standard pipeline:
SCAN-001 -> DIAG-001 -> DESIGN-001 -> IMPL-001 -> TEST-001 SCAN-001 -> DIAG-001 -> DESIGN-001 -> IMPL-001 -> TEST-001
## Phase 4: Spawn-and-Stop ## Phase 4: Spawn-and-Stop
Delegate to `commands/monitor.md#handleSpawnNext`: Delegate to `@commands/monitor.md#handleSpawnNext`:
1. Find ready tasks (pending + blockedBy resolved) 1. Find ready tasks (pending + blockedBy resolved)
2. Spawn team-worker agents (see SKILL.md Spawn Template) 2. Spawn team-worker agents (see SKILL.md Spawn Template)
3. Output status summary 3. Output status summary
@@ -110,7 +113,7 @@ Delegate to `commands/monitor.md#handleSpawnNext`:
3. **Wisdom Consolidation**: Check `<session>/wisdom/contributions/` for worker contributions 3. **Wisdom Consolidation**: Check `<session>/wisdom/contributions/` for worker contributions
- If contributions exist -> AskUserQuestion to merge to permanent wisdom - If contributions exist -> AskUserQuestion to merge to permanent wisdom
- If approved -> copy to `~ or <project>/.claude/skills/team-ux-improve/wisdom/` - If approved -> copy to `<skill_root>/wisdom/`
4. Calculate: completed_tasks, total_issues_found, issues_fixed, test_pass_rate 4. Calculate: completed_tasks, total_issues_found, issues_fixed, test_pass_rate
5. Output pipeline summary with [coordinator] prefix 5. Output pipeline summary with [coordinator] prefix