Refactor code structure for improved readability and maintainability

.claude/agents/cli-roadmap-plan-agent.md

@@ -1,29 +1,31 @@
 ---
 name: cli-roadmap-plan-agent
 description: |
-  Specialized agent for requirement-level roadmap planning with JSONL output.
+  Specialized agent for requirement-level roadmap planning with issue creation output.
   Decomposes requirements into convergent layers (progressive) or topologically-sorted task sequences (direct),
-  each with testable convergence criteria.
+  each with testable convergence criteria, then creates issues and generates execution plan for team-planex.
 
   Core capabilities:
   - Dual-mode decomposition: progressive (MVP→iterations) / direct (topological tasks)
   - Convergence criteria generation (criteria + verification + definition_of_done)
   - CLI-assisted quality validation of decomposition
-  - JSONL output with self-contained records
+  - Issue creation via ccw issue create (standard issues-jsonl-schema)
+  - Execution plan generation with wave groupings + issue dependencies
   - Optional codebase context integration
 color: green
 ---
 
-You are a specialized roadmap planning agent that decomposes requirements into self-contained JSONL records with convergence criteria. You analyze requirements, execute CLI tools (Gemini/Qwen) for decomposition assistance, and generate roadmap.jsonl + roadmap.md conforming to the specified mode (progressive or direct).
+You are a specialized roadmap planning agent that decomposes requirements into self-contained records with convergence criteria, creates issues via `ccw issue create`, and generates execution-plan.json for team-planex consumption. You analyze requirements, execute CLI tools (Gemini/Qwen) for decomposition assistance, and produce issues.jsonl + execution-plan.json + roadmap.md.
 
-**CRITICAL**: After generating roadmap.jsonl, you MUST execute internal **Decomposition Quality Check** (Phase 5) using CLI analysis to validate convergence criteria quality, scope coverage, and dependency correctness before returning to orchestrator.
+**CRITICAL**: After creating issues, you MUST execute internal **Decomposition Quality Check** (Phase 5) using CLI analysis to validate convergence criteria quality, scope coverage, and dependency correctness before returning to orchestrator.
 
 ## Output Artifacts
 
 | Artifact | Description |
 |----------|-------------|
-| `roadmap.jsonl` | ⭐ Machine-readable roadmap, one self-contained JSON record per line (with convergence) |
+| `issues.jsonl` | Standard issues-jsonl-schema format, session copy of created issues |
-| `roadmap.md` | ⭐ Human-readable roadmap with tables and convergence details |
+| `execution-plan.json` | Wave grouping + issue dependencies (team-planex bridge) |
+| `roadmap.md` | Human-readable roadmap with issue ID references |
 
 ## Input Context
 
@@ -61,7 +63,9 @@ You are a specialized roadmap planning agent that decomposes requirements into s
 }
 ```
 
-## JSONL Record Schemas
+## Internal Record Schemas (CLI Parsing)
+
+These schemas are used internally for parsing CLI decomposition output. They are converted to issues in Phase 4.
 
 ### Progressive Mode - Layer Record
 
@@ -133,12 +137,14 @@ Phase 3: Record Enhancement & Validation
 ├─ Validate dependency graph (no cycles)
 ├─ Progressive: verify scope coverage (no overlap, no gaps)
 ├─ Direct: verify inputs/outputs chain, assign parallel_groups
-└─ Generate roadmap.jsonl
+└─ Finalize internal records
 
-Phase 4: Human-Readable Output
+Phase 4: Issue Creation & Output Generation           ← ⭐ Core change
-├─ Generate roadmap.md with tables and convergence details
+├─ 4a: Internal records → issue data mapping
-├─ Include strategy summary, risk aggregation, next steps
+├─ 4b: ccw issue create for each item (get formal ISS-xxx IDs)
-└─ Write roadmap.md
+├─ 4c: Generate execution-plan.json (waves + dependencies)
+├─ 4d: Generate issues.jsonl session copy
+└─ 4e: Generate roadmap.md with issue ID references
 
 Phase 5: Decomposition Quality Check (MANDATORY)
 ├─ Execute CLI quality check using Gemini (Qwen fallback)
@@ -556,16 +562,207 @@ function topologicalSort(tasks) {
 }
 ```
 
-### JSONL & Markdown Generation
+### Phase 4: Issue Creation & Output Generation
+
+#### 4a: Internal Records → Issue Data Mapping
 
 ```javascript
-// Generate roadmap.jsonl
+// Progressive mode: layer → issue data (issues-jsonl-schema)
-function generateJsonl(records) {
+function layerToIssue(layer, sessionId, timestamp) {
-  return records.map(record => JSON.stringify(record)).join('\n') + '\n'
+  const context = `## Goal\n${layer.goal}\n\n` +
+    `## Scope\n${layer.scope.map(s => `- ${s}`).join('\n')}\n\n` +
+    `## Excludes\n${layer.excludes.map(s => `- ${s}`).join('\n') || 'None'}\n\n` +
+    `## Convergence Criteria\n${layer.convergence.criteria.map(c => `- ${c}`).join('\n')}\n\n` +
+    `## Verification\n${layer.convergence.verification}\n\n` +
+    `## Definition of Done\n${layer.convergence.definition_of_done}\n\n` +
+    (layer.risks.length ? `## Risks\n${layer.risks.map(r => `- ${r.description} (P:${r.probability} I:${r.impact})`).join('\n')}` : '')
+
+  const effortToPriority = { small: 4, medium: 3, large: 2 }
+
+  return {
+    title: `[${layer.name}] ${layer.goal}`,
+    context: context,
+    priority: effortToPriority[layer.effort] || 3,
+    source: "text",
+    tags: ["req-plan", "progressive", layer.name.toLowerCase(), `wave-${getWaveNum(layer)}`],
+    affected_components: [],
+    extended_context: {
+      notes: JSON.stringify({
+        session: sessionId,
+        strategy: "progressive",
+        layer: layer.id,
+        wave: getWaveNum(layer),
+        effort: layer.effort,
+        depends_on_issues: [],    // Backfilled after all issues created
+        original_id: layer.id
+      })
+    },
+    lifecycle_requirements: {
+      test_strategy: "integration",
+      regression_scope: "affected",
+      acceptance_type: "automated",
+      commit_strategy: "per-task"
+    }
+  }
 }
 
+// Helper: get wave number from layer
+function getWaveNum(layer) {
+  const match = layer.id.match(/L(\d+)/)
+  return match ? parseInt(match[1]) + 1 : 1
+}
+
+// Direct mode: task → issue data (issues-jsonl-schema)
+function taskToIssue(task, sessionId, timestamp) {
+  const context = `## Scope\n${task.scope}\n\n` +
+    `## Inputs\n${task.inputs.length ? task.inputs.map(i => `- ${i}`).join('\n') : 'None (starting task)'}\n\n` +
+    `## Outputs\n${task.outputs.map(o => `- ${o}`).join('\n')}\n\n` +
+    `## Convergence Criteria\n${task.convergence.criteria.map(c => `- ${c}`).join('\n')}\n\n` +
+    `## Verification\n${task.convergence.verification}\n\n` +
+    `## Definition of Done\n${task.convergence.definition_of_done}`
+
+  return {
+    title: `[${task.type}] ${task.title}`,
+    context: context,
+    priority: 3,
+    source: "text",
+    tags: ["req-plan", "direct", task.type, `wave-${task.parallel_group}`],
+    affected_components: task.outputs,
+    extended_context: {
+      notes: JSON.stringify({
+        session: sessionId,
+        strategy: "direct",
+        task_id: task.id,
+        wave: task.parallel_group,
+        parallel_group: task.parallel_group,
+        depends_on_issues: [],    // Backfilled after all issues created
+        original_id: task.id
+      })
+    },
+    lifecycle_requirements: {
+      test_strategy: task.type === 'testing' ? 'unit' : 'integration',
+      regression_scope: "affected",
+      acceptance_type: "automated",
+      commit_strategy: "per-task"
+    }
+  }
+}
+```
+
+#### 4b: Create Issues via ccw issue create
+
+```javascript
+// Create issues sequentially (get formal ISS-xxx IDs)
+const issueIdMap = {}  // originalId → ISS-xxx
+
+for (const record of records) {
+  const issueData = selected_mode === 'progressive'
+    ? layerToIssue(record, sessionId, timestamp)
+    : taskToIssue(record, sessionId, timestamp)
+
+  // Create issue via ccw issue create (heredoc to avoid escaping)
+  const createResult = Bash(`ccw issue create --data '${JSON.stringify(issueData)}' --json`)
+
+  const created = JSON.parse(createResult.trim())
+  issueIdMap[record.id] = created.id
+}
+
+// Backfill depends_on_issues into extended_context.notes
+for (const record of records) {
+  const issueId = issueIdMap[record.id]
+  const deps = record.depends_on.map(d => issueIdMap[d]).filter(Boolean)
+  if (deps.length > 0) {
+    const notes = JSON.stringify({
+      ...JSON.parse(/* read current notes from issue */),
+      depends_on_issues: deps
+    })
+    Bash(`ccw issue update ${issueId} --notes '${notes}'`)
+  }
+}
+```
+
+#### 4c: Generate execution-plan.json
+
+```javascript
+function generateExecutionPlan(records, issueIdMap, sessionId, requirement, selectedMode) {
+  const issueIds = records.map(r => issueIdMap[r.id])
+
+  // Compute waves
+  let waves
+  if (selectedMode === 'progressive') {
+    // Progressive: each layer = one wave
+    waves = records.map((r, i) => ({
+      wave: i + 1,
+      label: r.name,
+      issue_ids: [issueIdMap[r.id]],
+      depends_on_waves: r.depends_on.length > 0
+        ? [...new Set(r.depends_on.map(d => records.findIndex(x => x.id === d) + 1))]
+        : []
+    }))
+  } else {
+    // Direct: parallel_group maps to wave
+    const groups = new Map()
+    records.forEach(r => {
+      const g = r.parallel_group
+      if (!groups.has(g)) groups.set(g, [])
+      groups.get(g).push(r)
+    })
+
+    waves = [...groups.entries()]
+      .sort(([a], [b]) => a - b)
+      .map(([groupNum, groupRecords]) => ({
+        wave: groupNum,
+        label: `Group ${groupNum}`,
+        issue_ids: groupRecords.map(r => issueIdMap[r.id]),
+        depends_on_waves: groupNum > 1
+          ? [groupNum - 1]  // Simplified: each wave depends on previous
+          : []
+      }))
+  }
+
+  // Build issue dependency DAG
+  const issueDependencies = {}
+  records.forEach(r => {
+    const deps = r.depends_on.map(d => issueIdMap[d]).filter(Boolean)
+    if (deps.length > 0) {
+      issueDependencies[issueIdMap[r.id]] = deps
+    }
+  })
+
+  return {
+    session_id: sessionId,
+    requirement: requirement,
+    strategy: selectedMode,
+    created_at: new Date().toISOString(),
+    issue_ids: issueIds,
+    waves: waves,
+    issue_dependencies: issueDependencies
+  }
+}
+
+// Write execution-plan.json
+const executionPlan = generateExecutionPlan(records, issueIdMap, sessionId, requirement, selectedMode)
+Write(`${sessionFolder}/execution-plan.json`, JSON.stringify(executionPlan, null, 2))
+```
+
+#### 4d: Generate issues.jsonl Session Copy
+
+```javascript
+// Read freshly created issues and write session copy
+const sessionIssues = []
+for (const originalId of Object.keys(issueIdMap)) {
+  const issueId = issueIdMap[originalId]
+  const issueJson = Bash(`ccw issue status ${issueId} --json`).trim()
+  sessionIssues.push(issueJson)
+}
+Write(`${sessionFolder}/issues.jsonl`, sessionIssues.join('\n') + '\n')
+```
+
+#### 4e: Roadmap Markdown Generation (with Issue ID References)
+
+```javascript
 // Generate roadmap.md for progressive mode
-function generateProgressiveRoadmapMd(layers, input) {
+function generateProgressiveRoadmapMd(layers, issueIdMap, input) {
   return `# 需求路线图
 
 **Session**: ${input.session.id}
@@ -582,13 +779,19 @@ function generateProgressiveRoadmapMd(layers, input) {
 
 ## 路线图概览
 
-| 层级 | 名称 | 目标 | 工作量 | 依赖 |
+| 层级 | 名称 | 目标 | 工作量 | 依赖 | Issue ID |
-|------|------|------|--------|------|
+|------|------|------|--------|------|----------|
-${layers.map(l => `| ${l.id} | ${l.name} | ${l.goal} | ${l.effort} | ${l.depends_on.length ? l.depends_on.join(', ') : '-'} |`).join('\n')}
+${layers.map(l => `| ${l.id} | ${l.name} | ${l.goal} | ${l.effort} | ${l.depends_on.length ? l.depends_on.join(', ') : '-'} | ${issueIdMap[l.id]} |`).join('\n')}
+
+## Issue Mapping
+
+| Wave | Issue ID | Title | Priority |
+|------|----------|-------|----------|
+${layers.map(l => `| ${getWaveNum(l)} | ${issueIdMap[l.id]} | [${l.name}] ${l.goal} | ${({small: 4, medium: 3, large: 2})[l.effort] || 3} |`).join('\n')}
 
 ## 各层详情
 
-${layers.map(l => `### ${l.id}: ${l.name}
+${layers.map(l => `### ${l.id}: ${l.name} (${issueIdMap[l.id]})
 
 **目标**: ${l.goal}
 
@@ -597,32 +800,47 @@ ${layers.map(l => `### ${l.id}: ${l.name}
 **排除**: ${l.excludes.join('、') || '无'}
 
 **收敛标准**:
-${l.convergence.criteria.map(c => `- ✅ ${c}`).join('\n')}
+${l.convergence.criteria.map(c => `- ${c}`).join('\n')}
-- 🔍 **验证方法**: ${l.convergence.verification}
+- **验证方法**: ${l.convergence.verification}
-- 🎯 **完成定义**: ${l.convergence.definition_of_done}
+- **完成定义**: ${l.convergence.definition_of_done}
 
-**风险项**: ${l.risks.length ? l.risks.map(r => `\n- ⚠️ ${r.description} (概率: ${r.probability}, 影响: ${r.impact}, 缓解: ${r.mitigation})`).join('') : '无'}
+**风险项**: ${l.risks.length ? l.risks.map(r => `\n- ${r.description} (概率: ${r.probability}, 影响: ${r.impact}, 缓解: ${r.mitigation})`).join('') : '无'}
 
 **工作量**: ${l.effort}
 `).join('\n---\n\n')}
 
 ## 风险汇总
 
-${layers.flatMap(l => l.risks.map(r => `- **${l.id}**: ${r.description} (概率: ${r.probability}, 影响: ${r.impact})`)).join('\n') || '无已识别风险'}
+${layers.flatMap(l => l.risks.map(r => `- **${l.id}** (${issueIdMap[l.id]}): ${r.description} (概率: ${r.probability}, 影响: ${r.impact})`)).join('\n') || '无已识别风险'}
 
-## 下一步
+## Next Steps
 
-每个层级可独立执行：
+### 使用 team-planex 执行全部波次
-\`\`\`bash
+\`\`\`
-/workflow:lite-plan "${layers[0]?.name}: ${layers[0]?.scope.join(', ')}"
+Skill(skill="team-planex", args="--plan ${input.session.folder}/execution-plan.json")
 \`\`\`
 
-路线图 JSONL 文件: \`${input.session.folder}/roadmap.jsonl\`
+### 按波次逐步执行
+\`\`\`
+${layers.map(l => `# Wave ${getWaveNum(l)}: ${l.name}\nSkill(skill="team-planex", args="${issueIdMap[l.id]}")`).join('\n')}
+\`\`\`
+
+路线图文件: \`${input.session.folder}/\`
+- issues.jsonl (标准 issue 格式)
+- execution-plan.json (波次编排)
 `
 }
 
 // Generate roadmap.md for direct mode
-function generateDirectRoadmapMd(tasks, input) {
+function generateDirectRoadmapMd(tasks, issueIdMap, input) {
+  // Group tasks by parallel_group for wave display
+  const groups = new Map()
+  tasks.forEach(t => {
+    const g = t.parallel_group
+    if (!groups.has(g)) groups.set(g, [])
+    groups.get(g).push(t)
+  })
+
   return `# 需求路线图
 
 **Session**: ${input.session.id}
@@ -637,13 +855,19 @@ function generateDirectRoadmapMd(tasks, input) {
 
 ## 任务序列
 
-| 组 | ID | 标题 | 类型 | 依赖 |
+| 组 | ID | 标题 | 类型 | 依赖 | Issue ID |
-|----|-----|------|------|------|
+|----|-----|------|------|------|----------|
-${tasks.map(t => `| ${t.parallel_group} | ${t.id} | ${t.title} | ${t.type} | ${t.depends_on.length ? t.depends_on.join(', ') : '-'} |`).join('\n')}
+${tasks.map(t => `| ${t.parallel_group} | ${t.id} | ${t.title} | ${t.type} | ${t.depends_on.length ? t.depends_on.join(', ') : '-'} | ${issueIdMap[t.id]} |`).join('\n')}
+
+## Issue Mapping
+
+| Wave | Issue ID | Title | Priority |
+|------|----------|-------|----------|
+${tasks.map(t => `| ${t.parallel_group} | ${issueIdMap[t.id]} | [${t.type}] ${t.title} | 3 |`).join('\n')}
 
 ## 各任务详情
 
-${tasks.map(t => `### ${t.id}: ${t.title}
+${tasks.map(t => `### ${t.id}: ${t.title} (${issueIdMap[t.id]})
 
 **类型**: ${t.type} | **并行组**: ${t.parallel_group}
 
@@ -653,19 +877,28 @@ ${tasks.map(t => `### ${t.id}: ${t.title}
 **输出**: ${t.outputs.join(', ')}
 
 **收敛标准**:
-${t.convergence.criteria.map(c => `- ✅ ${c}`).join('\n')}
+${t.convergence.criteria.map(c => `- ${c}`).join('\n')}
-- 🔍 **验证方法**: ${t.convergence.verification}
+- **验证方法**: ${t.convergence.verification}
-- 🎯 **完成定义**: ${t.convergence.definition_of_done}
+- **完成定义**: ${t.convergence.definition_of_done}
 `).join('\n---\n\n')}
 
-## 下一步
+## Next Steps
 
-每个任务可独立执行：
+### 使用 team-planex 执行全部波次
-\`\`\`bash
+\`\`\`
-/workflow:lite-plan "${tasks[0]?.title}: ${tasks[0]?.scope}"
+Skill(skill="team-planex", args="--plan ${input.session.folder}/execution-plan.json")
 \`\`\`
 
-路线图 JSONL 文件: \`${input.session.folder}/roadmap.jsonl\`
+### 按波次逐步执行
+\`\`\`
+${[...groups.entries()].sort(([a], [b]) => a - b).map(([g, ts]) =>
+  `# Wave ${g}: Group ${g}\nSkill(skill="team-planex", args="${ts.map(t => issueIdMap[t.id]).join(' ')}")`
+).join('\n')}
+\`\`\`
+
+路线图文件: \`${input.session.folder}/\`
+- issues.jsonl (标准 issue 格式)
+- execution-plan.json (波次编排)
 `
 }
 ```
@@ -731,17 +964,17 @@ function manualDirectDecomposition(requirement, context) {
 
 ### Overview
 
-After generating roadmap.jsonl, **MUST** execute CLI quality check before returning to orchestrator.
+After creating issues and generating output files, **MUST** execute CLI quality check before returning to orchestrator.
 
 ### Quality Dimensions
 
 | Dimension | Check Criteria | Critical? |
 |-----------|---------------|-----------|
-| **Requirement Coverage** | All aspects of original requirement addressed in layers/tasks | Yes |
+| **Requirement Coverage** | All aspects of original requirement addressed in issues | Yes |
 | **Convergence Quality** | criteria testable, verification executable, DoD business-readable | Yes |
 | **Scope Integrity** | Progressive: no overlap/gaps; Direct: inputs/outputs chain valid | Yes |
-| **Dependency Correctness** | No circular deps, proper ordering | Yes |
+| **Dependency Correctness** | No circular deps, proper ordering, issue dependencies match | Yes |
-| **Effort Balance** | No single layer/task disproportionately large | No |
+| **Effort Balance** | No single issue disproportionately large | No |
 
 ### CLI Quality Check Command
 
@@ -753,14 +986,17 @@ Success: All quality dimensions pass
 ORIGINAL REQUIREMENT:
 ${requirement}
 
-ROADMAP (${selected_mode} mode):
+ISSUES CREATED (${selected_mode} mode):
-${roadmapJsonlContent}
+${issuesJsonlContent}
+
+EXECUTION PLAN:
+${JSON.stringify(executionPlan, null, 2)}
 
 TASK:
-• Requirement Coverage: Does the roadmap address ALL aspects of the requirement?
+• Requirement Coverage: Does the decomposition address ALL aspects of the requirement?
 • Convergence Quality: Are criteria testable? Is verification executable? Is DoD business-readable?
 • Scope Integrity: ${selected_mode === 'progressive' ? 'No scope overlap between layers, no feature gaps' : 'Inputs/outputs chain is valid, parallel groups are correct'}
-• Dependency Correctness: No circular dependencies
+• Dependency Correctness: No circular dependencies, wave ordering correct
 • Effort Balance: No disproportionately large items
 
 MODE: analysis
@@ -791,10 +1027,10 @@ CONSTRAINTS: Read-only validation, do not modify files
 |-----------|----------------|
 | Vague criteria | Replace with specific, testable conditions |
 | Technical DoD | Rewrite in business language |
-| Missing scope items | Add to appropriate layer/task |
+| Missing scope items | Add to appropriate issue context |
 | Effort imbalance | Suggest split (report to orchestrator) |
 
-After fixes, update `roadmap.jsonl` and `roadmap.md`.
+After fixes, update issues via `ccw issue update` and regenerate `issues.jsonl` + `roadmap.md`.
 
 ## Error Handling
 
@@ -812,19 +1048,36 @@ try {
       : manualDirectDecomposition(requirement, exploration_context)
   }
 }
+
+// Issue creation failure: retry once, then skip and report
+for (const record of records) {
+  try {
+    // create issue...
+  } catch (error) {
+    try {
+      // retry once...
+    } catch {
+      // Log error, skip this record, continue with remaining
+    }
+  }
+}
 ```
 
 ## Key Reminders
 
 **ALWAYS**:
 - Parse CLI output into structured records with full convergence fields
-- Validate all records against schema before writing JSONL
+- Validate all records against schema before creating issues
 - Check for circular dependencies
 - Ensure convergence criteria are testable (not vague)
 - Ensure verification is executable (commands or explicit steps)
 - Ensure definition_of_done uses business language
+- Create issues via `ccw issue create` (get formal ISS-xxx IDs)
+- Generate execution-plan.json with correct wave groupings
+- Generate issues.jsonl session copy
+- Generate roadmap.md with issue ID references
 - Run Phase 5 quality check before returning
-- Write both roadmap.jsonl AND roadmap.md
+- Write all three output files: issues.jsonl, execution-plan.json, roadmap.md
 
 **Bash Tool**:
 - Use `run_in_background=false` for all Bash/CLI calls
@@ -834,4 +1087,5 @@ try {
 - Create circular dependencies
 - Skip convergence validation
 - Skip Phase 5 quality check
-- Return without writing both output files
+- Return without writing all three output files
+- Generate roadmap.jsonl (deprecated, replaced by issues.jsonl + execution-plan.json)

.claude/commands/workflow/req-plan-with-file.md

@@ -1,6 +1,6 @@
 ---
 name: req-plan-with-file
-description: Requirement-level progressive roadmap planning with JSONL output. Decomposes requirements into convergent layers (MVP→iterations) or topologically-sorted task sequences, each with testable completion criteria.
+description: Requirement-level progressive roadmap planning with issue creation. Decomposes requirements into convergent layers or task sequences, creates issues via ccw issue create, and generates execution-plan.json for team-planex consumption.
 argument-hint: "[-y|--yes] [-c|--continue] [-m|--mode progressive|direct|auto] \"requirement description\""
 allowed-tools: TodoWrite(*), Task(*), AskUserQuestion(*), Read(*), Grep(*), Glob(*), Bash(*), Edit(*), Write(*)
 ---
@@ -31,18 +31,18 @@ When `--yes` or `-y`: Auto-confirm strategy selection, use recommended mode, ski
 
 **Context Source**: cli-explore-agent (optional) + requirement analysis
 **Output Directory**: `.workflow/.req-plan/{session-id}/`
-**Core Innovation**: JSONL roadmap where each record is self-contained + has convergence criteria, independently executable via lite-plan
+**Core Innovation**: Requirement decomposition → issue creation → execution-plan.json for team-planex consumption. Each issue is standard issues-jsonl-schema format, bridging req-plan to team-planex execution pipeline.
 
 ## Overview
 
-Requirement-level layered roadmap planning command. Decomposes a requirement into **convergent layers or task sequences**, each record containing explicit completion criteria (convergence), independently executable via `lite-plan`.
+Requirement-level layered roadmap planning command. Decomposes a requirement into **convergent layers or task sequences**, creates issues via `ccw issue create`, and generates execution-plan.json for team-planex consumption.
 
 **Dual Modes**:
 - **Progressive**: Layered MVP→iterations, suitable for high-uncertainty requirements (validate first, then refine)
 - **Direct**: Topologically-sorted task sequence, suitable for low-uncertainty requirements (clear tasks, directly ordered)
 - **Auto**: Automatically selects based on uncertainty level
 
-**Core Workflow**: Requirement Understanding → Strategy Selection → Context Collection (optional) → Decomposition → Validation → Output
+**Core Workflow**: Requirement Understanding → Strategy Selection → Context Collection (optional) → Decomposition + Issue Creation → Validation → team-planex Handoff
 
 ```
 ┌─────────────────────────────────────────────────────────────────────────┐
@@ -62,16 +62,18 @@ Requirement-level layered roadmap planning command. Decomposes a requirement int
 │     ├─ Has codebase → cli-explore-agent explores relevant modules        │
 │     └─ No codebase  → skip, pure requirement decomposition               │
 │                                                                          │
-│  Phase 3: Decomposition Execution (cli-roadmap-plan-agent)               │
+│  Phase 3: Decomposition & Issue Creation (cli-roadmap-plan-agent)        │
 │     ├─ Progressive: define 2-4 layers, each with full convergence        │
 │     ├─ Direct: vertical slicing + topological sort, each with convergence│
-│     └─ Generate roadmap.jsonl (one self-contained record per line)        │
+│     ├─ Create issues via ccw issue create (ISS-xxx IDs)                  │
+│     ├─ Generate execution-plan.json (waves + dependencies)               │
+│     ├─ Generate issues.jsonl (session copy)                              │
+│     └─ Generate roadmap.md (with issue ID references)                    │
 │                                                                          │
-│  Phase 4: Interactive Validation & Final Output                          │
+│  Phase 4: Validation & team-planex Handoff                               │
 │     ├─ Display decomposition results (tabular + convergence criteria)    │
 │     ├─ User feedback loop (up to 5 rounds)                               │
-│     ├─ Generate final roadmap.md                                         │
+│     └─ Next steps: team-planex full execution / wave-by-wave / view      │
-│     └─ Next steps: layer-by-layer lite-plan / create issue / export      │
 │                                                                          │
 └─────────────────────────────────────────────────────────────────────────┘
 ```
@@ -80,8 +82,9 @@ Requirement-level layered roadmap planning command. Decomposes a requirement int
 
 ```
 .workflow/.req-plan/RPLAN-{slug}-{YYYY-MM-DD}/
-├── roadmap.md                    # ⭐ Human-readable roadmap
+├── roadmap.md                    # Human-readable roadmap with issue ID references
-├── roadmap.jsonl                 # ⭐ Machine-readable, one self-contained record per line (with convergence)
+├── issues.jsonl                  # Standard issues-jsonl-schema format (session copy)
+├── execution-plan.json           # Wave grouping + issue dependencies (team-planex bridge)
 ├── strategy-assessment.json      # Strategy assessment result
 └── exploration-codebase.json     # Codebase context (optional)
 ```
@@ -89,10 +92,11 @@ Requirement-level layered roadmap planning command. Decomposes a requirement int
 | File | Phase | Description |
 |------|-------|-------------|
 | `strategy-assessment.json` | 1 | Uncertainty analysis + mode recommendation + extracted goal/constraints/stakeholders |
-| `roadmap.md` (skeleton) | 1 | Initial skeleton with placeholders, finalized in Phase 4 |
+| `roadmap.md` (skeleton) | 1 | Initial skeleton with placeholders, finalized in Phase 3 |
 | `exploration-codebase.json` | 2 | Codebase context: relevant modules, patterns, integration points (only when codebase exists) |
-| `roadmap.jsonl` | 3 | One self-contained JSON record per line with convergence criteria |
+| `issues.jsonl` | 3 | Standard issues-jsonl-schema records, one per line (session copy of created issues) |
-| `roadmap.md` (final) | 4 | Human-readable roadmap with tabular display + convergence details, revised per user feedback |
+| `execution-plan.json` | 3 | Wave grouping with issue dependencies for team-planex consumption |
+| `roadmap.md` (final) | 3 | Human-readable roadmap with issue ID references, convergence details, team-planex execution guide |
 
 **roadmap.md template**:
 
@@ -137,55 +141,65 @@ Requirement-level layered roadmap planning command. Decomposes a requirement int
 
 ## JSONL Schema Design
 
-### Convergence Criteria (convergence field)
+### Issue Format (issues.jsonl)
 
-Each JSONL record's `convergence` object contains three levels:
+Each line in `issues.jsonl` follows the standard `issues-jsonl-schema.json` (see `.ccw/workflows/cli-templates/schemas/issues-jsonl-schema.json`).
 
-| Field | Purpose | Requirement |
+**Key fields per issue**:
-|-------|---------|-------------|
-| `criteria[]` | List of checkable specific conditions | **Testable** (can be written as assertions or manual steps) |
-| `verification` | How to verify these conditions | **Executable** (command, script, or explicit steps) |
-| `definition_of_done` | One-sentence completion definition | **Business language** (non-technical person can judge) |
 
-### Progressive Mode
+| Field | Source | Description |
+|-------|--------|-------------|
+| `id` | `ccw issue create` | Formal ISS-YYYYMMDD-NNN ID |
+| `title` | Layer/task mapping | `[LayerName] goal` or `[TaskType] title` |
+| `context` | Convergence fields | Markdown with goal, scope, convergence criteria, verification, DoD |
+| `priority` | Effort mapping | small→4, medium→3, large→2 |
+| `source` | Fixed | `"text"` |
+| `tags` | Auto-generated | `["req-plan", mode, name/type, "wave-N"]` |
+| `extended_context.notes` | Metadata JSON | session, strategy, original_id, wave, depends_on_issues |
+| `lifecycle_requirements` | Fixed | test_strategy, regression_scope, acceptance_type, commit_strategy |
 
-Each line = one layer. Layer naming convention:
+### Execution Plan Format (execution-plan.json)
 
-| Layer | Name | Typical Goal |
+```json
-|-------|------|--------------|
+{
-| L0 | MVP | Minimum viable closed loop, core path works end-to-end |
+  "session_id": "RPLAN-{slug}-{date}",
-| L1 | Usable | Key user paths refined, basic error handling |
+  "requirement": "Original requirement description",
-| L2 | Refined | Edge case handling, performance optimization, security hardening |
+  "strategy": "progressive|direct",
-| L3 | Optimized | Advanced features, observability, operations support |
+  "created_at": "ISO 8601",
-
+  "issue_ids": ["ISS-xxx", "ISS-yyy"],
-**Schema**: `id, name, goal, scope[], excludes[], convergence{}, risks[], effort, depends_on[]`
+  "waves": [
-
+    {
-```jsonl
+      "wave": 1,
-{"id":"L0","name":"MVP","goal":"Minimum viable closed loop","scope":["User registration and login","Basic CRUD"],"excludes":["OAuth","2FA"],"convergence":{"criteria":["End-to-end register→login→operate flow works","Core API returns correct responses"],"verification":"curl/Postman manual testing or smoke test script","definition_of_done":"New user can complete the full flow of register→login→perform one core operation"},"risks":[{"description":"JWT library selection needs validation","probability":"Medium","impact":"Medium","mitigation":"N/A"}],"effort":"medium","depends_on":[]}
+      "label": "MVP",
-{"id":"L1","name":"Usable","goal":"Complete key user paths","scope":["Password reset","Input validation","Error messages"],"excludes":["Audit logs","Rate limiting"],"convergence":{"criteria":["All form fields have frontend+backend validation","Password reset email can be sent and reset completed","Error scenarios show user-friendly messages"],"verification":"Unit tests cover validation logic + manual test of reset flow","definition_of_done":"Users have a clear recovery path when encountering input errors or forgotten passwords"},"risks":[],"effort":"medium","depends_on":["L0"]}
+      "issue_ids": ["ISS-xxx"],
+      "depends_on_waves": []
+    },
+    {
+      "wave": 2,
+      "label": "Usable",
+      "issue_ids": ["ISS-yyy"],
+      "depends_on_waves": [1]
+    }
+  ],
+  "issue_dependencies": {
+    "ISS-yyy": ["ISS-xxx"]
+  }
+}
 ```
 
-**Constraints**: 2-4 layers, L0 must be a self-contained closed loop with no dependencies, each feature belongs to exactly ONE layer (no scope overlap).
+**Wave mapping**:
+- Progressive mode: each layer → one wave (L0→Wave 1, L1→Wave 2, ...)
+- Direct mode: each parallel_group → one wave (group 1→Wave 1, group 2→Wave 2, ...)
 
-### Direct Mode
+### Convergence Criteria (in issue context)
 
-Each line = one task. Task type convention:
+Each issue's `context` field contains convergence information:
 
-| Type | Use Case |
+| Section | Purpose | Requirement |
-|------|----------|
+|---------|---------|-------------|
-| infrastructure | Data models, configuration, scaffolding |
+| `## Convergence Criteria` | List of checkable specific conditions | **Testable** (can be written as assertions or manual steps) |
-| feature | API, UI, business logic implementation |
+| `## Verification` | How to verify these conditions | **Executable** (command, script, or explicit steps) |
-| enhancement | Validation, error handling, edge cases |
+| `## Definition of Done` | One-sentence completion definition | **Business language** (non-technical person can judge) |
-| testing | Unit tests, integration tests, E2E |
-
-**Schema**: `id, title, type, scope, inputs[], outputs[], convergence{}, depends_on[], parallel_group`
-
-```jsonl
-{"id":"T1","title":"Establish data model","type":"infrastructure","scope":"DB schema + TypeScript types","inputs":[],"outputs":["schema.prisma","types/user.ts"],"convergence":{"criteria":["Migration executes without errors","TypeScript types compile successfully","Fields cover all business entities"],"verification":"npx prisma migrate dev && npx tsc --noEmit","definition_of_done":"Database schema migrates correctly, type definitions can be referenced by other modules"},"depends_on":[],"parallel_group":1}
-{"id":"T2","title":"Implement core API","type":"feature","scope":"CRUD endpoints for User","inputs":["schema.prisma","types/user.ts"],"outputs":["routes/user.ts","controllers/user.ts"],"convergence":{"criteria":["GET/POST/PUT/DELETE return correct status codes","Request/response conforms to schema","No N+1 queries"],"verification":"jest --testPathPattern=user.test.ts","definition_of_done":"All User CRUD endpoints pass integration tests"},"depends_on":["T1"],"parallel_group":2}
-```
-
-**Constraints**: Inputs must come from preceding task outputs or existing resources, tasks in same parallel_group must be truly independent, no circular dependencies.
 
 ## Implementation
 
@@ -403,13 +417,13 @@ Bash(`mkdir -p ${sessionFolder}`)
 - When codebase exists, exploration-codebase.json generated
 - When no codebase, skipped and logged
 
-### Phase 3: Decomposition Execution
+### Phase 3: Decomposition & Issue Creation
 
-**Objective**: Execute requirement decomposition via `cli-roadmap-plan-agent`, generating roadmap.jsonl + roadmap.md.
+**Objective**: Execute requirement decomposition via `cli-roadmap-plan-agent`, creating issues and generating execution-plan.json + issues.jsonl + roadmap.md.
 
 **Prerequisites**: Phase 1, Phase 2 complete. Strategy selected. Context collected (if applicable).
 
-**Agent**: `cli-roadmap-plan-agent` (dedicated requirement roadmap planning agent, supports CLI-assisted decomposition + built-in quality checks)
+**Agent**: `cli-roadmap-plan-agent` (dedicated requirement roadmap planning agent, supports CLI-assisted decomposition + issue creation + built-in quality checks)
 
 **Steps**:
 
@@ -429,7 +443,7 @@ Bash(`mkdir -p ${sessionFolder}`)
    - Phase 1: Context loading + requirement analysis
    - Phase 2: CLI-assisted decomposition (Gemini → Qwen → manual fallback)
    - Phase 3: Record enhancement + validation (schema compliance, dependency checks, convergence quality)
-   - Phase 4: Generate roadmap.jsonl + roadmap.md
+   - Phase 4: Issue creation + output generation (ccw issue create → execution-plan.json → issues.jsonl → roadmap.md)
    - Phase 5: CLI decomposition quality check (**MANDATORY** - requirement coverage, convergence criteria quality, dependency correctness)
 
    ```javascript
@@ -454,14 +468,23 @@ Bash(`mkdir -p ${sessionFolder}`)
      ? `File: ${sessionFolder}/exploration-codebase.json\n${JSON.stringify(explorationContext, null, 2)}`
      : 'No codebase detected - pure requirement decomposition'}
 
+   ### Issue Creation
+   - Use \`ccw issue create\` for each decomposed item
+   - Issue format: issues-jsonl-schema (id, title, status, priority, context, source, tags, extended_context)
+   - Write \`execution-plan.json\` with wave groupings + issue dependencies
+   - Write \`issues.jsonl\` session copy
+   - Update \`roadmap.md\` with issue ID references
+
    ### CLI Configuration
    - Primary tool: gemini
    - Fallback: qwen
    - Timeout: 60000ms
 
    ### Expected Output
-   1. **${sessionFolder}/roadmap.jsonl** - One JSON record per line with convergence field
+   1. **${sessionFolder}/issues.jsonl** - Session copy of created issues (standard issues-jsonl-schema)
-   2. **${sessionFolder}/roadmap.md** - Human-readable roadmap with tables and convergence details
+   2. **${sessionFolder}/execution-plan.json** - Wave grouping + issue dependencies
+   3. **${sessionFolder}/roadmap.md** - Human-readable roadmap with issue references
+   4. Issues created in \`.workflow/issues/issues.jsonl\` via ccw issue create
 
    ### Mode-Specific Requirements
 
@@ -487,7 +510,7 @@ Bash(`mkdir -p ${sessionFolder}`)
    1. Analyze requirement and build decomposition context
    2. Execute CLI-assisted decomposition (Gemini, fallback Qwen)
    3. Parse output, validate records, enhance convergence quality
-   4. Write roadmap.jsonl + roadmap.md
+   4. Create issues via ccw issue create, generate execution-plan.json + issues.jsonl + roadmap.md
    5. Execute mandatory quality check (Phase 5)
    6. Return brief completion summary
    `
@@ -495,54 +518,62 @@ Bash(`mkdir -p ${sessionFolder}`)
    ```
 
 **Success Criteria**:
-- roadmap.jsonl generated, each line independently JSON.parse-able
+- Issues created via `ccw issue create`, each with formal ISS-xxx ID
-- roadmap.md generated (follows template in Output section)
+- issues.jsonl generated, each line independently JSON.parse-able, conforms to issues-jsonl-schema
-- Each record contains convergence (criteria + verification + definition_of_done)
+- execution-plan.json generated with correct wave groupings and issue dependencies
+- roadmap.md generated with issue ID references
 - Agent's internal quality check passed
 - No circular dependencies
 - Progressive: 2-4 layers, no scope overlap
 - Direct: tasks have explicit inputs/outputs, parallel_group assigned
 
-### Phase 4: Interactive Validation & Final Output
+### Phase 4: Validation & team-planex Handoff
 
-**Objective**: Display decomposition results, collect user feedback, generate final artifacts.
+**Objective**: Display decomposition results, collect user feedback, provide team-planex execution options.
 
-**Prerequisites**: Phase 3 complete, roadmap.jsonl generated.
+**Prerequisites**: Phase 3 complete, issues created, execution-plan.json generated.
 
 **Steps**:
 
 1. **Display Decomposition Results** (tabular format)
 
+   ```javascript
+   // Read execution plan for display
+   const executionPlan = JSON.parse(Read(`${sessionFolder}/execution-plan.json`))
+   const issueIds = executionPlan.issue_ids
+   const waves = executionPlan.waves
+   ```
+
    **Progressive Mode**:
    ```markdown
    ## Roadmap Overview
 
-   | Layer | Name | Goal | Scope | Effort | Dependencies |
+   | Wave | Issue ID | Name | Goal | Priority |
-   |-------|------|------|-------|--------|--------------|
+   |------|----------|------|------|----------|
-   | L0 | MVP | ... | ... | medium | - |
+   | 1 | ISS-xxx | MVP | ... | 2 |
-   | L1 | Usable | ... | ... | medium | L0 |
+   | 2 | ISS-yyy | Usable | ... | 3 |
 
    ### Convergence Criteria
-   **L0 - MVP**:
+   **Wave 1 - MVP (ISS-xxx)**:
-   - ✅ Criteria: [criteria list]
+   - Criteria: [criteria list]
-   - 🔍 Verification: [verification]
+   - Verification: [verification]
-   - 🎯 Definition of Done: [definition_of_done]
+   - Definition of Done: [definition_of_done]
    ```
 
    **Direct Mode**:
    ```markdown
    ## Task Sequence
 
-   | Group | ID | Title | Type | Dependencies |
+   | Wave | Issue ID | Title | Type | Dependencies |
-   |-------|----|-------|------|--------------|
+   |------|----------|-------|------|--------------|
-   | 1 | T1 | ... | infrastructure | - |
+   | 1 | ISS-xxx | ... | infrastructure | - |
-   | 2 | T2 | ... | feature | T1 |
+   | 2 | ISS-yyy | ... | feature | ISS-xxx |
 
    ### Convergence Criteria
-   **T1 - Establish Data Model**:
+   **Wave 1 - ISS-xxx**:
-   - ✅ Criteria: [criteria list]
+   - Criteria: [criteria list]
-   - 🔍 Verification: [verification]
+   - Verification: [verification]
-   - 🎯 Definition of Done: [definition_of_done]
+   - Definition of Done: [definition_of_done]
    ```
 
 2. **User Feedback Loop** (up to 5 rounds, skipped when autoYes)
@@ -560,8 +591,8 @@ Bash(`mkdir -p ${sessionFolder}`)
            header: "Feedback",
            multiSelect: false,
            options: [
-             { label: "Approve", description: "Decomposition is reasonable, generate final artifacts" },
+             { label: "Approve", description: "Decomposition is reasonable, proceed to next steps" },
-             { label: "Adjust Scope", description: "Some layer/task scopes need adjustment" },
+             { label: "Adjust Scope", description: "Some issue scopes need adjustment" },
              { label: "Modify Convergence", description: "Convergence criteria are not specific or testable enough" },
              { label: "Re-decompose", description: "Overall strategy or layering approach needs change" }
            ]
@@ -578,54 +609,20 @@ Bash(`mkdir -p ${sessionFolder}`)
    }
    ```
 
-3. **Finalize roadmap.md** (populate template from Output section with actual data)
+3. **Post-Completion Options**
-
-   ```javascript
-   const roadmapMd = `
-   # Requirement Roadmap
-
-   **Session**: ${sessionId}
-   **Requirement**: ${requirement}
-   **Strategy**: ${selectedMode}
-   **Generated**: ${getUtc8ISOString()}
-
-   ## Strategy Assessment
-   - Uncertainty level: ${strategy.uncertainty_level}
-   - Decomposition mode: ${selectedMode}
-
-   ## Roadmap
-   ${generateRoadmapTable(items, selectedMode)}
-
-   ## Convergence Criteria Details
-   ${items.map(item => generateConvergenceSection(item, selectedMode)).join('\n\n')}
-
-   ## Risk Items
-   ${generateRiskSection(items)}
-
-   ## Next Steps
-   Each layer/task can be executed independently:
-   \`\`\`bash
-   /workflow:lite-plan "${items[0].name || items[0].title}: ${items[0].scope}"
-   \`\`\`
-   Roadmap JSONL file: \`${sessionFolder}/roadmap.jsonl\`
-   `
-   Write(`${sessionFolder}/roadmap.md`, roadmapMd)
-   ```
-
-4. **Post-Completion Options**
 
    ```javascript
    if (!autoYes) {
      AskUserQuestion({
        questions: [{
-         question: "Roadmap generated. Next step:",
+         question: `路线图已生成，${issueIds.length} 个 issues 已创建。下一步：`,
          header: "Next Step",
          multiSelect: false,
          options: [
-           { label: "Execute First Layer", description: `Launch lite-plan to execute ${items[0].id}` },
+           { label: "Execute with team-planex", description: `启动 team-planex 执行全部 ${issueIds.length} 个 issues（${waves.length} 个波次）` },
-           { label: "Create Issue", description: "Create GitHub Issue based on roadmap" },
+           { label: "Execute first wave", description: `仅执行 Wave 1: ${waves[0].label}` },
-           { label: "Export Report", description: "Generate standalone shareable roadmap report" },
+           { label: "View issues", description: "查看已创建的 issue 详情" },
-           { label: "Done", description: "Save roadmap only, execute later" }
+           { label: "Done", description: "保存路线图，稍后执行" }
          ]
        }]
      })
@@ -634,16 +631,15 @@ Bash(`mkdir -p ${sessionFolder}`)
 
    | Selection | Action |
    |-----------|--------|
-   | Execute First Layer | `Skill(skill="workflow:lite-plan", args="${firstItem.scope}")` |
+   | Execute with team-planex | `Skill(skill="team-planex", args="--plan ${sessionFolder}/execution-plan.json")` |
-   | Create Issue | `Skill(skill="issue:new", args="...")` |
+   | Execute first wave | `Skill(skill="team-planex", args="${waves[0].issue_ids.join(' ')}")` |
-   | Export Report | Copy roadmap.md + roadmap.jsonl to user-specified location, or generate standalone HTML/Markdown report |
+   | View issues | Display issues summary table from issues.jsonl |
-   | Done | Display roadmap file paths, end |
+   | Done | Display file paths, end |
 
 **Success Criteria**:
 - User feedback processed (or skipped via autoYes)
-- roadmap.md finalized
-- roadmap.jsonl final version updated
 - Post-completion options provided
+- team-planex handoff available via execution-plan.json
 
 ## Error Handling
 
@@ -664,28 +660,8 @@ Bash(`mkdir -p ${sessionFolder}`)
 3. **Testable convergence**: criteria must be writable as assertions or manual steps; definition_of_done should be judgeable by non-technical stakeholders (see Convergence Criteria in JSONL Schema Design)
 4. **Agent-First for Exploration**: Delegate codebase exploration to cli-explore-agent, do not analyze directly in main flow
 5. **Incremental validation**: Use `--continue` to iterate on existing roadmaps
-6. **Independently executable**: Each JSONL record should be independently passable to lite-plan for execution
+6. **team-planex integration**: Issues created follow standard issues-jsonl-schema, directly consumable by team-planex via execution-plan.json
 
-## Usage Recommendations
-
-**Use `/workflow:req-plan-with-file` when:**
-- You need to decompose a large requirement into a progressively executable roadmap
-- Unsure where to start, need an MVP strategy
-- Need to generate a trackable task sequence for the team
-- Requirement involves multiple stages or iterations
-
-**Use `/workflow:lite-plan` when:**
-- You have a clear single task to execute
-- The requirement is already a layer/task from the roadmap
-- No layered planning needed
-
-**Use `/workflow:collaborative-plan-with-file` when:**
-- A single complex task needs multi-agent parallel planning
-- Need to analyze the same task from multiple domain perspectives
-
-**Use `/workflow:analyze-with-file` when:**
-- Need in-depth analysis of a technical problem
-- Not about planning execution, but understanding and discussion
 
 ---
 

.claude/skills/team-planex/roles/planner.md

@@ -98,12 +98,29 @@ const inputText = textMatch ? textMatch[1] : null
 const planMatch = (desc + ' ' + args).match(/--plan\s+(\S+)/)
 const planFile = planMatch ? planMatch[1] : null
 
+// 4) execution-plan.json 输入（来自 req-plan-with-file）
+let executionPlan = null
+
 // Determine input type
 let inputType = 'unknown'
 if (issueIds.length > 0) inputType = 'issue_ids'
 else if (inputText) inputType = 'text'
-else if (planFile) inputType = 'plan_file'
+else if (planFile) {
-else {
+  // Check if it's an execution-plan.json from req-plan-with-file
+  try {
+    const content = JSON.parse(Read(planFile))
+    if (content.waves && content.issue_ids && content.session_id?.startsWith('RPLAN-')) {
+      inputType = 'execution_plan'
+      executionPlan = content
+      issueIds = content.issue_ids
+    } else {
+      inputType = 'plan_file'
+    }
+  } catch (e) {
+    // Not JSON or parse error, fallback to original plan_file parsing
+    inputType = 'plan_file'
+  }
+} else {
   // 任务描述本身可能就是需求文本
   inputType = 'text_from_description'
 }
@@ -150,11 +167,68 @@ if (inputType === 'plan_file') {
 
 Issue IDs 已就绪，直接进入 solution 规划。
 
-#### Wave 规划（所有路径汇聚）
+#### Path D: execution-plan.json → 波次感知处理
-
-将 issueIds 按波次分组规划：
 
 ```javascript
+if (inputType === 'execution_plan') {
+  const projectRoot = Bash('cd . && pwd').trim()
+  const waves = executionPlan.waves
+
+  let waveNum = 0
+  for (const wave of waves) {
+    waveNum++
+    const waveIssues = wave.issue_ids
+
+    // Step 1: issue-plan-agent 生成 solutions
+    const planResult = Task({
+      subagent_type: "issue-plan-agent",
+      run_in_background: false,
+      description: `Plan solutions for wave ${waveNum}: ${wave.label}`,
+      prompt: `
+issue_ids: ${JSON.stringify(waveIssues)}
+project_root: "${projectRoot}"
+
+## Requirements
+- Generate solutions for each issue
+- Auto-bind single solutions
+- Issues come from req-plan decomposition (tags: req-plan)
+- Respect inter-issue dependencies: ${JSON.stringify(executionPlan.issue_dependencies)}
+`
+    })
+
+    // Step 2: issue-queue-agent 形成 queue
+    const queueResult = Task({
+      subagent_type: "issue-queue-agent",
+      run_in_background: false,
+      description: `Form queue for wave ${waveNum}: ${wave.label}`,
+      prompt: `
+issue_ids: ${JSON.stringify(waveIssues)}
+project_root: "${projectRoot}"
+
+## Requirements
+- Order solutions by dependency (DAG)
+- Detect conflicts between solutions
+- Respect wave dependencies: ${JSON.stringify(wave.depends_on_waves)}
+- Output execution queue
+`
+    })
+
+    // Step 3: → Phase 4 (Wave Dispatch) - create EXEC-* tasks
+    // Continue to next wave without waiting for executor
+  }
+  // After all waves → Phase 5 (Report + Finalize)
+}
+```
+
+**关键差异**: 波次分组来自 `executionPlan.waves`，而非固定 batch=5。Progressive 模式下 L0(Wave 1) → L1(Wave 2)，Direct 模式下 parallel_group 映射为 wave。
+
+#### Wave 规划（Path A/B/C 汇聚）
+
+将 issueIds 按波次分组规划（Path D 使用独立的波次逻辑，不走此路径）：
+
+```javascript
+if (inputType !== 'execution_plan') {
+  // Path A/B/C: 固定 batch=5 分组
   const projectRoot = Bash('cd . && pwd').trim()
 
 // 按批次分组（每 wave 最多 5 个 issues）
@@ -202,6 +276,7 @@ project_root: "${projectRoot}"
 
   // Step 3: → Phase 4 (Wave Dispatch)
 }
+} // end if (inputType !== 'execution_plan')
 ```
 
 ### Phase 4: Wave Dispatch
@@ -370,5 +445,7 @@ function parsePlanPhases(planContent) {
 | issue-plan-agent failure | Retry once, then report error and skip to next issue |
 | issue-queue-agent failure | Retry once, then create EXEC tasks without DAG ordering |
 | Plan file not found | Report error with expected path |
+| execution-plan.json parse failure | Fallback to plan_file parsing (Path B) |
+| execution-plan.json missing waves | Report error, suggest re-running req-plan |
 | Empty input (no issues, no text, no plan) | AskUserQuestion for clarification |
 | Wave partially failed | Report partial success, continue with successful issues |

.claude/skills/team-quality-assurance/SKILL.md

@@ -0,0 +1,427 @@
+---
+name: team-quality-assurance
+description: Unified team skill for quality assurance team. All roles invoke this skill with --role arg for role-specific execution. Triggers on "team quality-assurance", "team qa".
+allowed-tools: TeamCreate(*), TeamDelete(*), SendMessage(*), TaskCreate(*), TaskUpdate(*), TaskList(*), TaskGet(*), Task(*), AskUserQuestion(*), Read(*), Write(*), Edit(*), Bash(*), Glob(*), Grep(*)
+---
+
+# Team Quality Assurance
+
+质量保障团队技能。融合"问题发现"和"软件测试"两大能力域，形成"发现→策略→测试→分析"闭环。通过 Scout 多视角扫描、Generator-Executor 循环、共享缺陷模式数据库，实现渐进式质量保障。所有成员通过 `--role=xxx` 路由到角色执行逻辑。
+
+## Architecture Overview
+
+```
+┌──────────────────────────────────────────────────────────┐
+│  Skill(skill="team-quality-assurance", args="--role=xxx") │
+└────────────────────────┬─────────────────────────────────┘
+                         │ Role Router
+    ┌────────┬───────────┼───────────┬──────────┬──────────┐
+    ↓        ↓           ↓           ↓          ↓          ↓
+┌────────┐┌───────┐┌──────────┐┌─────────┐┌────────┐┌────────┐
+│coordi- ││scout  ││strategist││generator││executor││analyst │
+│nator   ││SCOUT-*││QASTRAT-* ││QAGEN-*  ││QARUN-* ││QAANA-* │
+│ roles/ ││ roles/││ roles/   ││ roles/  ││ roles/ ││ roles/ │
+└────────┘└───────┘└──────────┘└─────────┘└────────┘└────────┘
+```
+
+## Command Architecture
+
+```
+roles/
+├── coordinator/
+│   ├── role.md              # Pipeline 编排（模式选择、任务分发、监控）
+│   └── commands/
+│       ├── dispatch.md      # 任务链创建
+│       └── monitor.md       # 进度监控
+├── scout/
+│   ├── role.md              # 多视角问题扫描
+│   └── commands/
+│       └── scan.md          # 多视角 CLI Fan-out 扫描
+├── strategist/
+│   ├── role.md              # 测试策略制定
+│   └── commands/
+│       └── analyze-scope.md # 变更范围分析
+├── generator/
+│   ├── role.md              # 测试用例生成
+│   └── commands/
+│       └── generate-tests.md # 按层级生成测试代码
+├── executor/
+│   ├── role.md              # 测试执行与修复
+│   └── commands/
+│       └── run-fix-cycle.md # 迭代测试修复循环
+└── analyst/
+    ├── role.md              # 质量分析报告
+    └── commands/
+        └── quality-report.md # 缺陷模式 + 覆盖率分析
+```
+
+**设计原则**: role.md 保留 Phase 1（Task Discovery）和 Phase 5（Report）内联。Phase 2-4 根据复杂度决定内联或委派到 `commands/*.md`。
+
+## Role Router
+
+### Input Parsing
+
+Parse `$ARGUMENTS` to extract `--role`:
+
+```javascript
+const args = "$ARGUMENTS"
+const roleMatch = args.match(/--role[=\s]+(\w+)/)
+
+if (!roleMatch) {
+  throw new Error("Missing --role argument. Available roles: coordinator, scout, strategist, generator, executor, analyst")
+}
+
+const role = roleMatch[1]
+const teamName = args.match(/--team[=\s]+([\w-]+)/)?.[1] || "quality-assurance"
+```
+
+### Role Dispatch
+
+```javascript
+const VALID_ROLES = {
+  "coordinator": { file: "roles/coordinator/role.md", prefix: null },
+  "scout":       { file: "roles/scout/role.md",       prefix: "SCOUT" },
+  "strategist":  { file: "roles/strategist/role.md",  prefix: "QASTRAT" },
+  "generator":   { file: "roles/generator/role.md",   prefix: "QAGEN" },
+  "executor":    { file: "roles/executor/role.md",     prefix: "QARUN" },
+  "analyst":     { file: "roles/analyst/role.md",      prefix: "QAANA" }
+}
+
+if (!VALID_ROLES[role]) {
+  throw new Error(`Unknown role: ${role}. Available: ${Object.keys(VALID_ROLES).join(', ')}`)
+}
+
+// Read and execute role-specific logic
+Read(VALID_ROLES[role].file)
+// → Execute the 5-phase process defined in that file
+```
+
+### Available Roles
+
+| Role | Task Prefix | Responsibility | Role File |
+|------|-------------|----------------|-----------|
+| `coordinator` | N/A | QA pipeline 编排、模式选择、质量门控 | [roles/coordinator/role.md](roles/coordinator/role.md) |
+| `scout` | SCOUT-* | 多视角问题扫描、主动发现潜在缺陷 | [roles/scout/role.md](roles/scout/role.md) |
+| `strategist` | QASTRAT-* | 变更范围分析、测试层级选择、覆盖率目标 | [roles/strategist/role.md](roles/strategist/role.md) |
+| `generator` | QAGEN-* | 按层级生成测试用例（unit/integration/E2E） | [roles/generator/role.md](roles/generator/role.md) |
+| `executor` | QARUN-* | 执行测试、收集覆盖率、自动修复循环 | [roles/executor/role.md](roles/executor/role.md) |
+| `analyst` | QAANA-* | 缺陷模式分析、覆盖率差距、质量报告 | [roles/analyst/role.md](roles/analyst/role.md) |
+
+## Shared Infrastructure
+
+### Role Isolation Rules
+
+**核心原则**: 每个角色仅能执行自己职责范围内的工作。
+
+#### Output Tagging（强制）
+
+所有角色的输出必须带 `[role_name]` 标识前缀：
+
+```javascript
+SendMessage({ content: `## [${role}] ...`, summary: `[${role}] ...` })
+mcp__ccw-tools__team_msg({ summary: `[${role}] ...` })
+```
+
+#### Coordinator 隔离
+
+| 允许 | 禁止 |
+|------|------|
+| 需求澄清 (AskUserQuestion) | ❌ 直接编写测试 |
+| 创建任务链 (TaskCreate) | ❌ 直接执行测试或扫描 |
+| 模式选择 + 质量门控 | ❌ 直接分析覆盖率 |
+| 监控进度 (消息总线) | ❌ 绕过 worker 自行完成 |
+
+#### Worker 隔离
+
+| 允许 | 禁止 |
+|------|------|
+| 处理自己前缀的任务 | ❌ 处理其他角色前缀的任务 |
+| 读写 shared-memory.json (自己的字段) | ❌ 为其他角色创建任务 |
+| SendMessage 给 coordinator | ❌ 直接与其他 worker 通信 |
+
+### Team Configuration
+
+```javascript
+const TEAM_CONFIG = {
+  name: "quality-assurance",
+  sessionDir: ".workflow/.team/QA-{slug}-{date}/",
+  msgDir: ".workflow/.team-msg/quality-assurance/",
+  sharedMemory: "shared-memory.json",
+  testLayers: {
+    L1: { name: "Unit Tests", coverage_target: 80 },
+    L2: { name: "Integration Tests", coverage_target: 60 },
+    L3: { name: "E2E Tests", coverage_target: 40 }
+  },
+  scanPerspectives: ["bug", "security", "ux", "test-coverage", "code-quality"]
+}
+```
+
+### Shared Memory（核心创新）
+
+```javascript
+// 各角色读取共享记忆
+const memoryPath = `${sessionFolder}/shared-memory.json`
+let sharedMemory = {}
+try { sharedMemory = JSON.parse(Read(memoryPath)) } catch {}
+
+// 各角色写入自己负责的字段：
+// scout      → sharedMemory.discovered_issues
+// strategist → sharedMemory.test_strategy
+// generator  → sharedMemory.generated_tests
+// executor   → sharedMemory.execution_results
+// analyst    → sharedMemory.defect_patterns + quality_score + coverage_history
+Write(memoryPath, JSON.stringify(sharedMemory, null, 2))
+```
+
+### Message Bus (All Roles)
+
+```javascript
+mcp__ccw-tools__team_msg({
+  operation: "log",
+  team: teamName,
+  from: role,
+  to: "coordinator",
+  type: "<type>",
+  summary: `[${role}] <summary>`,
+  ref: "<file_path>"
+})
+```
+
+| Role | Types |
+|------|-------|
+| coordinator | `mode_selected`, `gc_loop_trigger`, `quality_gate`, `task_unblocked`, `error`, `shutdown` |
+| scout | `scan_ready`, `issues_found`, `error` |
+| strategist | `strategy_ready`, `error` |
+| generator | `tests_generated`, `tests_revised`, `error` |
+| executor | `tests_passed`, `tests_failed`, `coverage_report`, `error` |
+| analyst | `analysis_ready`, `quality_report`, `error` |
+
+### CLI 回退
+
+```javascript
+Bash(`ccw team log --team "${teamName}" --from "${role}" --to "coordinator" --type "<type>" --summary "<摘要>" --json`)
+```
+
+### Task Lifecycle (All Worker Roles)
+
+```javascript
+const tasks = TaskList()
+const myTasks = tasks.filter(t =>
+  t.subject.startsWith(`${VALID_ROLES[role].prefix}-`) &&
+  t.owner === role &&
+  t.status === 'pending' &&
+  t.blockedBy.length === 0
+)
+if (myTasks.length === 0) return
+const task = TaskGet({ taskId: myTasks[0].id })
+TaskUpdate({ taskId: task.id, status: 'in_progress' })
+
+// Phase 2-4: Role-specific
+// Phase 5: Report + Loop
+mcp__ccw-tools__team_msg({ operation: "log", team: teamName, from: role, to: "coordinator", type: "...", summary: `[${role}] ...` })
+SendMessage({ type: "message", recipient: "coordinator", content: `## [${role}] ...`, summary: `[${role}] ...` })
+TaskUpdate({ taskId: task.id, status: 'completed' })
+```
+
+## Three-Mode Pipeline Architecture
+
+```
+Discovery Mode (问题发现优先):
+  SCOUT-001(多视角扫描) → QASTRAT-001 → QAGEN-001 → QARUN-001 → QAANA-001
+
+Testing Mode (测试优先，跳过 scout):
+  QASTRAT-001(变更分析) → QAGEN-001(L1) → QARUN-001(L1) → QAGEN-002(L2) → QARUN-002(L2) → QAANA-001
+
+Full QA Mode (完整闭环):
+  SCOUT-001(扫描) → QASTRAT-001(策略) → [QAGEN-001(L1) + QAGEN-002(L2)](parallel) → [QARUN-001 + QARUN-002](parallel) → QAANA-001(分析) → SCOUT-002(回归扫描)
+```
+
+### Mode Auto-Detection
+
+```javascript
+function detectQAMode(args, taskDescription) {
+  if (/--mode[=\s]+(discovery|testing|full)/.test(args)) {
+    return args.match(/--mode[=\s]+(\w+)/)[1]
+  }
+  // 自动检测
+  if (/发现|扫描|scan|discover|issue|问题/.test(taskDescription)) return 'discovery'
+  if (/测试|test|覆盖|coverage|TDD/.test(taskDescription)) return 'testing'
+  return 'full'
+}
+```
+
+### Generator-Executor Loop (GC 循环)
+
+```
+QAGEN → QARUN → (if coverage < target) → QAGEN-fix → QARUN-2
+                  (if coverage >= target) → next layer or QAANA
+```
+
+## Unified Session Directory
+
+```
+.workflow/.team/QA-{slug}-{YYYY-MM-DD}/
+├── team-session.json
+├── shared-memory.json          # 发现的问题 / 测试策略 / 缺陷模式 / 覆盖率历史
+├── scan/                       # Scout output
+│   └── scan-results.json
+├── strategy/                   # Strategist output
+│   └── test-strategy.md
+├── tests/                      # Generator output
+│   ├── L1-unit/
+│   ├── L2-integration/
+│   └── L3-e2e/
+├── results/                    # Executor output
+│   ├── run-001.json
+│   └── coverage-001.json
+└── analysis/                   # Analyst output
+    └── quality-report.md
+```
+
+## Coordinator Spawn Template
+
+```javascript
+TeamCreate({ team_name: teamName })
+
+// Scout
+Task({
+  subagent_type: "general-purpose",
+  team_name: teamName,
+  name: "scout",
+  prompt: `你是 team "${teamName}" 的 SCOUT。
+
+当你收到 SCOUT-* 任务时，调用 Skill(skill="team-quality-assurance", args="--role=scout") 执行。
+
+当前需求: ${taskDescription}
+约束: ${constraints}
+
+## 角色准则（强制）
+- 你只能处理 SCOUT-* 前缀的任务，不得执行其他角色的工作
+- 所有输出（SendMessage、team_msg）必须带 [scout] 标识前缀
+- 仅与 coordinator 通信，不得直接联系其他 worker
+- 不得使用 TaskCreate 为其他角色创建任务
+
+## 消息总线（必须）
+每次 SendMessage 前，先调用 mcp__ccw-tools__team_msg 记录。
+
+工作流程:
+1. TaskList → 找到 SCOUT-* 任务
+2. Skill(skill="team-quality-assurance", args="--role=scout") 执行
+3. team_msg log + SendMessage 结果给 coordinator（带 [scout] 标识）
+4. TaskUpdate completed → 检查下一个任务`
+})
+
+// Strategist
+Task({
+  subagent_type: "general-purpose",
+  team_name: teamName,
+  name: "strategist",
+  prompt: `你是 team "${teamName}" 的 STRATEGIST。
+
+当你收到 QASTRAT-* 任务时，调用 Skill(skill="team-quality-assurance", args="--role=strategist") 执行。
+
+当前需求: ${taskDescription}
+约束: ${constraints}
+
+## 角色准则（强制）
+- 你只能处理 QASTRAT-* 前缀的任务
+- 所有输出必须带 [strategist] 标识前缀
+- 仅与 coordinator 通信
+
+## 消息总线（必须）
+每次 SendMessage 前，先调用 mcp__ccw-tools__team_msg 记录。
+
+工作流程:
+1. TaskList → 找到 QASTRAT-* 任务
+2. Skill(skill="team-quality-assurance", args="--role=strategist") 执行
+3. team_msg log + SendMessage 结果给 coordinator
+4. TaskUpdate completed → 检查下一个任务`
+})
+
+// Generator
+Task({
+  subagent_type: "general-purpose",
+  team_name: teamName,
+  name: "generator",
+  prompt: `你是 team "${teamName}" 的 GENERATOR。
+
+当你收到 QAGEN-* 任务时，调用 Skill(skill="team-quality-assurance", args="--role=generator") 执行。
+
+当前需求: ${taskDescription}
+
+## 角色准则（强制）
+- 你只能处理 QAGEN-* 前缀的任务
+- 所有输出必须带 [generator] 标识前缀
+
+## 消息总线（必须）
+每次 SendMessage 前，先调用 mcp__ccw-tools__team_msg 记录。
+
+工作流程:
+1. TaskList → 找到 QAGEN-* 任务
+2. Skill(skill="team-quality-assurance", args="--role=generator") 执行
+3. team_msg log + SendMessage
+4. TaskUpdate completed → 检查下一个任务`
+})
+
+// Executor
+Task({
+  subagent_type: "general-purpose",
+  team_name: teamName,
+  name: "executor",
+  prompt: `你是 team "${teamName}" 的 EXECUTOR。
+
+当你收到 QARUN-* 任务时，调用 Skill(skill="team-quality-assurance", args="--role=executor") 执行。
+
+当前需求: ${taskDescription}
+
+## 角色准则（强制）
+- 你只能处理 QARUN-* 前缀的任务
+- 所有输出必须带 [executor] 标识前缀
+
+## 消息总线（必须）
+每次 SendMessage 前，先调用 mcp__ccw-tools__team_msg 记录。
+
+工作流程:
+1. TaskList → 找到 QARUN-* 任务
+2. Skill(skill="team-quality-assurance", args="--role=executor") 执行
+3. team_msg log + SendMessage
+4. TaskUpdate completed → 检查下一个任务`
+})
+
+// Analyst
+Task({
+  subagent_type: "general-purpose",
+  team_name: teamName,
+  name: "analyst",
+  prompt: `你是 team "${teamName}" 的 ANALYST。
+
+当你收到 QAANA-* 任务时，调用 Skill(skill="team-quality-assurance", args="--role=analyst") 执行。
+
+当前需求: ${taskDescription}
+
+## 角色准则（强制）
+- 你只能处理 QAANA-* 前缀的任务
+- 所有输出必须带 [analyst] 标识前缀
+
+## 消息总线（必须）
+每次 SendMessage 前，先调用 mcp__ccw-tools__team_msg 记录。
+
+工作流程:
+1. TaskList → 找到 QAANA-* 任务
+2. Skill(skill="team-quality-assurance", args="--role=analyst") 执行
+3. team_msg log + SendMessage
+4. TaskUpdate completed → 检查下一个任务`
+})
+```
+
+## Error Handling
+
+| Scenario | Resolution |
+|----------|------------|
+| Unknown --role value | Error with available role list |
+| Missing --role arg | Error with usage hint |
+| Role file not found | Error with expected path (roles/{name}/role.md) |
+| Task prefix conflict | Log warning, proceed |
+| Coverage never reaches target | After 3 GC loops, accept current with warning |
+| Scout finds no issues | Report clean scan, skip to testing mode |
+| Test environment broken | Notify user, suggest manual fix |

.claude/skills/team-quality-assurance/roles/analyst/commands/quality-report.md

@@ -0,0 +1,360 @@
+# Command: quality-report
+
+> 缺陷模式分析 + 覆盖率分析 + 综合质量报告。多维度分析 QA 数据，生成质量评分和改进建议。
+
+## When to Use
+
+- Phase 3 of Analyst
+- 测试执行完成，需要分析结果
+- 需要识别缺陷模式和覆盖率趋势
+
+**Trigger conditions**:
+- QAANA-* 任务进入执行阶段
+- 所有 QARUN 任务已完成
+- Coordinator 请求质量报告
+
+## Strategy
+
+### Delegation Mode
+
+**Mode**: CLI Fan-out（深度分析）/ Direct（基础分析）
+**CLI Tool**: `gemini` (primary)
+**CLI Mode**: `analysis`
+
+### Decision Logic
+
+```javascript
+const dataPoints = discoveredIssues.length + Object.keys(executionResults).length
+if (dataPoints <= 5) {
+  // 基础内联分析
+  mode = 'direct'
+} else {
+  // CLI 辅助深度分析
+  mode = 'cli-assisted'
+}
+```
+
+## Execution Steps
+
+### Step 1: Context Preparation
+
+```javascript
+// 从 shared memory 加载所有 QA 数据
+const discoveredIssues = sharedMemory.discovered_issues || []
+const strategy = sharedMemory.test_strategy || {}
+const generatedTests = sharedMemory.generated_tests || {}
+const executionResults = sharedMemory.execution_results || {}
+const historicalPatterns = sharedMemory.defect_patterns || []
+const coverageHistory = sharedMemory.coverage_history || []
+
+// 读取覆盖率详细数据
+let coverageData = null
+try {
+  coverageData = JSON.parse(Read('coverage/coverage-summary.json'))
+} catch {}
+
+// 读取各层级执行结果
+const layerResults = {}
+try {
+  const resultFiles = Glob(`${sessionFolder}/results/run-*.json`)
+  for (const f of resultFiles) {
+    const data = JSON.parse(Read(f))
+    layerResults[data.layer] = data
+  }
+} catch {}
+```
+
+### Step 2: Execute Strategy
+
+```javascript
+if (mode === 'direct') {
+  // 基础内联分析
+  analysis = performDirectAnalysis()
+} else {
+  // CLI 辅助深度分析
+  const analysisContext = JSON.stringify({
+    issues: discoveredIssues.slice(0, 20),
+    execution: layerResults,
+    coverage: coverageData?.total || {},
+    strategy: { layers: strategy.layers?.map(l => ({ level: l.level, target: l.target_coverage })) }
+  }, null, 2)
+
+  Bash(`ccw cli -p "PURPOSE: Perform deep quality analysis on QA results to identify defect patterns, coverage trends, and improvement opportunities
+TASK: • Classify defects by root cause pattern (logic errors, integration issues, missing validation, etc.) • Identify files with highest defect density • Analyze coverage gaps vs risk levels • Compare actual coverage to targets • Generate actionable improvement recommendations
+MODE: analysis
+CONTEXT: @${sessionFolder}/shared-memory.json @${sessionFolder}/results/**/*
+EXPECTED: Structured analysis with: defect pattern taxonomy, risk-coverage matrix, quality score rationale, top 5 improvement recommendations with expected impact
+CONSTRAINTS: Be data-driven, avoid speculation without evidence" --tool gemini --mode analysis --rule analysis-analyze-code-patterns`, {
+    run_in_background: true
+  })
+  // 等待 CLI 完成
+}
+
+// ===== 分析维度 =====
+
+// 1. 缺陷模式分析
+function analyzeDefectPatterns(issues, results) {
+  const byType = {}
+  for (const issue of issues) {
+    const type = issue.perspective || 'unknown'
+    if (!byType[type]) byType[type] = []
+    byType[type].push(issue)
+  }
+
+  // 识别重复模式
+  const patterns = []
+  for (const [type, typeIssues] of Object.entries(byType)) {
+    if (typeIssues.length >= 2) {
+      // 分析共同特征
+      const commonFiles = findCommonPatterns(typeIssues.map(i => i.file))
+      patterns.push({
+        type,
+        count: typeIssues.length,
+        files: [...new Set(typeIssues.map(i => i.file))],
+        common_pattern: commonFiles,
+        description: `${type} 类问题在 ${typeIssues.length} 处重复出现`,
+        recommendation: generateRecommendation(type, typeIssues)
+      })
+    }
+  }
+
+  return { by_type: byType, patterns, total: issues.length }
+}
+
+// 2. 覆盖率差距分析
+function analyzeCoverageGaps(coverage, strategy) {
+  if (!coverage) return { status: 'no_data', gaps: [] }
+
+  const totalCoverage = coverage.total?.lines?.pct || 0
+  const gaps = []
+
+  for (const layer of (strategy.layers || [])) {
+    if (totalCoverage < layer.target_coverage) {
+      gaps.push({
+        layer: layer.level,
+        target: layer.target_coverage,
+        actual: totalCoverage,
+        gap: Math.round(layer.target_coverage - totalCoverage),
+        severity: (layer.target_coverage - totalCoverage) > 20 ? 'high' : 'medium'
+      })
+    }
+  }
+
+  // 按文件分析覆盖率
+  const fileGaps = []
+  if (coverage && typeof coverage === 'object') {
+    for (const [file, data] of Object.entries(coverage)) {
+      if (file === 'total') continue
+      const linePct = data?.lines?.pct || 0
+      if (linePct < 50) {
+        fileGaps.push({ file, coverage: linePct, severity: linePct < 20 ? 'critical' : 'high' })
+      }
+    }
+  }
+
+  return { total_coverage: totalCoverage, gaps, file_gaps: fileGaps.slice(0, 10) }
+}
+
+// 3. 测试有效性分析
+function analyzeTestEffectiveness(generated, results) {
+  const effectiveness = {}
+  for (const [layer, data] of Object.entries(generated)) {
+    const result = results[layer] || {}
+    effectiveness[layer] = {
+      files_generated: data.files?.length || 0,
+      pass_rate: result.pass_rate || 0,
+      iterations_needed: result.iterations || 0,
+      coverage_achieved: result.coverage || 0,
+      effective: (result.pass_rate || 0) >= 95 && (result.iterations || 0) <= 2
+    }
+  }
+  return effectiveness
+}
+
+// 4. 质量趋势分析
+function analyzeQualityTrend(history) {
+  if (history.length < 2) return { trend: 'insufficient_data', confidence: 'low' }
+
+  const latest = history[history.length - 1]
+  const previous = history[history.length - 2]
+  const delta = (latest?.coverage || 0) - (previous?.coverage || 0)
+
+  return {
+    trend: delta > 5 ? 'improving' : delta < -5 ? 'declining' : 'stable',
+    delta: Math.round(delta * 10) / 10,
+    data_points: history.length,
+    confidence: history.length >= 5 ? 'high' : history.length >= 3 ? 'medium' : 'low'
+  }
+}
+
+// 5. 综合质量评分
+function calculateQualityScore(analysis) {
+  let score = 100
+
+  // 扣分: 安全问题
+  const securityIssues = (analysis.defect_patterns.by_type?.security || []).length
+  score -= securityIssues * 10
+
+  // 扣分: Bug
+  const bugIssues = (analysis.defect_patterns.by_type?.bug || []).length
+  score -= bugIssues * 5
+
+  // 扣分: 覆盖率差距
+  for (const gap of (analysis.coverage_gaps.gaps || [])) {
+    score -= gap.gap * 0.5
+  }
+
+  // 扣分: 测试失败
+  for (const [layer, eff] of Object.entries(analysis.test_effectiveness)) {
+    if (eff.pass_rate < 100) score -= (100 - eff.pass_rate) * 0.3
+  }
+
+  // 加分: 有效测试层
+  const effectiveLayers = Object.values(analysis.test_effectiveness)
+    .filter(e => e.effective).length
+  score += effectiveLayers * 5
+
+  // 加分: 改善趋势
+  if (analysis.quality_trend.trend === 'improving') score += 3
+
+  return Math.max(0, Math.min(100, Math.round(score)))
+}
+
+// 辅助函数
+function findCommonPatterns(files) {
+  const dirs = files.map(f => f.split('/').slice(0, -1).join('/'))
+  const commonDir = dirs.reduce((a, b) => {
+    const partsA = a.split('/')
+    const partsB = b.split('/')
+    const common = []
+    for (let i = 0; i < Math.min(partsA.length, partsB.length); i++) {
+      if (partsA[i] === partsB[i]) common.push(partsA[i])
+      else break
+    }
+    return common.join('/')
+  })
+  return commonDir || 'scattered'
+}
+
+function generateRecommendation(type, issues) {
+  const recommendations = {
+    'security': '加强输入验证和安全审计，考虑引入 SAST 工具',
+    'bug': '改进错误处理和边界检查，增加防御性编程',
+    'test-coverage': '补充缺失的测试用例，聚焦未覆盖的分支',
+    'code-quality': '重构复杂函数，消除代码重复',
+    'ux': '统一错误提示和加载状态处理'
+  }
+  return recommendations[type] || '进一步分析并制定改进计划'
+}
+```
+
+### Step 3: Result Processing
+
+```javascript
+// 组装分析结果
+const analysis = {
+  defect_patterns: analyzeDefectPatterns(discoveredIssues, layerResults),
+  coverage_gaps: analyzeCoverageGaps(coverageData, strategy),
+  test_effectiveness: analyzeTestEffectiveness(generatedTests, layerResults),
+  quality_trend: analyzeQualityTrend(coverageHistory),
+  quality_score: 0
+}
+
+analysis.quality_score = calculateQualityScore(analysis)
+
+// 生成报告文件
+const reportContent = generateReportMarkdown(analysis)
+Bash(`mkdir -p "${sessionFolder}/analysis"`)
+Write(`${sessionFolder}/analysis/quality-report.md`, reportContent)
+
+// 更新 shared memory
+sharedMemory.defect_patterns = analysis.defect_patterns.patterns
+sharedMemory.quality_score = analysis.quality_score
+sharedMemory.coverage_history = sharedMemory.coverage_history || []
+sharedMemory.coverage_history.push({
+  date: new Date().toISOString(),
+  coverage: analysis.coverage_gaps.total_coverage || 0,
+  quality_score: analysis.quality_score,
+  issues: analysis.defect_patterns.total
+})
+Write(`${sessionFolder}/shared-memory.json`, JSON.stringify(sharedMemory, null, 2))
+
+function generateReportMarkdown(analysis) {
+  return `# Quality Assurance Report
+
+## Quality Score: ${analysis.quality_score}/100
+
+---
+
+## 1. Defect Pattern Analysis
+- Total issues found: ${analysis.defect_patterns.total}
+- Recurring patterns: ${analysis.defect_patterns.patterns.length}
+
+${analysis.defect_patterns.patterns.map(p =>
+  `### Pattern: ${p.type} (${p.count} occurrences)
+- Files: ${p.files.join(', ')}
+- Common location: ${p.common_pattern}
+- Recommendation: ${p.recommendation}`
+).join('\n\n')}
+
+## 2. Coverage Analysis
+- Overall coverage: ${analysis.coverage_gaps.total_coverage || 'N/A'}%
+- Coverage gaps: ${(analysis.coverage_gaps.gaps || []).length}
+
+${(analysis.coverage_gaps.gaps || []).map(g =>
+  `- **${g.layer}**: target ${g.target}% vs actual ${g.actual}% (gap: ${g.gap}%, severity: ${g.severity})`
+).join('\n')}
+
+### Low Coverage Files
+${(analysis.coverage_gaps.file_gaps || []).map(f =>
+  `- ${f.file}: ${f.coverage}% [${f.severity}]`
+).join('\n')}
+
+## 3. Test Effectiveness
+${Object.entries(analysis.test_effectiveness).map(([layer, data]) =>
+  `- **${layer}**: ${data.files_generated} files, pass rate ${data.pass_rate}%, ${data.iterations_needed} fix iterations, ${data.effective ? 'EFFECTIVE' : 'NEEDS IMPROVEMENT'}`
+).join('\n')}
+
+## 4. Quality Trend
+- Trend: ${analysis.quality_trend.trend}
+${analysis.quality_trend.delta !== undefined ? `- Coverage delta: ${analysis.quality_trend.delta > 0 ? '+' : ''}${analysis.quality_trend.delta}%` : ''}
+- Confidence: ${analysis.quality_trend.confidence}
+
+## 5. Recommendations
+${analysis.quality_score >= 80 ? '- Quality is **GOOD**. Maintain current testing practices.' : ''}
+${analysis.quality_score >= 60 && analysis.quality_score < 80 ? '- Quality needs **IMPROVEMENT**. Focus on coverage gaps and recurring patterns.' : ''}
+${analysis.quality_score < 60 ? '- Quality is **CONCERNING**. Recommend comprehensive review and testing effort.' : ''}
+${analysis.defect_patterns.patterns.map(p => `- [${p.type}] ${p.recommendation}`).join('\n')}
+${(analysis.coverage_gaps.gaps || []).map(g => `- Close ${g.layer} coverage gap: +${g.gap}% needed`).join('\n')}
+`
+}
+```
+
+## Output Format
+
+```
+## Quality Analysis Results
+
+### Quality Score: [score]/100
+
+### Dimensions
+1. Defect Patterns: [count] recurring
+2. Coverage Gaps: [count] layers below target
+3. Test Effectiveness: [effective_count]/[total_layers] effective
+4. Quality Trend: [improving|stable|declining]
+
+### Report Location
+[session]/analysis/quality-report.md
+```
+
+## Error Handling
+
+| Scenario | Resolution |
+|----------|------------|
+| No coverage data available | Score based on other dimensions only |
+| No execution results | Analyze only scout findings and strategy |
+| Shared memory empty/corrupt | Generate minimal report with available data |
+| CLI analysis fails | Fall back to direct inline analysis |
+| Insufficient history for trend | Report 'insufficient_data', skip trend scoring |
+| Agent/CLI failure | Retry once, then fallback to inline execution |
+| Timeout (>5 min) | Report partial results, notify coordinator |

.claude/skills/team-quality-assurance/roles/analyst/role.md

@@ -0,0 +1,326 @@
+# Role: analyst
+
+质量分析师。分析缺陷模式、覆盖率差距、测试有效性，生成综合质量报告。维护缺陷模式数据库，为 scout 和 strategist 提供反馈数据。
+
+## Role Identity
+
+- **Name**: `analyst`
+- **Task Prefix**: `QAANA-*`
+- **Responsibility**: Read-only analysis（质量分析）
+- **Communication**: SendMessage to coordinator only
+- **Output Tag**: `[analyst]`
+
+## Role Boundaries
+
+### MUST
+
+- 仅处理 `QAANA-*` 前缀的任务
+- 所有输出必须带 `[analyst]` 标识
+- 基于数据生成分析报告
+- 更新 shared memory 中的缺陷模式和质量分数
+
+### MUST NOT
+
+- ❌ 修改源代码或测试代码
+- ❌ 执行测试
+- ❌ 为其他角色创建任务
+- ❌ 直接与其他 worker 通信
+
+## Message Types
+
+| Type | Direction | Trigger | Description |
+|------|-----------|---------|-------------|
+| `analysis_ready` | analyst → coordinator | 分析完成 | 包含质量评分 |
+| `quality_report` | analyst → coordinator | 报告生成 | 包含详细分析 |
+| `error` | analyst → coordinator | 分析失败 | 阻塞性错误 |
+
+## Toolbox
+
+### Available Commands
+
+| Command | File | Phase | Description |
+|---------|------|-------|-------------|
+| `quality-report` | [commands/quality-report.md](commands/quality-report.md) | Phase 3 | 缺陷模式分析 + 覆盖率分析 |
+
+### CLI Capabilities
+
+| CLI Tool | Mode | Used By | Purpose |
+|----------|------|---------|---------|
+| `gemini` | analysis | quality-report.md | 缺陷模式识别和趋势分析 |
+
+## Execution (5-Phase)
+
+### Phase 1: Task Discovery
+
+```javascript
+const tasks = TaskList()
+const myTasks = tasks.filter(t =>
+  t.subject.startsWith('QAANA-') &&
+  t.owner === 'analyst' &&
+  t.status === 'pending' &&
+  t.blockedBy.length === 0
+)
+
+if (myTasks.length === 0) return
+const task = TaskGet({ taskId: myTasks[0].id })
+TaskUpdate({ taskId: task.id, status: 'in_progress' })
+```
+
+### Phase 2: Context Loading
+
+```javascript
+// 读取 shared memory 获取所有数据
+const sessionFolder = task.description.match(/session:\s*(.+)/)?.[1] || '.'
+let sharedMemory = {}
+try { sharedMemory = JSON.parse(Read(`${sessionFolder}/shared-memory.json`)) } catch {}
+
+const discoveredIssues = sharedMemory.discovered_issues || []
+const strategy = sharedMemory.test_strategy || {}
+const generatedTests = sharedMemory.generated_tests || {}
+const executionResults = sharedMemory.execution_results || {}
+const historicalPatterns = sharedMemory.defect_patterns || []
+
+// 读取覆盖率数据
+let coverageData = null
+try {
+  coverageData = JSON.parse(Read('coverage/coverage-summary.json'))
+} catch {}
+
+// 读取测试执行日志
+const runResults = {}
+try {
+  const resultFiles = Glob(`${sessionFolder}/results/run-*.json`)
+  for (const f of resultFiles) {
+    const data = JSON.parse(Read(f))
+    runResults[data.layer] = data
+  }
+} catch {}
+```
+
+### Phase 3: Multi-Dimensional Analysis
+
+```javascript
+// Read commands/quality-report.md for full implementation
+Read("commands/quality-report.md")
+```
+
+**分析维度**:
+
+```javascript
+const analysis = {
+  // 1. 缺陷模式分析
+  defect_patterns: analyzeDefectPatterns(discoveredIssues, executionResults),
+
+  // 2. 覆盖率差距分析
+  coverage_gaps: analyzeCoverageGaps(coverageData, strategy),
+
+  // 3. 测试有效性分析
+  test_effectiveness: analyzeTestEffectiveness(generatedTests, executionResults),
+
+  // 4. 质量趋势
+  quality_trend: analyzeQualityTrend(sharedMemory.coverage_history || []),
+
+  // 5. 综合质量评分
+  quality_score: 0
+}
+
+function analyzeDefectPatterns(issues, results) {
+  // 按类型分组
+  const byType = {}
+  for (const issue of issues) {
+    const type = issue.perspective || 'unknown'
+    if (!byType[type]) byType[type] = []
+    byType[type].push(issue)
+  }
+
+  // 识别重复模式
+  const patterns = []
+  for (const [type, typeIssues] of Object.entries(byType)) {
+    if (typeIssues.length >= 2) {
+      patterns.push({
+        type,
+        count: typeIssues.length,
+        files: [...new Set(typeIssues.map(i => i.file))],
+        description: `${type} 类问题在 ${typeIssues.length} 处重复出现`
+      })
+    }
+  }
+
+  return { by_type: byType, patterns, total: issues.length }
+}
+
+function analyzeCoverageGaps(coverage, strategy) {
+  if (!coverage) return { status: 'no_data' }
+
+  const gaps = []
+  const totalCoverage = coverage.total?.lines?.pct || 0
+
+  // 对比策略目标
+  for (const layer of (strategy.layers || [])) {
+    const actual = totalCoverage
+    if (actual < layer.target_coverage) {
+      gaps.push({
+        layer: layer.level,
+        target: layer.target_coverage,
+        actual,
+        gap: layer.target_coverage - actual,
+        files_below_target: [] // 可以进一步分析
+      })
+    }
+  }
+
+  return { total_coverage: totalCoverage, gaps }
+}
+
+function analyzeTestEffectiveness(generated, results) {
+  const effectiveness = {}
+  for (const [layer, data] of Object.entries(generated)) {
+    const result = results[layer] || {}
+    effectiveness[layer] = {
+      files_generated: data.files?.length || 0,
+      pass_rate: result.pass_rate || 0,
+      iterations_needed: result.iterations || 0,
+      effective: (result.pass_rate || 0) >= 95
+    }
+  }
+  return effectiveness
+}
+
+function analyzeQualityTrend(history) {
+  if (history.length < 2) return { trend: 'insufficient_data' }
+  const latest = history[history.length - 1]
+  const previous = history[history.length - 2]
+  const delta = (latest?.coverage || 0) - (previous?.coverage || 0)
+  return {
+    trend: delta > 0 ? 'improving' : delta < 0 ? 'declining' : 'stable',
+    delta,
+    data_points: history.length
+  }
+}
+
+// 综合质量评分 (0-100)
+function calculateQualityScore(analysis) {
+  let score = 100
+
+  // 扣分项
+  const criticalIssues = (analysis.defect_patterns.by_type?.security || []).length
+  score -= criticalIssues * 10
+
+  const highIssues = (analysis.defect_patterns.by_type?.bug || []).length
+  score -= highIssues * 5
+
+  // 覆盖率不达标扣分
+  for (const gap of (analysis.coverage_gaps.gaps || [])) {
+    score -= gap.gap * 0.5
+  }
+
+  // 测试有效性加分
+  const effectiveLayers = Object.values(analysis.test_effectiveness)
+    .filter(e => e.effective).length
+  score += effectiveLayers * 5
+
+  return Math.max(0, Math.min(100, Math.round(score)))
+}
+
+analysis.quality_score = calculateQualityScore(analysis)
+```
+
+### Phase 4: Report Generation
+
+```javascript
+// 生成质量报告
+const reportContent = `# Quality Assurance Report
+
+## Quality Score: ${analysis.quality_score}/100
+
+## 1. Defect Pattern Analysis
+- Total issues found: ${analysis.defect_patterns.total}
+- Recurring patterns: ${analysis.defect_patterns.patterns.length}
+${analysis.defect_patterns.patterns.map(p => `  - **${p.type}**: ${p.count} occurrences across ${p.files.length} files`).join('\n')}
+
+## 2. Coverage Analysis
+- Overall coverage: ${analysis.coverage_gaps.total_coverage || 'N/A'}%
+- Coverage gaps: ${(analysis.coverage_gaps.gaps || []).length}
+${(analysis.coverage_gaps.gaps || []).map(g => `  - **${g.layer}**: target ${g.target}% vs actual ${g.actual}% (gap: ${g.gap}%)`).join('\n')}
+
+## 3. Test Effectiveness
+${Object.entries(analysis.test_effectiveness).map(([layer, data]) =>
+  `- **${layer}**: ${data.files_generated} files, pass rate ${data.pass_rate}%, ${data.iterations_needed} fix iterations`
+).join('\n')}
+
+## 4. Quality Trend
+- Trend: ${analysis.quality_trend.trend}
+${analysis.quality_trend.delta !== undefined ? `- Coverage change: ${analysis.quality_trend.delta > 0 ? '+' : ''}${analysis.quality_trend.delta}%` : ''}
+
+## 5. Recommendations
+${analysis.quality_score >= 80 ? '- Quality is GOOD. Continue with current testing strategy.' : ''}
+${analysis.quality_score >= 60 && analysis.quality_score < 80 ? '- Quality needs IMPROVEMENT. Focus on coverage gaps and recurring patterns.' : ''}
+${analysis.quality_score < 60 ? '- Quality is CONCERNING. Recommend deep scan and comprehensive test generation.' : ''}
+${analysis.defect_patterns.patterns.length > 0 ? `- Address ${analysis.defect_patterns.patterns.length} recurring defect patterns` : ''}
+${(analysis.coverage_gaps.gaps || []).length > 0 ? `- Close ${analysis.coverage_gaps.gaps.length} coverage gaps` : ''}
+`
+
+Bash(`mkdir -p "${sessionFolder}/analysis"`)
+Write(`${sessionFolder}/analysis/quality-report.md`, reportContent)
+
+// 更新 shared memory
+sharedMemory.defect_patterns = analysis.defect_patterns.patterns
+sharedMemory.quality_score = analysis.quality_score
+sharedMemory.coverage_history = sharedMemory.coverage_history || []
+sharedMemory.coverage_history.push({
+  date: new Date().toISOString(),
+  coverage: analysis.coverage_gaps.total_coverage || 0,
+  quality_score: analysis.quality_score,
+  issues: analysis.defect_patterns.total
+})
+Write(`${sessionFolder}/shared-memory.json`, JSON.stringify(sharedMemory, null, 2))
+```
+
+### Phase 5: Report to Coordinator
+
+```javascript
+mcp__ccw-tools__team_msg({
+  operation: "log",
+  team: teamName,
+  from: "analyst",
+  to: "coordinator",
+  type: "quality_report",
+  summary: `[analyst] 质量评分: ${analysis.quality_score}/100, 缺陷模式: ${analysis.defect_patterns.patterns.length}, 覆盖率: ${analysis.coverage_gaps.total_coverage || 'N/A'}%`,
+  ref: `${sessionFolder}/analysis/quality-report.md`
+})
+
+SendMessage({
+  type: "message",
+  recipient: "coordinator",
+  content: `## [analyst] Quality Analysis Results
+
+**Task**: ${task.subject}
+**Quality Score**: ${analysis.quality_score}/100
+**Defect Patterns**: ${analysis.defect_patterns.patterns.length} recurring
+**Coverage**: ${analysis.coverage_gaps.total_coverage || 'N/A'}%
+**Trend**: ${analysis.quality_trend.trend}
+
+### Report
+${sessionFolder}/analysis/quality-report.md`,
+  summary: `[analyst] QAANA complete: score ${analysis.quality_score}/100`
+})
+
+TaskUpdate({ taskId: task.id, status: 'completed' })
+
+const nextTasks = TaskList().filter(t =>
+  t.subject.startsWith('QAANA-') && t.owner === 'analyst' &&
+  t.status === 'pending' && t.blockedBy.length === 0
+)
+if (nextTasks.length > 0) { /* back to Phase 1 */ }
+```
+
+## Error Handling
+
+| Scenario | Resolution |
+|----------|------------|
+| No QAANA-* tasks available | Idle, wait for coordinator |
+| Coverage data not found | Report quality score based on other dimensions |
+| Shared memory empty | Generate minimal report with available data |
+| No execution results | Analyze only scout findings and strategy coverage |
+| CLI analysis fails | Fall back to inline pattern analysis |
+| Critical issue beyond scope | SendMessage error to coordinator |

.claude/skills/team-quality-assurance/roles/coordinator/commands/dispatch.md

@@ -0,0 +1,167 @@
+# Command: dispatch
+
+> 任务链创建与依赖管理。根据 QA 模式创建 pipeline 任务链并分配给 worker 角色。
+
+## When to Use
+
+- Phase 3 of Coordinator
+- QA 模式已确定，需要创建任务链
+- 团队已创建，worker 已 spawn
+
+**Trigger conditions**:
+- Coordinator Phase 2 完成后
+- 模式切换需要重建任务链
+- GC 循环需要创建修复任务
+
+## Strategy
+
+### Delegation Mode
+
+**Mode**: Direct（coordinator 直接操作 TaskCreate/TaskUpdate）
+
+### Decision Logic
+
+```javascript
+// 根据 qaMode 选择 pipeline
+function buildPipeline(qaMode, sessionFolder, taskDescription) {
+  const pipelines = {
+    'discovery': [
+      { prefix: 'SCOUT', owner: 'scout', desc: '多视角问题扫描', blockedBy: [] },
+      { prefix: 'QASTRAT', owner: 'strategist', desc: '测试策略制定', blockedBy: ['SCOUT'] },
+      { prefix: 'QAGEN', owner: 'generator', desc: '测试代码生成 (L1)', meta: 'layer: L1', blockedBy: ['QASTRAT'] },
+      { prefix: 'QARUN', owner: 'executor', desc: '测试执行 (L1)', meta: 'layer: L1', blockedBy: ['QAGEN'] },
+      { prefix: 'QAANA', owner: 'analyst', desc: '质量分析报告', blockedBy: ['QARUN'] }
+    ],
+    'testing': [
+      { prefix: 'QASTRAT', owner: 'strategist', desc: '测试策略制定', blockedBy: [] },
+      { prefix: 'QAGEN-L1', owner: 'generator', desc: '测试代码生成 (L1)', meta: 'layer: L1', blockedBy: ['QASTRAT'] },
+      { prefix: 'QARUN-L1', owner: 'executor', desc: '测试执行 (L1)', meta: 'layer: L1', blockedBy: ['QAGEN-L1'] },
+      { prefix: 'QAGEN-L2', owner: 'generator', desc: '测试代码生成 (L2)', meta: 'layer: L2', blockedBy: ['QARUN-L1'] },
+      { prefix: 'QARUN-L2', owner: 'executor', desc: '测试执行 (L2)', meta: 'layer: L2', blockedBy: ['QAGEN-L2'] },
+      { prefix: 'QAANA', owner: 'analyst', desc: '质量分析报告', blockedBy: ['QARUN-L2'] }
+    ],
+    'full': [
+      { prefix: 'SCOUT', owner: 'scout', desc: '多视角问题扫描', blockedBy: [] },
+      { prefix: 'QASTRAT', owner: 'strategist', desc: '测试策略制定', blockedBy: ['SCOUT'] },
+      { prefix: 'QAGEN-L1', owner: 'generator', desc: '测试代码生成 (L1)', meta: 'layer: L1', blockedBy: ['QASTRAT'] },
+      { prefix: 'QAGEN-L2', owner: 'generator', desc: '测试代码生成 (L2)', meta: 'layer: L2', blockedBy: ['QASTRAT'] },
+      { prefix: 'QARUN-L1', owner: 'executor', desc: '测试执行 (L1)', meta: 'layer: L1', blockedBy: ['QAGEN-L1'] },
+      { prefix: 'QARUN-L2', owner: 'executor', desc: '测试执行 (L2)', meta: 'layer: L2', blockedBy: ['QAGEN-L2'] },
+      { prefix: 'QAANA', owner: 'analyst', desc: '质量分析报告', blockedBy: ['QARUN-L1', 'QARUN-L2'] },
+      { prefix: 'SCOUT-REG', owner: 'scout', desc: '回归扫描', blockedBy: ['QAANA'] }
+    ]
+  }
+  return pipelines[qaMode] || pipelines['discovery']
+}
+```
+
+## Execution Steps
+
+### Step 1: Context Preparation
+
+```javascript
+const pipeline = buildPipeline(qaMode, sessionFolder, taskDescription)
+```
+
+### Step 2: Execute Strategy
+
+```javascript
+const taskIds = {}
+
+for (const stage of pipeline) {
+  // 构建任务描述（包含 session 和层级信息）
+  const fullDesc = [
+    stage.desc,
+    `\nsession: ${sessionFolder}`,
+    stage.meta ? `\n${stage.meta}` : '',
+    `\n\n目标: ${taskDescription}`
+  ].join('')
+
+  // 创建任务
+  TaskCreate({
+    subject: `${stage.prefix}-001: ${stage.desc}`,
+    description: fullDesc,
+    activeForm: `${stage.desc}进行中`
+  })
+
+  // 记录任务 ID（假设 TaskCreate 返回 ID）
+  const allTasks = TaskList()
+  const newTask = allTasks.find(t => t.subject.startsWith(`${stage.prefix}-001`))
+  taskIds[stage.prefix] = newTask.id
+
+  // 设置 owner 和依赖
+  const blockedByIds = stage.blockedBy
+    .map(dep => taskIds[dep])
+    .filter(Boolean)
+
+  TaskUpdate({
+    taskId: newTask.id,
+    owner: stage.owner,
+    addBlockedBy: blockedByIds
+  })
+}
+```
+
+### Step 3: Result Processing
+
+```javascript
+// 验证任务链
+const allTasks = TaskList()
+const chainTasks = pipeline.map(s => taskIds[s.prefix]).filter(Boolean)
+const chainValid = chainTasks.length === pipeline.length
+
+if (!chainValid) {
+  mcp__ccw-tools__team_msg({
+    operation: "log", team: teamName, from: "coordinator",
+    to: "user", type: "error",
+    summary: `[coordinator] 任务链创建不完整: ${chainTasks.length}/${pipeline.length}`
+  })
+}
+```
+
+## GC Loop Task Creation
+
+当 executor 报告覆盖率不达标时，coordinator 调用此逻辑追加任务：
+
+```javascript
+function createGCLoopTasks(gcIteration, targetLayer, sessionFolder) {
+  // 创建修复任务
+  TaskCreate({
+    subject: `QAGEN-fix-${gcIteration}: 修复 ${targetLayer} 测试 (GC #${gcIteration})`,
+    description: `修复未通过测试并补充覆盖\nsession: ${sessionFolder}\nlayer: ${targetLayer}\ntype: gc-fix`,
+    activeForm: `GC循环 #${gcIteration} 修复中`
+  })
+
+  // 创建重新执行任务
+  TaskCreate({
+    subject: `QARUN-gc-${gcIteration}: 重新执行 ${targetLayer} (GC #${gcIteration})`,
+    description: `重新执行测试验证修复\nsession: ${sessionFolder}\nlayer: ${targetLayer}`,
+    activeForm: `GC循环 #${gcIteration} 执行中`
+  })
+
+  // 设置依赖: QARUN-gc 依赖 QAGEN-fix
+  // ... TaskUpdate addBlockedBy
+}
+```
+
+## Output Format
+
+```
+## Task Chain Created
+
+### Mode: [discovery|testing|full]
+### Pipeline Stages: [count]
+- [prefix]-001: [description] (owner: [role], blocked by: [deps])
+
+### Verification: PASS/FAIL
+```
+
+## Error Handling
+
+| Scenario | Resolution |
+|----------|------------|
+| Task creation fails | Retry once, then report to user |
+| Dependency cycle detected | Flatten dependencies, warn coordinator |
+| Invalid qaMode | Default to 'discovery' mode |
+| Agent/CLI failure | Retry once, then fallback to inline execution |
+| Timeout (>5 min) | Report partial results, notify coordinator |

.claude/skills/team-quality-assurance/roles/coordinator/commands/monitor.md

@@ -0,0 +1,247 @@
+# Command: monitor
+
+> 消息总线轮询与协调循环。持续监控 worker 进度，路由消息，触发 GC 循环，执行质量门控。
+
+## When to Use
+
+- Phase 4 of Coordinator
+- 任务链已创建并分发
+- 需要持续监控直到所有任务完成
+
+**Trigger conditions**:
+- dispatch 完成后立即启动
+- GC 循环创建新任务后重新进入
+
+## Strategy
+
+### Delegation Mode
+
+**Mode**: Direct（coordinator 直接轮询和路由）
+
+### Decision Logic
+
+```javascript
+// 消息路由表
+const routingTable = {
+  // Scout 完成
+  'scan_ready': {
+    action: 'Mark SCOUT complete, unblock QASTRAT',
+    next: 'strategist'
+  },
+  'issues_found': {
+    action: 'Mark SCOUT complete with issues, unblock QASTRAT',
+    next: 'strategist'
+  },
+
+  // Strategist 完成
+  'strategy_ready': {
+    action: 'Mark QASTRAT complete, unblock QAGEN',
+    next: 'generator'
+  },
+
+  // Generator 完成
+  'tests_generated': {
+    action: 'Mark QAGEN complete, unblock QARUN',
+    next: 'executor'
+  },
+  'tests_revised': {
+    action: 'Mark QAGEN-fix complete, unblock QARUN-gc',
+    next: 'executor'
+  },
+
+  // Executor 完成
+  'tests_passed': {
+    action: 'Mark QARUN complete, check coverage, unblock next',
+    next: 'check_coverage'
+  },
+  'tests_failed': {
+    action: 'Evaluate failures, decide GC loop or continue',
+    next: 'gc_decision'
+  },
+
+  // Analyst 完成
+  'analysis_ready': {
+    action: 'Mark QAANA complete, evaluate quality gate',
+    next: 'quality_gate'
+  },
+  'quality_report': {
+    action: 'Quality report received, prepare final report',
+    next: 'finalize'
+  },
+
+  // 错误
+  'error': {
+    action: 'Assess severity, retry or escalate',
+    next: 'error_handler'
+  }
+}
+```
+
+## Execution Steps
+
+### Step 1: Context Preparation
+
+```javascript
+// 从 shared memory 获取覆盖率目标
+const sharedMemory = JSON.parse(Read(`${sessionFolder}/shared-memory.json`))
+const strategy = sharedMemory.test_strategy || {}
+const coverageTargets = {}
+for (const layer of (strategy.layers || [])) {
+  coverageTargets[layer.level] = layer.target_coverage
+}
+
+let gcIteration = 0
+const MAX_GC_ITERATIONS = 3
+```
+
+### Step 2: Execute Strategy
+
+```javascript
+let allComplete = false
+
+while (!allComplete) {
+  // 1. Poll message bus
+  const messages = mcp__ccw-tools__team_msg({
+    operation: "list",
+    team: teamName,
+    last: 10
+  })
+
+  // 2. Route each unprocessed message
+  for (const msg of messages) {
+    const handler = routingTable[msg.type]
+    if (!handler) continue
+
+    switch (handler.next) {
+      case 'check_coverage': {
+        // 读取执行结果
+        const coverage = msg.data?.coverage || 0
+        const targetLayer = msg.data?.layer || 'L1'
+        const target = coverageTargets[targetLayer] || 80
+
+        if (coverage >= target) {
+          // 覆盖率达标，继续流水线
+          // 解锁下一个任务（QAANA 或下一层级）
+        } else {
+          // 转入 GC 决策
+          handler.next = 'gc_decision'
+        }
+        break
+      }
+
+      case 'gc_decision': {
+        const coverage = msg.data?.coverage || 0
+        const targetLayer = msg.data?.layer || 'L1'
+
+        if (gcIteration < MAX_GC_ITERATIONS) {
+          gcIteration++
+          // 触发 GC 循环
+          mcp__ccw-tools__team_msg({
+            operation: "log", team: teamName, from: "coordinator",
+            to: "generator", type: "gc_loop_trigger",
+            summary: `[coordinator] GC循环 #${gcIteration}: 覆盖率 ${coverage}% 未达标，请修复`,
+            data: { iteration: gcIteration, layer: targetLayer, coverage }
+          })
+
+          // 创建 GC 修复任务（参见 dispatch.md createGCLoopTasks）
+          // createGCLoopTasks(gcIteration, targetLayer, sessionFolder)
+        } else {
+          // 超过最大迭代次数，接受当前覆盖率
+          mcp__ccw-tools__team_msg({
+            operation: "log", team: teamName, from: "coordinator",
+            to: "user", type: "quality_gate",
+            summary: `[coordinator] GC循环已达上限(${MAX_GC_ITERATIONS})，接受当前覆盖率 ${coverage}%`
+          })
+          // 继续流水线，解锁 QAANA
+        }
+        break
+      }
+
+      case 'quality_gate': {
+        const qualityScore = sharedMemory.quality_score || 0
+        let status = 'PASS'
+        if (qualityScore < 60) status = 'FAIL'
+        else if (qualityScore < 80) status = 'CONDITIONAL'
+
+        mcp__ccw-tools__team_msg({
+          operation: "log", team: teamName, from: "coordinator",
+          to: "user", type: "quality_gate",
+          summary: `[coordinator] 质量门控: ${status} (score: ${qualityScore})`
+        })
+        break
+      }
+
+      case 'error_handler': {
+        const fromRole = msg.from
+        const severity = msg.data?.severity || 'medium'
+
+        if (severity === 'critical') {
+          // 通知用户
+          SendMessage({
+            content: `## [coordinator] Critical Error from ${fromRole}\n\n${msg.summary}`,
+            summary: `[coordinator] Critical error: ${msg.summary}`
+          })
+        } else {
+          // 标记任务失败，尝试重试
+        }
+        break
+      }
+    }
+  }
+
+  // 3. Check TaskList for overall completion
+  const tasks = TaskList()
+  const pendingWorkerTasks = tasks.filter(t =>
+    t.owner !== 'coordinator' &&
+    t.status !== 'completed' &&
+    t.status !== 'deleted'
+  )
+
+  allComplete = pendingWorkerTasks.length === 0
+
+  // 4. 如果没有完成，等待片刻再轮询
+  if (!allComplete) {
+    // 短暂等待（在实际执行中 coordinator 会在 subagent 返回后继续）
+  }
+}
+```
+
+### Step 3: Result Processing
+
+```javascript
+// 汇总所有结果
+const finalSharedMemory = JSON.parse(Read(`${sessionFolder}/shared-memory.json`))
+const summary = {
+  total_tasks: TaskList().filter(t => t.owner !== 'coordinator').length,
+  completed_tasks: TaskList().filter(t => t.status === 'completed' && t.owner !== 'coordinator').length,
+  gc_iterations: gcIteration,
+  quality_score: finalSharedMemory.quality_score,
+  coverage: finalSharedMemory.execution_results?.coverage
+}
+```
+
+## Output Format
+
+```
+## Coordination Summary
+
+### Pipeline Status: COMPLETE
+### Tasks: [completed]/[total]
+### GC Iterations: [count]
+### Quality Score: [score]/100
+### Coverage: [percent]%
+
+### Message Log (last 10)
+- [timestamp] [from] → [to]: [type] - [summary]
+```
+
+## Error Handling
+
+| Scenario | Resolution |
+|----------|------------|
+| Message bus unavailable | Fall back to TaskList polling only |
+| Teammate unresponsive (2x no response) | Respawn teammate with same task |
+| Deadlock detected (tasks blocked indefinitely) | Identify cycle, manually unblock |
+| Quality gate FAIL | Report to user, suggest targeted re-run |
+| Agent/CLI failure | Retry once, then fallback to inline execution |
+| Timeout (>5 min) | Report partial results, notify coordinator |

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

@@ -0,0 +1,228 @@
+# Role: coordinator
+
+QA 团队协调者。编排 pipeline：需求澄清 → 模式选择 → 团队创建 → 任务分发 → 监控协调 → 质量门控 → 结果汇报。
+
+## Role Identity
+
+- **Name**: `coordinator`
+- **Task Prefix**: N/A (coordinator creates tasks, doesn't receive them)
+- **Responsibility**: Orchestration
+- **Communication**: SendMessage to all teammates
+- **Output Tag**: `[coordinator]`
+
+## Role Boundaries
+
+### MUST
+
+- 所有输出（SendMessage、team_msg、日志）必须带 `[coordinator]` 标识
+- 仅负责需求澄清、模式选择、任务创建/分发、进度监控、质量门控、结果汇报
+- 通过 TaskCreate 创建任务并分配给 worker 角色
+- 通过消息总线监控 worker 进度并路由消息
+
+### MUST NOT
+
+- ❌ **直接执行任何业务任务**（扫描、测试、分析等）
+- ❌ 直接调用 cli-explore-agent、code-developer 等实现类 subagent
+- ❌ 直接修改源代码或生成产物文件
+- ❌ 绕过 worker 角色自行完成应委派的工作
+- ❌ 在输出中省略 `[coordinator]` 标识
+
+> **核心原则**: coordinator 是指挥者，不是执行者。所有实际工作必须通过 TaskCreate 委派给 worker 角色。
+
+## Message Types
+
+| Type | Direction | Trigger | Description |
+|------|-----------|---------|-------------|
+| `mode_selected` | coordinator → all | QA 模式确定 | Discovery/Testing/Full |
+| `gc_loop_trigger` | coordinator → generator | 覆盖率不达标 | 触发 Generator-Executor 循环 |
+| `quality_gate` | coordinator → user | 质量评估 | 通过/不通过/有条件通过 |
+| `task_unblocked` | coordinator → worker | 依赖解除 | 任务可执行 |
+| `error` | coordinator → user | 协调错误 | 阻塞性问题 |
+| `shutdown` | coordinator → all | 团队关闭 | 清理资源 |
+
+## Toolbox
+
+### Available Commands
+
+| Command | File | Phase | Description |
+|---------|------|-------|-------------|
+| `dispatch` | [commands/dispatch.md](commands/dispatch.md) | Phase 3 | 任务链创建与依赖管理 |
+| `monitor` | [commands/monitor.md](commands/monitor.md) | Phase 4 | 消息总线轮询与协调循环 |
+
+### Subagent Capabilities
+
+> Coordinator 不直接使用 subagent（通过 worker 角色间接使用）
+
+### CLI Capabilities
+
+> Coordinator 不直接使用 CLI 分析工具
+
+## Execution
+
+### Phase 1: Requirement Clarification
+
+```javascript
+const args = "$ARGUMENTS"
+
+// 提取任务描述
+const taskDescription = args.replace(/--role[=\s]+\w+/, '').replace(/--team[=\s]+[\w-]+/, '').replace(/--mode[=\s]+\w+/, '').trim()
+
+// QA 模式选择
+function detectQAMode(args, desc) {
+  const modeMatch = args.match(/--mode[=\s]+(discovery|testing|full)/)
+  if (modeMatch) return modeMatch[1]
+  if (/发现|扫描|scan|discover|issue|问题/.test(desc)) return 'discovery'
+  if (/测试|test|覆盖|coverage|TDD/.test(desc)) return 'testing'
+  return 'full'
+}
+
+let qaMode = detectQAMode(args, taskDescription)
+
+// 简单任务可跳过确认
+if (!taskDescription || taskDescription.length < 10) {
+  const clarification = AskUserQuestion({
+    questions: [{
+      question: "请描述 QA 目标（哪些模块需要质量保障？关注哪些方面？）",
+      header: "QA Target",
+      multiSelect: false,
+      options: [
+        { label: "自定义", description: "输入具体描述" },
+        { label: "全项目扫描", description: "对整个项目进行多视角质量扫描" },
+        { label: "变更测试", description: "针对最近代码变更生成和执行测试" },
+        { label: "完整QA流程", description: "扫描+测试+分析的完整闭环" }
+      ]
+    }]
+  })
+}
+```
+
+### Phase 2: Create Team + Spawn Teammates
+
+```javascript
+const teamName = "quality-assurance"
+const sessionSlug = taskDescription.slice(0, 30).replace(/[^a-zA-Z0-9\u4e00-\u9fa5]/g, '-')
+const sessionDate = new Date().toISOString().slice(0, 10)
+const sessionFolder = `.workflow/.team/QA-${sessionSlug}-${sessionDate}`
+Bash(`mkdir -p "${sessionFolder}"`)
+
+// 初始化 shared memory
+Write(`${sessionFolder}/shared-memory.json`, JSON.stringify({
+  discovered_issues: [],
+  test_strategy: {},
+  generated_tests: {},
+  execution_results: {},
+  defect_patterns: [],
+  coverage_history: [],
+  quality_score: null
+}, null, 2))
+
+TeamCreate({ team_name: teamName })
+
+// Spawn teammates (see SKILL.md Coordinator Spawn Template)
+// Scout, Strategist, Generator, Executor, Analyst
+```
+
+### Phase 3: Create Task Chain
+
+根据 qaMode 创建不同的任务链：
+
+```javascript
+// Read commands/dispatch.md for full implementation
+Read("commands/dispatch.md")
+```
+
+**Discovery Mode**:
+```
+SCOUT-001 → QASTRAT-001 → QAGEN-001 → QARUN-001 → QAANA-001
+```
+
+**Testing Mode** (跳过 scout):
+```
+QASTRAT-001 → QAGEN-001(L1) → QARUN-001(L1) → QAGEN-002(L2) → QARUN-002(L2) → QAANA-001
+```
+
+**Full QA Mode**:
+```
+SCOUT-001 → QASTRAT-001 → [QAGEN-001(L1) + QAGEN-002(L2)](parallel) → [QARUN-001 + QARUN-002](parallel) → QAANA-001 → SCOUT-002(回归)
+```
+
+### Phase 4: Coordination Loop
+
+```javascript
+// Read commands/monitor.md for full implementation
+Read("commands/monitor.md")
+```
+
+| Received Message | Action |
+|-----------------|--------|
+| `scan_ready` | 标记 SCOUT complete → 解锁 QASTRAT |
+| `strategy_ready` | 标记 QASTRAT complete → 解锁 QAGEN |
+| `tests_generated` | 标记 QAGEN complete → 解锁 QARUN |
+| `tests_passed` | 标记 QARUN complete → 解锁 QAANA 或下一层 |
+| `tests_failed` | 评估覆盖率 → 触发 GC 循环（gc_loop_trigger）或继续 |
+| `analysis_ready` | 标记 QAANA complete → 评估质量门控 |
+| Worker: `error` | 评估严重性 → 重试或上报用户 |
+
+**GC 循环触发逻辑**:
+```javascript
+if (coverage < targetCoverage && gcIteration < 3) {
+  // 创建 QAGEN-fix 任务 → QARUN 重新执行
+  gcIteration++
+} else if (gcIteration >= 3) {
+  // 接受当前覆盖率，继续流水线
+  team_msg({ type: "quality_gate", data: { status: "CONDITIONAL", coverage } })
+}
+```
+
+### Phase 5: Report + Persist
+
+```javascript
+// 读取 shared memory 汇总结果
+const memory = JSON.parse(Read(`${sessionFolder}/shared-memory.json`))
+
+const report = {
+  mode: qaMode,
+  issues_found: memory.discovered_issues?.length || 0,
+  test_strategy: memory.test_strategy?.layers || [],
+  tests_generated: Object.keys(memory.generated_tests || {}).length,
+  pass_rate: memory.execution_results?.pass_rate || 0,
+  coverage: memory.execution_results?.coverage || 0,
+  quality_score: memory.quality_score || 'N/A',
+  defect_patterns: memory.defect_patterns?.length || 0
+}
+
+mcp__ccw-tools__team_msg({
+  operation: "log", team: teamName, from: "coordinator",
+  to: "user", type: "quality_gate",
+  summary: `[coordinator] QA完成: ${report.issues_found}个问题, 覆盖率${report.coverage}%, 质量分${report.quality_score}`
+})
+
+SendMessage({
+  content: `## [coordinator] Quality Assurance Report\n\n${JSON.stringify(report, null, 2)}`,
+  summary: `[coordinator] QA report: ${report.quality_score}`
+})
+
+// 询问下一步
+AskUserQuestion({
+  questions: [{
+    question: "QA 流程已完成。下一步：",
+    header: "Next",
+    multiSelect: false,
+    options: [
+      { label: "新目标", description: "对新模块/需求执行QA" },
+      { label: "深入分析", description: "对发现的问题进行更深入分析" },
+      { label: "关闭团队", description: "关闭所有 teammate 并清理" }
+    ]
+  }]
+})
+```
+
+## Error Handling
+
+| Scenario | Resolution |
+|----------|------------|
+| Teammate unresponsive | Send follow-up, 2x → respawn |
+| Scout finds nothing | Skip to testing mode |
+| GC loop stuck >3 iterations | Accept current coverage, continue pipeline |
+| Test environment broken | Notify user, suggest manual fix |
+| All tasks completed but quality_score < 60 | Report with WARNING, suggest re-run with deeper analysis |

.claude/skills/team-quality-assurance/roles/executor/commands/run-fix-cycle.md

@@ -0,0 +1,220 @@
+# Command: run-fix-cycle
+
+> 迭代测试执行与自动修复。运行测试套件，解析结果，失败时委派 code-developer 修复，最多迭代 5 次。
+
+## When to Use
+
+- Phase 3 of Executor
+- 测试代码已生成，需要执行并验证
+- GC 循环中重新执行修复后的测试
+
+**Trigger conditions**:
+- QARUN-* 任务进入执行阶段
+- Generator 报告测试生成完成
+- GC 循环中 coordinator 创建的重新执行任务
+
+## Strategy
+
+### Delegation Mode
+
+**Mode**: Sequential Delegation（修复时）/ Direct（执行时）
+**Agent Type**: `code-developer`（仅用于修复）
+**Max Iterations**: 5
+
+### Decision Logic
+
+```javascript
+// 每次迭代的决策
+function shouldContinue(iteration, passRate, testsFailed) {
+  if (iteration >= MAX_ITERATIONS) return false
+  if (testsFailed === 0) return false  // 全部通过
+  if (passRate >= 95 && iteration >= 2) return false  // 足够好
+  return true
+}
+```
+
+## Execution Steps
+
+### Step 1: Context Preparation
+
+```javascript
+// 检测测试框架和命令
+const strategy = sharedMemory.test_strategy || {}
+const framework = strategy.test_framework || 'vitest'
+const targetLayer = task.description.match(/layer:\s*(L[123])/)?.[1] || 'L1'
+
+// 构建测试命令
+function buildTestCommand(framework, layer) {
+  const layerFilter = {
+    'L1': 'unit',
+    'L2': 'integration',
+    'L3': 'e2e'
+  }
+
+  const commands = {
+    'vitest': `npx vitest run --coverage --reporter=json --outputFile=test-results.json`,
+    'jest': `npx jest --coverage --json --outputFile=test-results.json`,
+    'pytest': `python -m pytest --cov --cov-report=json -v`,
+    'mocha': `npx mocha --reporter json > test-results.json`
+  }
+
+  let cmd = commands[framework] || 'npm test -- --coverage'
+
+  // 添加层级过滤（如果测试文件按目录组织）
+  const filter = layerFilter[layer]
+  if (filter && framework === 'vitest') {
+    cmd += ` --testPathPattern="${filter}"`
+  }
+
+  return cmd
+}
+
+const testCommand = buildTestCommand(framework, targetLayer)
+
+// 获取关联的测试文件
+const generatedTests = sharedMemory.generated_tests?.[targetLayer]?.files || []
+```
+
+### Step 2: Execute Strategy
+
+```javascript
+let iteration = 0
+const MAX_ITERATIONS = 5
+let lastOutput = ''
+let passRate = 0
+let coverage = 0
+let testsPassed = 0
+let testsFailed = 0
+
+while (iteration < MAX_ITERATIONS) {
+  // ===== EXECUTE TESTS =====
+  lastOutput = Bash(`${testCommand} 2>&1 || true`)
+
+  // ===== PARSE RESULTS =====
+  // 解析通过/失败数
+  const passedMatch = lastOutput.match(/(\d+)\s*(?:passed|passing)/)
+  const failedMatch = lastOutput.match(/(\d+)\s*(?:failed|failing)/)
+  testsPassed = passedMatch ? parseInt(passedMatch[1]) : 0
+  testsFailed = failedMatch ? parseInt(failedMatch[1]) : 0
+  const testsTotal = testsPassed + testsFailed
+
+  passRate = testsTotal > 0 ? Math.round(testsPassed / testsTotal * 100) : 0
+
+  // 解析覆盖率
+  try {
+    const coverageJson = JSON.parse(Read('coverage/coverage-summary.json'))
+    coverage = coverageJson.total?.lines?.pct || 0
+  } catch {
+    // 尝试从输出解析
+    const covMatch = lastOutput.match(/(?:Lines|Stmts|All files)\s*[:|]\s*(\d+\.?\d*)%/)
+    coverage = covMatch ? parseFloat(covMatch[1]) : 0
+  }
+
+  // ===== CHECK PASS =====
+  if (testsFailed === 0) {
+    break  // 全部通过
+  }
+
+  // ===== SHOULD CONTINUE? =====
+  if (!shouldContinue(iteration + 1, passRate, testsFailed)) {
+    break
+  }
+
+  // ===== AUTO-FIX =====
+  iteration++
+
+  // 提取失败详情
+  const failureLines = lastOutput.split('\n')
+    .filter(l => /FAIL|Error|AssertionError|Expected|Received|TypeError|ReferenceError/.test(l))
+    .slice(0, 30)
+    .join('\n')
+
+  // 委派修复给 code-developer
+  Task({
+    subagent_type: "code-developer",
+    run_in_background: false,
+    description: `Fix ${testsFailed} test failures (iteration ${iteration}/${MAX_ITERATIONS})`,
+    prompt: `## Goal
+Fix failing tests. ONLY modify test files, NEVER modify source code.
+
+## Test Output
+\`\`\`
+${failureLines}
+\`\`\`
+
+## Test Files to Fix
+${generatedTests.map(f => `- ${f}`).join('\n')}
+
+## Rules
+- Read each failing test file before modifying
+- Fix: incorrect assertions, missing imports, wrong mocks, setup issues
+- Do NOT: skip tests, add \`@ts-ignore\`, use \`as any\`, modify source code
+- Keep existing test structure and naming
+- If a test is fundamentally wrong about expected behavior, fix the assertion to match actual source behavior`
+  })
+}
+```
+
+### Step 3: Result Processing
+
+```javascript
+const resultData = {
+  layer: targetLayer,
+  framework: framework,
+  iterations: iteration,
+  pass_rate: passRate,
+  coverage: coverage,
+  tests_passed: testsPassed,
+  tests_failed: testsFailed,
+  all_passed: testsFailed === 0,
+  max_iterations_reached: iteration >= MAX_ITERATIONS
+}
+
+// 保存执行结果
+Bash(`mkdir -p "${sessionFolder}/results"`)
+Write(`${sessionFolder}/results/run-${targetLayer}.json`, JSON.stringify(resultData, null, 2))
+
+// 保存最后一次测试输出（截取关键部分）
+const outputSummary = lastOutput.split('\n').slice(-30).join('\n')
+Write(`${sessionFolder}/results/output-${targetLayer}.txt`, outputSummary)
+
+// 更新 shared memory
+sharedMemory.execution_results = sharedMemory.execution_results || {}
+sharedMemory.execution_results[targetLayer] = resultData
+sharedMemory.execution_results.pass_rate = passRate
+sharedMemory.execution_results.coverage = coverage
+Write(`${sessionFolder}/shared-memory.json`, JSON.stringify(sharedMemory, null, 2))
+```
+
+## Output Format
+
+```
+## Test Execution Results
+
+### Layer: [L1|L2|L3]
+### Framework: [vitest|jest|pytest]
+### Status: [PASS|FAIL]
+
+### Results
+- Tests passed: [count]
+- Tests failed: [count]
+- Pass rate: [percent]%
+- Coverage: [percent]%
+- Fix iterations: [count]/[max]
+
+### Failure Details (if any)
+- [test name]: [error description]
+```
+
+## Error Handling
+
+| Scenario | Resolution |
+|----------|------------|
+| Test command not found | Try fallback: npm test → npx vitest → npx jest → pytest |
+| Test environment broken | Report error to coordinator, suggest manual fix |
+| Max iterations reached with failures | Report current state, let coordinator decide (GC loop or accept) |
+| Coverage data unavailable | Report 0%, note coverage collection failure |
+| Sub-agent fix introduces new failures | Revert last fix, try different approach |
+| No test files to run | Report empty, notify coordinator |
+| Agent/CLI failure | Retry once, then fallback to inline execution |
+| Timeout (>5 min) | Report partial results, notify coordinator |

.claude/skills/team-quality-assurance/roles/executor/role.md

@@ -0,0 +1,252 @@
+# Role: executor
+
+测试执行者。运行测试套件，收集覆盖率数据，在测试失败时进行自动修复循环。实现 Generator-Executor（GC）循环中的执行端。
+
+## Role Identity
+
+- **Name**: `executor`
+- **Task Prefix**: `QARUN-*`
+- **Responsibility**: Validation（测试执行与修复）
+- **Communication**: SendMessage to coordinator only
+- **Output Tag**: `[executor]`
+
+## Role Boundaries
+
+### MUST
+
+- 仅处理 `QARUN-*` 前缀的任务
+- 所有输出必须带 `[executor]` 标识
+- 执行测试并收集覆盖率
+- 在失败时尝试自动修复
+
+### MUST NOT
+
+- ❌ 从零生成新测试（那是 generator 的职责）
+- ❌ 修改源代码（除非修复测试本身）
+- ❌ 为其他角色创建任务
+- ❌ 直接与其他 worker 通信
+
+## Message Types
+
+| Type | Direction | Trigger | Description |
+|------|-----------|---------|-------------|
+| `tests_passed` | executor → coordinator | 所有测试通过 | 包含覆盖率数据 |
+| `tests_failed` | executor → coordinator | 测试失败 | 包含失败详情和修复尝试 |
+| `coverage_report` | executor → coordinator | 覆盖率收集完成 | 覆盖率数据 |
+| `error` | executor → coordinator | 执行环境错误 | 阻塞性错误 |
+
+## Toolbox
+
+### Available Commands
+
+| Command | File | Phase | Description |
+|---------|------|-------|-------------|
+| `run-fix-cycle` | [commands/run-fix-cycle.md](commands/run-fix-cycle.md) | Phase 3 | 迭代测试执行与自动修复 |
+
+### Subagent Capabilities
+
+| Agent Type | Used By | Purpose |
+|------------|---------|---------|
+| `code-developer` | run-fix-cycle.md | 测试失败自动修复 |
+
+## Execution (5-Phase)
+
+### Phase 1: Task Discovery
+
+```javascript
+const tasks = TaskList()
+const myTasks = tasks.filter(t =>
+  t.subject.startsWith('QARUN-') &&
+  t.owner === 'executor' &&
+  t.status === 'pending' &&
+  t.blockedBy.length === 0
+)
+
+if (myTasks.length === 0) return
+const task = TaskGet({ taskId: myTasks[0].id })
+TaskUpdate({ taskId: task.id, status: 'in_progress' })
+```
+
+### Phase 2: Environment Detection
+
+```javascript
+// 读取 shared memory
+const sessionFolder = task.description.match(/session:\s*(.+)/)?.[1] || '.'
+let sharedMemory = {}
+try { sharedMemory = JSON.parse(Read(`${sessionFolder}/shared-memory.json`)) } catch {}
+
+const strategy = sharedMemory.test_strategy || {}
+const generatedTests = sharedMemory.generated_tests || {}
+const targetLayer = task.description.match(/layer:\s*(L[123])/)?.[1] || 'L1'
+
+// 检测测试命令
+function detectTestCommand(framework, layer) {
+  const commands = {
+    'jest': `npx jest --coverage --testPathPattern="${layer === 'L1' ? 'unit' : layer === 'L2' ? 'integration' : 'e2e'}"`,
+    'vitest': `npx vitest run --coverage --reporter=json`,
+    'pytest': `python -m pytest --cov --cov-report=json`,
+    'mocha': `npx mocha --reporter json`,
+  }
+  return commands[framework] || 'npm test -- --coverage'
+}
+
+const testCommand = detectTestCommand(strategy.test_framework || 'vitest', targetLayer)
+
+// 获取变更的测试文件
+const testFiles = generatedTests[targetLayer]?.files || []
+```
+
+### Phase 3: Execution & Fix Cycle
+
+```javascript
+// Read commands/run-fix-cycle.md for full implementation
+Read("commands/run-fix-cycle.md")
+```
+
+**核心逻辑**: 迭代执行测试，失败时自动修复
+
+```javascript
+let iteration = 0
+const MAX_ITERATIONS = 5
+let lastResult = null
+let passRate = 0
+let coverage = 0
+
+while (iteration < MAX_ITERATIONS) {
+  // 执行测试
+  lastResult = Bash(`${testCommand} 2>&1 || true`)
+
+  // 解析结果
+  const testsPassed = (lastResult.match(/(\d+) passed/)?.[1] || 0) * 1
+  const testsFailed = (lastResult.match(/(\d+) failed/)?.[1] || 0) * 1
+  const testsTotal = testsPassed + testsFailed
+  passRate = testsTotal > 0 ? (testsPassed / testsTotal * 100) : 0
+
+  // 解析覆盖率
+  try {
+    const coverageJson = JSON.parse(Read('coverage/coverage-summary.json'))
+    coverage = coverageJson.total?.lines?.pct || 0
+  } catch {
+    coverage = 0
+  }
+
+  // 检查是否通过
+  if (testsFailed === 0) {
+    break  // 全部通过
+  }
+
+  // 尝试自动修复
+  iteration++
+  if (iteration < MAX_ITERATIONS) {
+    // 提取失败信息
+    const failureDetails = lastResult.split('\n')
+      .filter(l => /FAIL|Error|AssertionError|Expected|Received/.test(l))
+      .slice(0, 20)
+      .join('\n')
+
+    // 委派修复给 code-developer
+    Task({
+      subagent_type: "code-developer",
+      run_in_background: false,
+      description: `Fix ${testsFailed} test failures (iteration ${iteration})`,
+      prompt: `## Goal
+Fix failing tests. Do NOT modify source code, only fix test files.
+
+## Test Failures
+${failureDetails}
+
+## Test Files
+${testFiles.map(f => `- ${f}`).join('\n')}
+
+## Instructions
+- Read failing test files
+- Fix assertions, imports, or test setup
+- Do NOT change source code
+- Do NOT skip/ignore tests`
+    })
+  }
+}
+```
+
+### Phase 4: Result Analysis
+
+```javascript
+const resultData = {
+  layer: targetLayer,
+  iterations: iteration,
+  pass_rate: passRate,
+  coverage: coverage,
+  tests_passed: lastResult?.match(/(\d+) passed/)?.[1] || 0,
+  tests_failed: lastResult?.match(/(\d+) failed/)?.[1] || 0,
+  all_passed: passRate === 100 || (lastResult && !lastResult.includes('FAIL'))
+}
+
+// 保存执行结果
+Bash(`mkdir -p "${sessionFolder}/results"`)
+Write(`${sessionFolder}/results/run-${targetLayer}.json`, JSON.stringify(resultData, null, 2))
+
+// 更新 shared memory
+sharedMemory.execution_results = sharedMemory.execution_results || {}
+sharedMemory.execution_results[targetLayer] = resultData
+sharedMemory.execution_results.pass_rate = passRate
+sharedMemory.execution_results.coverage = coverage
+Write(`${sessionFolder}/shared-memory.json`, JSON.stringify(sharedMemory, null, 2))
+```
+
+### Phase 5: Report to Coordinator
+
+```javascript
+const statusMsg = resultData.all_passed
+  ? `全部通过 (${resultData.tests_passed} tests, 覆盖率 ${coverage}%)`
+  : `${resultData.tests_failed} 个失败 (${iteration}次修复尝试, 覆盖率 ${coverage}%)`
+
+const msgType = resultData.all_passed ? 'tests_passed' : 'tests_failed'
+
+mcp__ccw-tools__team_msg({
+  operation: "log",
+  team: teamName,
+  from: "executor",
+  to: "coordinator",
+  type: msgType,
+  summary: `[executor] ${targetLayer}: ${statusMsg}`,
+  ref: `${sessionFolder}/results/run-${targetLayer}.json`,
+  data: { pass_rate: passRate, coverage, iterations: iteration }
+})
+
+SendMessage({
+  type: "message",
+  recipient: "coordinator",
+  content: `## [executor] Test Execution Results
+
+**Task**: ${task.subject}
+**Layer**: ${targetLayer}
+**Status**: ${resultData.all_passed ? 'PASS' : 'FAIL'}
+**Pass Rate**: ${passRate}%
+**Coverage**: ${coverage}%
+**Iterations**: ${iteration}/${MAX_ITERATIONS}
+
+### Details
+- Tests passed: ${resultData.tests_passed}
+- Tests failed: ${resultData.tests_failed}`,
+  summary: `[executor] QARUN ${targetLayer}: ${resultData.all_passed ? 'PASS' : 'FAIL'} ${passRate}%`
+})
+
+TaskUpdate({ taskId: task.id, status: 'completed' })
+
+const nextTasks = TaskList().filter(t =>
+  t.subject.startsWith('QARUN-') && t.owner === 'executor' &&
+  t.status === 'pending' && t.blockedBy.length === 0
+)
+if (nextTasks.length > 0) { /* back to Phase 1 */ }
+```
+
+## Error Handling
+
+| Scenario | Resolution |
+|----------|------------|
+| No QARUN-* tasks available | Idle, wait for coordinator |
+| Test command fails to execute | Try fallback: `npm test`, `npx vitest run`, `pytest` |
+| Max iterations reached | Report current pass rate, let coordinator decide |
+| Coverage data unavailable | Report 0%, note coverage collection failure |
+| Test environment broken | SendMessage error to coordinator, suggest manual fix |
+| Sub-agent fix introduces new failures | Revert fix, try next failure |

.claude/skills/team-quality-assurance/roles/generator/commands/generate-tests.md

@@ -0,0 +1,258 @@
+# Command: generate-tests
+
+> 按层级生成测试代码。根据 strategist 策略和项目现有测试模式，生成 L1/L2/L3 测试用例。
+
+## When to Use
+
+- Phase 3 of Generator
+- 策略已制定，需要生成对应层级的测试代码
+- GC 循环中修订失败的测试
+
+**Trigger conditions**:
+- QAGEN-* 任务进入执行阶段
+- 测试策略中包含当前层级
+- GC 循环触发修复任务（QAGEN-fix-*）
+
+## Strategy
+
+### Delegation Mode
+
+**Mode**: Sequential Delegation（复杂时）/ Direct（简单时）
+**Agent Type**: `code-developer`
+**Delegation Scope**: Per-layer
+
+### Decision Logic
+
+```javascript
+const focusFiles = layerConfig.focus_files || []
+const isGCFix = task.subject.includes('fix')
+
+if (isGCFix) {
+  // GC 修复模式：读取失败信息，针对性修复
+  mode = 'gc-fix'
+} else if (focusFiles.length <= 3) {
+  // 直接生成：内联 Read → 分析 → Write
+  mode = 'direct'
+} else {
+  // 委派给 code-developer
+  mode = 'delegate'
+}
+```
+
+## Execution Steps
+
+### Step 1: Context Preparation
+
+```javascript
+// 从 shared memory 获取策略
+const strategy = sharedMemory.test_strategy || {}
+const targetLayer = task.description.match(/layer:\s*(L[123])/)?.[1] || 'L1'
+
+// 确定层级配置
+const layerConfig = strategy.layers?.find(l => l.level === targetLayer) || {
+  level: targetLayer,
+  name: targetLayer === 'L1' ? 'Unit Tests' : targetLayer === 'L2' ? 'Integration Tests' : 'E2E Tests',
+  target_coverage: targetLayer === 'L1' ? 80 : targetLayer === 'L2' ? 60 : 40,
+  focus_files: []
+}
+
+// 学习现有测试模式（必须找 3 个相似测试文件）
+const existingTests = Glob(`**/*.{test,spec}.{ts,tsx,js,jsx}`)
+const testPatterns = existingTests.slice(0, 3).map(f => ({
+  path: f,
+  content: Read(f)
+}))
+
+// 检测测试约定
+const testConventions = detectTestConventions(testPatterns)
+```
+
+### Step 2: Execute Strategy
+
+```javascript
+if (mode === 'gc-fix') {
+  // GC 修复模式
+  // 读取失败信息
+  const failedTests = sharedMemory.execution_results?.[targetLayer]
+  const failureOutput = Read(`${sessionFolder}/results/run-${targetLayer}.json`)
+
+  Task({
+    subagent_type: "code-developer",
+    run_in_background: false,
+    description: `Fix failing ${targetLayer} tests (GC iteration)`,
+    prompt: `## Goal
+Fix the failing tests based on execution results. Do NOT modify source code.
+
+## Test Execution Results
+${JSON.stringify(failedTests, null, 2)}
+
+## Test Conventions
+${JSON.stringify(testConventions, null, 2)}
+
+## Instructions
+- Read each failing test file
+- Fix assertions, imports, mocks, or test setup
+- Ensure tests match actual source behavior
+- Do NOT skip or ignore tests
+- Do NOT modify source files`
+  })
+
+} else if (mode === 'direct') {
+  // 直接生成模式
+  const focusFiles = layerConfig.focus_files || []
+
+  for (const sourceFile of focusFiles) {
+    const sourceContent = Read(sourceFile)
+
+    // 确定测试文件路径（遵循项目约定）
+    const testPath = determineTestPath(sourceFile, testConventions)
+
+    // 检查是否已有测试
+    let existingTest = null
+    try { existingTest = Read(testPath) } catch {}
+
+    if (existingTest) {
+      // 补充现有测试：分析缺失的测试用例
+      const missingCases = analyzeMissingCases(sourceContent, existingTest)
+      if (missingCases.length > 0) {
+        // 追加测试用例
+        Edit({
+          file_path: testPath,
+          old_string: findLastTestBlock(existingTest),
+          new_string: `${findLastTestBlock(existingTest)}\n\n${generateCases(missingCases, testConventions)}`
+        })
+      }
+    } else {
+      // 创建新测试文件
+      const testContent = generateFullTestFile(sourceFile, sourceContent, testConventions, targetLayer)
+      Write(testPath, testContent)
+    }
+  }
+
+} else {
+  // 委派模式
+  const focusFiles = layerConfig.focus_files || []
+
+  Task({
+    subagent_type: "code-developer",
+    run_in_background: false,
+    description: `Generate ${targetLayer} tests for ${focusFiles.length} files`,
+    prompt: `## Goal
+Generate ${layerConfig.name} for the following source files.
+
+## Test Framework
+${strategy.test_framework || 'vitest'}
+
+## Existing Test Patterns (MUST follow these exactly)
+${testPatterns.map(t => `### ${t.path}\n\`\`\`\n${t.content.substring(0, 800)}\n\`\`\``).join('\n\n')}
+
+## Test Conventions
+- Test file location: ${testConventions.location}
+- Import style: ${testConventions.importStyle}
+- Describe/it nesting: ${testConventions.nesting}
+
+## Source Files to Test
+${focusFiles.map(f => `- ${f}`).join('\n')}
+
+## Requirements
+- Follow existing test patterns exactly (import style, naming, structure)
+- Cover: happy path + edge cases + error cases
+- Target coverage: ${layerConfig.target_coverage}%
+- Do NOT modify source files, only create/modify test files
+- Do NOT use \`any\` type assertions
+- Do NOT skip or mark tests as TODO without implementation`
+  })
+}
+
+// 辅助函数
+function determineTestPath(sourceFile, conventions) {
+  if (conventions.location === 'colocated') {
+    return sourceFile.replace(/\.(ts|tsx|js|jsx)$/, `.test.$1`)
+  } else if (conventions.location === '__tests__') {
+    const dir = sourceFile.substring(0, sourceFile.lastIndexOf('/'))
+    const name = sourceFile.substring(sourceFile.lastIndexOf('/') + 1)
+    return `${dir}/__tests__/${name.replace(/\.(ts|tsx|js|jsx)$/, `.test.$1`)}`
+  }
+  return sourceFile.replace(/\.(ts|tsx|js|jsx)$/, `.test.$1`)
+}
+
+function detectTestConventions(patterns) {
+  const conventions = {
+    location: 'colocated',  // or '__tests__'
+    importStyle: 'named',   // or 'default'
+    nesting: 'describe-it', // or 'test-only'
+    framework: 'vitest'
+  }
+
+  for (const p of patterns) {
+    if (p.path.includes('__tests__')) conventions.location = '__tests__'
+    if (p.content.includes("import { describe")) conventions.nesting = 'describe-it'
+    if (p.content.includes("from 'vitest'")) conventions.framework = 'vitest'
+    if (p.content.includes("from '@jest'") || p.content.includes("from 'jest'")) conventions.framework = 'jest'
+  }
+
+  return conventions
+}
+```
+
+### Step 3: Result Processing
+
+```javascript
+// 收集生成/修改的测试文件
+const generatedTests = Bash(`git diff --name-only`).split('\n')
+  .filter(f => /\.(test|spec)\.(ts|tsx|js|jsx)$/.test(f))
+
+// TypeScript 语法检查
+const syntaxResult = Bash(`npx tsc --noEmit ${generatedTests.join(' ')} 2>&1 || true`)
+const hasSyntaxErrors = syntaxResult.includes('error TS')
+
+// 自动修复语法错误（最多 3 次）
+if (hasSyntaxErrors) {
+  let fixAttempt = 0
+  while (fixAttempt < 3 && syntaxResult.includes('error TS')) {
+    const errors = syntaxResult.split('\n').filter(l => l.includes('error TS')).slice(0, 5)
+    // 尝试修复每个错误...
+    fixAttempt++
+  }
+}
+
+// 更新 shared memory
+const testInfo = {
+  layer: targetLayer,
+  files: generatedTests,
+  count: generatedTests.length,
+  syntax_clean: !hasSyntaxErrors,
+  mode: mode,
+  gc_fix: mode === 'gc-fix'
+}
+
+sharedMemory.generated_tests = sharedMemory.generated_tests || {}
+sharedMemory.generated_tests[targetLayer] = testInfo
+Write(`${sessionFolder}/shared-memory.json`, JSON.stringify(sharedMemory, null, 2))
+```
+
+## Output Format
+
+```
+## Test Generation Results
+
+### Layer: [L1|L2|L3]
+### Mode: [direct|delegate|gc-fix]
+### Files Generated: [count]
+- [test file path]
+
+### Syntax Check: PASS/FAIL
+### Conventions Applied: [framework], [location], [nesting]
+```
+
+## Error Handling
+
+| Scenario | Resolution |
+|----------|------------|
+| No focus files in strategy | Generate L1 tests for all source files in scope |
+| No existing test patterns | Use framework defaults (vitest/jest/pytest) |
+| Sub-agent failure | Retry once, fallback to direct generation |
+| Syntax errors persist after 3 fixes | Report errors, proceed with available tests |
+| Source file not found | Skip file, log warning |
+| Agent/CLI failure | Retry once, then fallback to inline execution |
+| Timeout (>5 min) | Report partial results, notify coordinator |

.claude/skills/team-quality-assurance/roles/generator/role.md

@@ -0,0 +1,282 @@
+# Role: generator
+
+测试用例生成器。按 strategist 制定的策略和层级，生成对应的测试代码。支持 L1 单元测试、L2 集成测试、L3 E2E 测试。遵循项目现有测试模式和框架约定。
+
+## Role Identity
+
+- **Name**: `generator`
+- **Task Prefix**: `QAGEN-*`
+- **Responsibility**: Code generation（测试代码生成）
+- **Communication**: SendMessage to coordinator only
+- **Output Tag**: `[generator]`
+
+## Role Boundaries
+
+### MUST
+
+- 仅处理 `QAGEN-*` 前缀的任务
+- 所有输出必须带 `[generator]` 标识
+- 遵循项目现有测试框架和模式
+- 生成的测试必须可运行
+
+### MUST NOT
+
+- ❌ 修改源代码（仅生成测试代码）
+- ❌ 执行测试
+- ❌ 为其他角色创建任务
+- ❌ 直接与其他 worker 通信
+
+## Message Types
+
+| Type | Direction | Trigger | Description |
+|------|-----------|---------|-------------|
+| `tests_generated` | generator → coordinator | 测试生成完成 | 包含生成的测试文件列表 |
+| `tests_revised` | generator → coordinator | 测试修订完成 | GC 循环中修订后 |
+| `error` | generator → coordinator | 生成失败 | 阻塞性错误 |
+
+## Toolbox
+
+### Available Commands
+
+| Command | File | Phase | Description |
+|---------|------|-------|-------------|
+| `generate-tests` | [commands/generate-tests.md](commands/generate-tests.md) | Phase 3 | 按层级生成测试代码 |
+
+### Subagent Capabilities
+
+| Agent Type | Used By | Purpose |
+|------------|---------|---------|
+| `code-developer` | generate-tests.md | 复杂测试代码生成 |
+
+### CLI Capabilities
+
+| CLI Tool | Mode | Used By | Purpose |
+|----------|------|---------|---------|
+| `gemini` | analysis | generate-tests.md | 分析现有测试模式 |
+
+## Execution (5-Phase)
+
+### Phase 1: Task Discovery
+
+```javascript
+const tasks = TaskList()
+const myTasks = tasks.filter(t =>
+  t.subject.startsWith('QAGEN-') &&
+  t.owner === 'generator' &&
+  t.status === 'pending' &&
+  t.blockedBy.length === 0
+)
+
+if (myTasks.length === 0) return
+const task = TaskGet({ taskId: myTasks[0].id })
+TaskUpdate({ taskId: task.id, status: 'in_progress' })
+```
+
+### Phase 2: Strategy & Pattern Loading
+
+```javascript
+// 读取 shared memory 获取策略
+const sessionFolder = task.description.match(/session:\s*(.+)/)?.[1] || '.'
+let sharedMemory = {}
+try { sharedMemory = JSON.parse(Read(`${sessionFolder}/shared-memory.json`)) } catch {}
+
+const strategy = sharedMemory.test_strategy || {}
+const targetLayer = task.description.match(/layer:\s*(L[123])/)?.[1] || strategy.layers?.[0]?.level || 'L1'
+
+// 确定目标层级的详情
+const layerConfig = strategy.layers?.find(l => l.level === targetLayer) || {
+  level: targetLayer,
+  name: targetLayer === 'L1' ? 'Unit Tests' : targetLayer === 'L2' ? 'Integration Tests' : 'E2E Tests',
+  target_coverage: targetLayer === 'L1' ? 80 : targetLayer === 'L2' ? 60 : 40,
+  focus_files: []
+}
+
+// 学习现有测试模式（找 3 个相似测试文件）
+const existingTests = Glob(`**/*.{test,spec}.{ts,tsx,js,jsx}`)
+const testPatterns = existingTests.slice(0, 3).map(f => ({
+  path: f,
+  content: Read(f)
+}))
+
+// 检测测试框架和配置
+const testFramework = strategy.test_framework || 'vitest'
+```
+
+### Phase 3: Test Generation
+
+```javascript
+// Read commands/generate-tests.md for full implementation
+Read("commands/generate-tests.md")
+```
+
+**核心策略**: 基于复杂度选择生成方式
+
+```javascript
+const focusFiles = layerConfig.focus_files || []
+
+if (focusFiles.length <= 3) {
+  // 直接生成：读取源文件 → 分析 → 写测试
+  for (const sourceFile of focusFiles) {
+    const sourceContent = Read(sourceFile)
+
+    // 确定测试文件路径（遵循项目约定）
+    const testPath = sourceFile
+      .replace(/\.(ts|tsx|js|jsx)$/, `.test.$1`)
+      .replace(/^src\//, 'src/__tests__/')  // 或保持同级
+
+    // 检查是否已有测试
+    let existingTest = null
+    try { existingTest = Read(testPath) } catch {}
+
+    if (existingTest) {
+      // 补充现有测试
+      Edit({
+        file_path: testPath,
+        old_string: "// END OF TESTS",
+        new_string: `// Additional tests for coverage\n// ...new test cases...\n// END OF TESTS`
+      })
+    } else {
+      // 创建新测试文件
+      Write(testPath, generateTestContent(sourceFile, sourceContent, testPatterns, testFramework))
+    }
+  }
+} else {
+  // 委派给 code-developer
+  Task({
+    subagent_type: "code-developer",
+    run_in_background: false,
+    description: `Generate ${targetLayer} tests for ${focusFiles.length} files`,
+    prompt: `## Goal
+Generate ${layerConfig.name} for the following source files.
+
+## Test Framework
+${testFramework}
+
+## Existing Test Patterns
+${testPatterns.map(t => `### ${t.path}\n\`\`\`\n${t.content.substring(0, 500)}\n\`\`\``).join('\n\n')}
+
+## Source Files to Test
+${focusFiles.map(f => `- ${f}`).join('\n')}
+
+## Requirements
+- Follow existing test patterns exactly
+- Cover happy path + edge cases + error cases
+- Target coverage: ${layerConfig.target_coverage}%
+- Do NOT modify source files, only create/modify test files`
+  })
+}
+
+// 辅助函数
+function generateTestContent(sourceFile, sourceContent, patterns, framework) {
+  // 基于模式生成测试代码骨架
+  const imports = extractExports(sourceContent)
+  const pattern = patterns[0]?.content || ''
+
+  return `import { ${imports.join(', ')} } from '${sourceFile.replace(/\.(ts|tsx|js|jsx)$/, '')}'
+
+describe('${sourceFile}', () => {
+  ${imports.map(exp => `
+  describe('${exp}', () => {
+    it('should work correctly with valid input', () => {
+      // TODO: implement test
+    })
+
+    it('should handle edge cases', () => {
+      // TODO: implement test
+    })
+
+    it('should handle error cases', () => {
+      // TODO: implement test
+    })
+  })`).join('\n')}
+})`
+}
+
+function extractExports(content) {
+  const matches = content.match(/export\s+(function|const|class|interface|type)\s+(\w+)/g) || []
+  return matches.map(m => m.split(/\s+/).pop())
+}
+```
+
+### Phase 4: Self-Validation
+
+```javascript
+// 验证生成的测试文件语法正确
+const generatedTests = Bash(`git diff --name-only`).split('\n')
+  .filter(f => /\.(test|spec)\.(ts|tsx|js|jsx)$/.test(f))
+
+// TypeScript 语法检查
+const syntaxResult = Bash(`npx tsc --noEmit ${generatedTests.join(' ')} 2>&1 || true`)
+const hasSyntaxErrors = syntaxResult.includes('error TS')
+
+if (hasSyntaxErrors) {
+  // 自动修复语法错误
+  const errors = syntaxResult.split('\n').filter(l => l.includes('error TS'))
+  for (const error of errors.slice(0, 5)) {
+    // 解析错误并尝试修复
+  }
+}
+
+// 记录生成的测试
+const generatedTestInfo = {
+  layer: targetLayer,
+  files: generatedTests,
+  count: generatedTests.length,
+  syntax_clean: !hasSyntaxErrors
+}
+
+// 更新 shared memory
+sharedMemory.generated_tests = sharedMemory.generated_tests || {}
+sharedMemory.generated_tests[targetLayer] = generatedTestInfo
+Write(`${sessionFolder}/shared-memory.json`, JSON.stringify(sharedMemory, null, 2))
+```
+
+### Phase 5: Report to Coordinator
+
+```javascript
+const msgType = task.subject.includes('fix') ? 'tests_revised' : 'tests_generated'
+
+mcp__ccw-tools__team_msg({
+  operation: "log",
+  team: teamName,
+  from: "generator",
+  to: "coordinator",
+  type: msgType,
+  summary: `[generator] ${targetLayer} 测试生成完成: ${generatedTests.length} 文件, 语法${hasSyntaxErrors ? '有错误' : '正常'}`,
+  ref: generatedTests[0]
+})
+
+SendMessage({
+  type: "message",
+  recipient: "coordinator",
+  content: `## [generator] Test Generation Results
+
+**Task**: ${task.subject}
+**Layer**: ${targetLayer} - ${layerConfig.name}
+**Generated**: ${generatedTests.length} test files
+**Syntax**: ${hasSyntaxErrors ? 'ERRORS' : 'CLEAN'}
+
+### Generated Files
+${generatedTests.map(f => `- ${f}`).join('\n')}`,
+  summary: `[generator] QAGEN complete: ${targetLayer} ${generatedTests.length} files`
+})
+
+TaskUpdate({ taskId: task.id, status: 'completed' })
+
+const nextTasks = TaskList().filter(t =>
+  t.subject.startsWith('QAGEN-') && t.owner === 'generator' &&
+  t.status === 'pending' && t.blockedBy.length === 0
+)
+if (nextTasks.length > 0) { /* back to Phase 1 */ }
+```
+
+## Error Handling
+
+| Scenario | Resolution |
+|----------|------------|
+| No QAGEN-* tasks available | Idle, wait for coordinator |
+| Strategy not found in shared memory | Generate L1 unit tests for changed files |
+| No existing test patterns found | Use framework defaults |
+| Sub-agent failure | Retry once, fallback to direct generation |
+| Syntax errors in generated tests | Auto-fix up to 3 attempts, report remaining |
+| Source file not found | Skip file, report to coordinator |

.claude/skills/team-quality-assurance/roles/scout/commands/scan.md

@@ -0,0 +1,216 @@
+# Command: scan
+
+> 多视角 CLI Fan-out 扫描。从 bug、安全、测试覆盖、代码质量、UX 等视角并行分析代码，发现潜在问题。
+
+## When to Use
+
+- Phase 3 of Scout
+- 需要对代码库进行多视角问题扫描
+- 复杂度为 Medium 或 High 时使用 CLI Fan-out
+
+**Trigger conditions**:
+- SCOUT-* 任务进入 Phase 3
+- 复杂度评估为 Medium/High
+- 需要深度分析超出 ACE 搜索能力
+
+## Strategy
+
+### Delegation Mode
+
+**Mode**: CLI Fan-out
+**CLI Tool**: `gemini` (primary)
+**CLI Mode**: `analysis`
+**Parallel Perspectives**: 2-5（根据复杂度）
+
+### Decision Logic
+
+```javascript
+// 复杂度决定扫描策略
+if (complexity === 'Low') {
+  // ACE 搜索 + Grep 内联分析（不使用 CLI）
+  mode = 'inline'
+} else if (complexity === 'Medium') {
+  // CLI Fan-out: 3 个核心视角
+  mode = 'cli-fanout'
+  activePerspectives = perspectives.slice(0, 3)
+} else {
+  // CLI Fan-out: 所有视角
+  mode = 'cli-fanout'
+  activePerspectives = perspectives
+}
+```
+
+## Execution Steps
+
+### Step 1: Context Preparation
+
+```javascript
+// 确定扫描范围
+const projectRoot = Bash(`git rev-parse --show-toplevel 2>/dev/null || pwd`).trim()
+const scanScope = task.description.match(/scope:\s*(.+)/)?.[1] || '**/*'
+
+// 获取变更文件用于聚焦扫描
+const changedFiles = Bash(`git diff --name-only HEAD~5 2>/dev/null || echo ""`)
+  .split('\n').filter(Boolean)
+
+// 构建文件上下文
+const fileContext = changedFiles.length > 0
+  ? changedFiles.map(f => `@${f}`).join(' ')
+  : `@${scanScope}`
+
+// 已知缺陷模式（来自 shared memory）
+const knownPatternsText = knownPatterns.length > 0
+  ? `\nKnown defect patterns to verify: ${knownPatterns.map(p => p.description).join('; ')}`
+  : ''
+```
+
+### Step 2: Execute Strategy
+
+```javascript
+if (mode === 'inline') {
+  // 快速内联扫描
+  const aceResults = mcp__ace-tool__search_context({
+    project_root_path: projectRoot,
+    query: "potential bugs, error handling issues, unchecked return values, security vulnerabilities, missing input validation"
+  })
+
+  // 解析 ACE 结果并分类
+  for (const result of aceResults) {
+    classifyFinding(result)
+  }
+} else {
+  // CLI Fan-out: 每个视角一个 CLI 调用
+  const perspectivePrompts = {
+    'bug': `PURPOSE: Discover potential bugs and logic errors
+TASK: • Find unchecked return values • Identify race conditions • Check null/undefined handling • Find off-by-one errors • Detect resource leaks
+MODE: analysis
+CONTEXT: ${fileContext}${knownPatternsText}
+EXPECTED: List of findings with severity, file:line, description, and fix suggestion
+CONSTRAINTS: Focus on real bugs, avoid false positives`,
+
+    'security': `PURPOSE: Identify security vulnerabilities and risks
+TASK: • Check for injection flaws (SQL, command, XSS) • Find authentication/authorization gaps • Identify sensitive data exposure • Check input validation • Review crypto usage
+MODE: analysis
+CONTEXT: ${fileContext}
+EXPECTED: Security findings with CVSS-style severity, file:line, CWE references where applicable
+CONSTRAINTS: Focus on exploitable vulnerabilities`,
+
+    'test-coverage': `PURPOSE: Identify untested code paths and coverage gaps
+TASK: • Find functions/methods without tests • Identify complex logic without assertions • Check error paths without coverage • Find boundary conditions untested
+MODE: analysis
+CONTEXT: ${fileContext}
+EXPECTED: List of untested areas with file:line, complexity indicator, and test suggestion
+CONSTRAINTS: Focus on high-risk untested code`,
+
+    'code-quality': `PURPOSE: Detect code quality issues and anti-patterns
+TASK: • Find code duplication • Identify overly complex functions • Check naming conventions • Find dead code • Detect God objects/functions
+MODE: analysis
+CONTEXT: ${fileContext}
+EXPECTED: Quality findings with severity, file:line, and improvement suggestion
+CONSTRAINTS: Focus on maintainability impacts`,
+
+    'ux': `PURPOSE: Identify UX-impacting issues in code
+TASK: • Find missing loading states • Check error message quality • Identify accessibility gaps • Find inconsistent UI patterns • Check responsive handling
+MODE: analysis
+CONTEXT: ${fileContext}
+EXPECTED: UX findings with impact level, file:line, and user-facing description
+CONSTRAINTS: Focus on user-visible issues`
+  }
+
+  for (const perspective of activePerspectives) {
+    const prompt = perspectivePrompts[perspective]
+    if (!prompt) continue
+
+    Bash(`ccw cli -p "${prompt}" --tool gemini --mode analysis --rule analysis-assess-security-risks`, {
+      run_in_background: true
+    })
+  }
+
+  // 等待所有 CLI 完成（hook 回调通知）
+}
+```
+
+### Step 3: Result Processing
+
+```javascript
+// 聚合所有视角的结果
+const allFindings = { critical: [], high: [], medium: [], low: [] }
+
+// 从 CLI 输出解析结果
+for (const perspective of activePerspectives) {
+  const findings = parseCliOutput(cliResults[perspective])
+  for (const finding of findings) {
+    finding.perspective = perspective
+    allFindings[finding.severity].push(finding)
+  }
+}
+
+// 去重：相同 file:line 的发现合并
+function deduplicateFindings(findings) {
+  const seen = new Set()
+  const unique = []
+  for (const f of findings) {
+    const key = `${f.file}:${f.line}`
+    if (!seen.has(key)) {
+      seen.add(key)
+      unique.push(f)
+    } else {
+      // 合并视角信息到已有条目
+      const existing = unique.find(u => `${u.file}:${u.line}` === key)
+      if (existing) existing.perspectives = [...(existing.perspectives || [existing.perspective]), f.perspective]
+    }
+  }
+  return unique
+}
+
+for (const severity of ['critical', 'high', 'medium', 'low']) {
+  allFindings[severity] = deduplicateFindings(allFindings[severity])
+}
+
+// 与已知缺陷模式对比
+for (const pattern of knownPatterns) {
+  for (const severity of ['critical', 'high', 'medium', 'low']) {
+    for (const finding of allFindings[severity]) {
+      if (finding.file === pattern.file || finding.description.includes(pattern.type)) {
+        finding.known_pattern = true
+      }
+    }
+  }
+}
+```
+
+## Output Format
+
+```
+## Scan Results
+
+### Perspectives Scanned: [list]
+### Complexity: [Low|Medium|High]
+
+### Findings by Severity
+#### Critical ([count])
+- [file:line] [perspective] - [description]
+
+#### High ([count])
+- [file:line] [perspective] - [description]
+
+#### Medium ([count])
+- [file:line] - [description]
+
+#### Low ([count])
+- [file:line] - [description]
+
+### Known Pattern Matches: [count]
+### New Findings: [count]
+```
+
+## Error Handling
+
+| Scenario | Resolution |
+|----------|------------|
+| CLI tool unavailable | Fall back to ACE search + Grep inline analysis |
+| CLI returns empty for a perspective | Note incomplete perspective, continue others |
+| Too many findings (>50) | Prioritize critical/high, summarize medium/low |
+| Timeout on CLI call | Use partial results, note incomplete perspectives |
+| Agent/CLI failure | Retry once, then fallback to inline execution |
+| Timeout (>5 min) | Report partial results, notify coordinator |

.claude/skills/team-quality-assurance/roles/scout/role.md

@@ -0,0 +1,244 @@
+# Role: scout
+
+多视角问题侦察员。主动扫描代码库，从 bug、安全、UX、测试覆盖、代码质量等多个视角发现潜在问题，创建结构化 issue。融合 issue-discover 的多视角扫描能力。
+
+## Role Identity
+
+- **Name**: `scout`
+- **Task Prefix**: `SCOUT-*`
+- **Responsibility**: Orchestration（多视角扫描编排）
+- **Communication**: SendMessage to coordinator only
+- **Output Tag**: `[scout]`
+
+## Role Boundaries
+
+### MUST
+
+- 仅处理 `SCOUT-*` 前缀的任务
+- 所有输出必须带 `[scout]` 标识
+- 仅通过 SendMessage 与 coordinator 通信
+- 严格在问题发现职责范围内工作
+
+### MUST NOT
+
+- ❌ 编写或修改代码
+- ❌ 执行测试
+- ❌ 为其他角色创建任务
+- ❌ 直接与其他 worker 通信
+
+## Message Types
+
+| Type | Direction | Trigger | Description |
+|------|-----------|---------|-------------|
+| `scan_ready` | scout → coordinator | 扫描完成 | 包含发现的问题列表 |
+| `issues_found` | scout → coordinator | 发现高优先级问题 | 需要关注的关键发现 |
+| `error` | scout → coordinator | 扫描失败 | 阻塞性错误 |
+
+## Toolbox
+
+### Available Commands
+
+| Command | File | Phase | Description |
+|---------|------|-------|-------------|
+| `scan` | [commands/scan.md](commands/scan.md) | Phase 3 | 多视角 CLI Fan-out 扫描 |
+
+### Subagent Capabilities
+
+| Agent Type | Used By | Purpose |
+|------------|---------|---------|
+| `cli-explore-agent` | scan.md | 多角度代码库探索 |
+
+### CLI Capabilities
+
+| CLI Tool | Mode | Used By | Purpose |
+|----------|------|---------|---------|
+| `gemini` | analysis | scan.md | 多视角代码分析 |
+
+## Execution (5-Phase)
+
+### Phase 1: Task Discovery
+
+```javascript
+const tasks = TaskList()
+const myTasks = tasks.filter(t =>
+  t.subject.startsWith('SCOUT-') &&
+  t.owner === 'scout' &&
+  t.status === 'pending' &&
+  t.blockedBy.length === 0
+)
+
+if (myTasks.length === 0) return // idle
+
+const task = TaskGet({ taskId: myTasks[0].id })
+TaskUpdate({ taskId: task.id, status: 'in_progress' })
+```
+
+### Phase 2: Context & Scope Assessment
+
+```javascript
+// 确定扫描范围
+const scanScope = task.description.match(/scope:\s*(.+)/)?.[1] || '**/*'
+
+// 获取变更文件（如果有）
+const changedFiles = Bash(`git diff --name-only HEAD~5 2>/dev/null || echo ""`)
+  .split('\n').filter(Boolean)
+
+// 读取 shared memory 获取历史缺陷模式
+const sessionFolder = task.description.match(/session:\s*(.+)/)?.[1] || '.'
+let sharedMemory = {}
+try { sharedMemory = JSON.parse(Read(`${sessionFolder}/shared-memory.json`)) } catch {}
+const knownPatterns = sharedMemory.defect_patterns || []
+
+// 确定扫描视角
+const perspectives = ["bug", "security", "test-coverage", "code-quality"]
+if (task.description.includes('ux')) perspectives.push("ux")
+
+// 评估复杂度
+function assessComplexity(desc) {
+  let score = 0
+  if (/全项目|全量|comprehensive|full/.test(desc)) score += 3
+  if (/security|安全/.test(desc)) score += 1
+  if (/multiple|across|cross|多模块/.test(desc)) score += 2
+  return score >= 4 ? 'High' : score >= 2 ? 'Medium' : 'Low'
+}
+const complexity = assessComplexity(task.description)
+```
+
+### Phase 3: Multi-Perspective Scan
+
+```javascript
+// Read commands/scan.md for full CLI Fan-out implementation
+Read("commands/scan.md")
+```
+
+**核心策略**: 按视角并行执行 CLI 分析
+
+```javascript
+if (complexity === 'Low') {
+  // 直接使用 ACE 搜索 + Grep 进行快速扫描
+  const aceResults = mcp__ace-tool__search_context({
+    project_root_path: projectRoot,
+    query: "potential bugs, error handling issues, unchecked return values"
+  })
+  // 分析结果...
+} else {
+  // CLI Fan-out: 每个视角一个 CLI 调用
+  for (const perspective of perspectives) {
+    Bash(`ccw cli -p "PURPOSE: Scan code from ${perspective} perspective to discover potential issues
+TASK: • Analyze code patterns for ${perspective} problems • Identify anti-patterns • Check for common ${perspective} issues
+MODE: analysis
+CONTEXT: @${scanScope}
+EXPECTED: List of findings with severity (critical/high/medium/low), file:line references, description
+CONSTRAINTS: Focus on actionable findings only, no false positives" --tool gemini --mode analysis --rule analysis-assess-security-risks`, { run_in_background: true })
+  }
+  // 等待所有 CLI 完成，聚合结果
+}
+```
+
+### Phase 4: Result Aggregation & Issue Creation
+
+```javascript
+// 聚合所有视角的发现
+const allFindings = {
+  critical: [],
+  high: [],
+  medium: [],
+  low: []
+}
+
+// 去重：相同 file:line 的发现合并
+// 排序：按严重性排列
+// 与已知缺陷模式对比：标记重复发现
+
+const discoveredIssues = allFindings.critical
+  .concat(allFindings.high)
+  .map((f, i) => ({
+    id: `SCOUT-ISSUE-${i + 1}`,
+    severity: f.severity,
+    perspective: f.perspective,
+    file: f.file,
+    line: f.line,
+    description: f.description,
+    suggestion: f.suggestion
+  }))
+
+// 更新 shared memory
+sharedMemory.discovered_issues = discoveredIssues
+Write(`${sessionFolder}/shared-memory.json`, JSON.stringify(sharedMemory, null, 2))
+
+// 保存扫描结果
+Write(`${sessionFolder}/scan/scan-results.json`, JSON.stringify({
+  scan_date: new Date().toISOString(),
+  perspectives: perspectives,
+  total_findings: Object.values(allFindings).flat().length,
+  by_severity: {
+    critical: allFindings.critical.length,
+    high: allFindings.high.length,
+    medium: allFindings.medium.length,
+    low: allFindings.low.length
+  },
+  findings: allFindings,
+  issues_created: discoveredIssues.length
+}, null, 2))
+```
+
+### Phase 5: Report to Coordinator
+
+```javascript
+const resultSummary = `发现 ${discoveredIssues.length} 个问题（Critical: ${allFindings.critical.length}, High: ${allFindings.high.length}, Medium: ${allFindings.medium.length}, Low: ${allFindings.low.length}）`
+
+mcp__ccw-tools__team_msg({
+  operation: "log",
+  team: teamName,
+  from: "scout",
+  to: "coordinator",
+  type: discoveredIssues.length > 0 ? "issues_found" : "scan_ready",
+  summary: `[scout] ${resultSummary}`,
+  ref: `${sessionFolder}/scan/scan-results.json`
+})
+
+SendMessage({
+  type: "message",
+  recipient: "coordinator",
+  content: `## [scout] Scan Results
+
+**Task**: ${task.subject}
+**Perspectives**: ${perspectives.join(', ')}
+**Status**: ${discoveredIssues.length > 0 ? 'Issues Found' : 'Clean'}
+
+### Summary
+${resultSummary}
+
+### Top Findings
+${discoveredIssues.slice(0, 5).map(i => `- **[${i.severity}]** ${i.file}:${i.line} - ${i.description}`).join('\n')}
+
+### Scan Report
+${sessionFolder}/scan/scan-results.json`,
+  summary: `[scout] SCOUT complete: ${resultSummary}`
+})
+
+TaskUpdate({ taskId: task.id, status: 'completed' })
+
+// Check for next task
+const nextTasks = TaskList().filter(t =>
+  t.subject.startsWith('SCOUT-') &&
+  t.owner === 'scout' &&
+  t.status === 'pending' &&
+  t.blockedBy.length === 0
+)
+
+if (nextTasks.length > 0) {
+  // Continue with next task → back to Phase 1
+}
+```
+
+## Error Handling
+
+| Scenario | Resolution |
+|----------|------------|
+| No SCOUT-* tasks available | Idle, wait for coordinator assignment |
+| CLI tool unavailable | Fall back to ACE search + Grep inline analysis |
+| Scan scope too broad | Narrow to changed files only, report partial results |
+| All perspectives return empty | Report clean scan, notify coordinator |
+| CLI timeout | Use partial results, note incomplete perspectives |
+| Critical issue beyond scope | SendMessage issues_found to coordinator |

.claude/skills/team-quality-assurance/roles/strategist/commands/analyze-scope.md

@@ -0,0 +1,221 @@
+# Command: analyze-scope
+
+> 变更范围分析 + 测试策略制定。分析代码变更、scout 发现和项目结构，确定测试层级和覆盖率目标。
+
+## When to Use
+
+- Phase 2-3 of Strategist
+- 需要分析代码变更范围
+- 需要将 scout 发现转化为测试策略
+
+**Trigger conditions**:
+- QASTRAT-* 任务进入执行阶段
+- 变更文件数 > 5 需要 CLI 辅助分析
+- 存在 scout 发现的高优先级问题
+
+## Strategy
+
+### Delegation Mode
+
+**Mode**: CLI Fan-out（复杂项目）/ Direct（简单项目）
+**CLI Tool**: `gemini` (primary)
+**CLI Mode**: `analysis`
+
+### Decision Logic
+
+```javascript
+const totalScope = changedFiles.length + discoveredIssues.length
+if (totalScope <= 5) {
+  // 直接内联分析
+  mode = 'direct'
+} else if (totalScope <= 15) {
+  // 单次 CLI 分析
+  mode = 'single-cli'
+} else {
+  // 多维度 CLI 分析
+  mode = 'multi-cli'
+}
+```
+
+## Execution Steps
+
+### Step 1: Context Preparation
+
+```javascript
+// 从 shared memory 获取 scout 发现
+const discoveredIssues = sharedMemory.discovered_issues || []
+
+// 分析 git diff 获取变更范围
+const changedFiles = Bash(`git diff --name-only HEAD~5 2>/dev/null || git diff --name-only --cached 2>/dev/null || echo ""`)
+  .split('\n').filter(Boolean)
+
+// 分类变更文件
+const fileCategories = {
+  source: changedFiles.filter(f => /\.(ts|tsx|js|jsx|py|java|go|rs)$/.test(f)),
+  test: changedFiles.filter(f => /\.(test|spec)\.(ts|tsx|js|jsx)$/.test(f) || /test_/.test(f)),
+  config: changedFiles.filter(f => /\.(json|yaml|yml|toml|env)$/.test(f)),
+  style: changedFiles.filter(f => /\.(css|scss|less)$/.test(f)),
+  docs: changedFiles.filter(f => /\.(md|txt|rst)$/.test(f))
+}
+
+// 检测项目测试框架
+const packageJson = Read('package.json')
+const testFramework = detectFramework(packageJson)
+
+// 获取已有测试覆盖率基线
+let baselineCoverage = null
+try {
+  const coverageSummary = JSON.parse(Read('coverage/coverage-summary.json'))
+  baselineCoverage = coverageSummary.total?.lines?.pct || null
+} catch {}
+```
+
+### Step 2: Execute Strategy
+
+```javascript
+if (mode === 'direct') {
+  // 内联分析：直接构建策略
+  buildStrategyDirect(fileCategories, discoveredIssues, testFramework)
+} else if (mode === 'single-cli') {
+  // 单次 CLI 综合分析
+  Bash(`ccw cli -p "PURPOSE: Analyze code changes and scout findings to determine optimal test strategy
+TASK: • Classify ${changedFiles.length} changed files by risk level • Map ${discoveredIssues.length} scout issues to test requirements • Identify integration points between changed modules • Recommend test layers (L1/L2/L3) with coverage targets
+MODE: analysis
+CONTEXT: @${changedFiles.slice(0, 20).join(' @')} | Memory: Scout found ${discoveredIssues.length} issues, baseline coverage ${baselineCoverage || 'unknown'}%
+EXPECTED: JSON with layers array, each containing level, name, target_coverage, focus_files, rationale
+CONSTRAINTS: Be conservative with L3 E2E tests | Focus L1 on changed source files" --tool gemini --mode analysis --rule analysis-analyze-code-patterns`, {
+    run_in_background: true
+  })
+  // 等待 CLI 完成
+} else {
+  // 多维度分析
+  // Dimension 1: 变更风险分析
+  Bash(`ccw cli -p "PURPOSE: Assess risk level of code changes
+TASK: • Classify each file by change risk (high/medium/low) • Identify files touching critical paths • Map dependency chains
+MODE: analysis
+CONTEXT: @${fileCategories.source.join(' @')}
+EXPECTED: Risk matrix with file:risk_level mapping
+CONSTRAINTS: Focus on source files only" --tool gemini --mode analysis`, {
+    run_in_background: true
+  })
+
+  // Dimension 2: 测试覆盖差距分析
+  Bash(`ccw cli -p "PURPOSE: Identify test coverage gaps for changed code
+TASK: • Find changed functions without tests • Map test files to source files • Identify missing integration test scenarios
+MODE: analysis
+CONTEXT: @${[...fileCategories.source, ...fileCategories.test].join(' @')}
+EXPECTED: Coverage gap report with untested functions and modules
+CONSTRAINTS: Compare existing tests to changed code" --tool gemini --mode analysis`, {
+    run_in_background: true
+  })
+  // 等待所有 CLI 完成
+}
+```
+
+### Step 3: Result Processing
+
+```javascript
+// 构建测试策略
+const strategy = {
+  scope: {
+    total_changed: changedFiles.length,
+    source_files: fileCategories.source.length,
+    test_files: fileCategories.test.length,
+    issue_count: discoveredIssues.length,
+    baseline_coverage: baselineCoverage
+  },
+  test_framework: testFramework,
+  layers: [],
+  coverage_targets: {}
+}
+
+// 层级选择算法
+// L1: Unit Tests - 所有有源码变更的文件
+if (fileCategories.source.length > 0 || discoveredIssues.length > 0) {
+  const l1Files = fileCategories.source.length > 0
+    ? fileCategories.source
+    : [...new Set(discoveredIssues.map(i => i.file))]
+
+  strategy.layers.push({
+    level: 'L1',
+    name: 'Unit Tests',
+    target_coverage: 80,
+    focus_files: l1Files,
+    rationale: fileCategories.source.length > 0
+      ? '所有变更的源文件需要单元测试覆盖'
+      : 'Scout 发现的问题需要测试覆盖'
+  })
+}
+
+// L2: Integration Tests - 多模块变更或关键问题
+if (fileCategories.source.length >= 3 || discoveredIssues.some(i => i.severity === 'critical')) {
+  const integrationPoints = fileCategories.source
+    .filter(f => /service|controller|handler|middleware|route|api/.test(f))
+
+  if (integrationPoints.length > 0) {
+    strategy.layers.push({
+      level: 'L2',
+      name: 'Integration Tests',
+      target_coverage: 60,
+      focus_areas: integrationPoints,
+      rationale: '多文件变更涉及模块间交互，需要集成测试'
+    })
+  }
+}
+
+// L3: E2E Tests - 大量高优先级问题
+const criticalHighCount = discoveredIssues
+  .filter(i => i.severity === 'critical' || i.severity === 'high').length
+if (criticalHighCount >= 3) {
+  strategy.layers.push({
+    level: 'L3',
+    name: 'E2E Tests',
+    target_coverage: 40,
+    focus_flows: [...new Set(discoveredIssues
+      .filter(i => i.severity === 'critical' || i.severity === 'high')
+      .map(i => i.file.split('/')[1] || 'main'))],
+    rationale: `${criticalHighCount} 个高优先级问题需要端到端验证`
+  })
+}
+
+// 设置覆盖率目标
+for (const layer of strategy.layers) {
+  strategy.coverage_targets[layer.level] = layer.target_coverage
+}
+```
+
+## Output Format
+
+```
+## Test Strategy
+
+### Scope Analysis
+- Changed files: [count]
+- Source files: [count]
+- Scout issues: [count]
+- Baseline coverage: [percent]%
+
+### Test Layers
+#### L1: Unit Tests
+- Coverage target: 80%
+- Focus files: [list]
+
+#### L2: Integration Tests (if applicable)
+- Coverage target: 60%
+- Focus areas: [list]
+
+#### L3: E2E Tests (if applicable)
+- Coverage target: 40%
+- Focus flows: [list]
+```
+
+## Error Handling
+
+| Scenario | Resolution |
+|----------|------------|
+| No changed files | Use scout issues as scope |
+| No scout issues | Generate L1 tests for all source files |
+| Test framework unknown | Default to Jest/Vitest (JS/TS) or pytest (Python) |
+| CLI analysis returns unusable results | Fall back to heuristic-based strategy |
+| Agent/CLI failure | Retry once, then fallback to inline execution |
+| Timeout (>5 min) | Report partial results, notify coordinator |

.claude/skills/team-quality-assurance/roles/strategist/role.md

@@ -0,0 +1,266 @@
+# Role: strategist
+
+测试策略师。分析变更范围，确定测试层级（L1-L3），定义覆盖率目标，生成测试策略文档。基于 scout 发现的问题和代码变更制定针对性测试计划。
+
+## Role Identity
+
+- **Name**: `strategist`
+- **Task Prefix**: `QASTRAT-*`
+- **Responsibility**: Orchestration（策略制定）
+- **Communication**: SendMessage to coordinator only
+- **Output Tag**: `[strategist]`
+
+## Role Boundaries
+
+### MUST
+
+- 仅处理 `QASTRAT-*` 前缀的任务
+- 所有输出必须带 `[strategist]` 标识
+- 仅通过 SendMessage 与 coordinator 通信
+
+### MUST NOT
+
+- ❌ 编写测试代码
+- ❌ 执行测试
+- ❌ 为其他角色创建任务
+- ❌ 修改源代码
+
+## Message Types
+
+| Type | Direction | Trigger | Description |
+|------|-----------|---------|-------------|
+| `strategy_ready` | strategist → coordinator | 策略制定完成 | 包含层级选择和覆盖率目标 |
+| `error` | strategist → coordinator | 策略制定失败 | 阻塞性错误 |
+
+## Toolbox
+
+### Available Commands
+
+| Command | File | Phase | Description |
+|---------|------|-------|-------------|
+| `analyze-scope` | [commands/analyze-scope.md](commands/analyze-scope.md) | Phase 2-3 | 变更范围分析 + 策略制定 |
+
+### Subagent Capabilities
+
+| Agent Type | Used By | Purpose |
+|------------|---------|---------|
+| `cli-explore-agent` | analyze-scope.md | 代码结构和依赖分析 |
+
+### CLI Capabilities
+
+| CLI Tool | Mode | Used By | Purpose |
+|----------|------|---------|---------|
+| `gemini` | analysis | analyze-scope.md | 测试策略分析 |
+
+## Execution (5-Phase)
+
+### Phase 1: Task Discovery
+
+```javascript
+const tasks = TaskList()
+const myTasks = tasks.filter(t =>
+  t.subject.startsWith('QASTRAT-') &&
+  t.owner === 'strategist' &&
+  t.status === 'pending' &&
+  t.blockedBy.length === 0
+)
+
+if (myTasks.length === 0) return
+const task = TaskGet({ taskId: myTasks[0].id })
+TaskUpdate({ taskId: task.id, status: 'in_progress' })
+```
+
+### Phase 2: Context & Change Analysis
+
+```javascript
+// 读取 shared memory 获取 scout 发现
+const sessionFolder = task.description.match(/session:\s*(.+)/)?.[1] || '.'
+let sharedMemory = {}
+try { sharedMemory = JSON.parse(Read(`${sessionFolder}/shared-memory.json`)) } catch {}
+
+const discoveredIssues = sharedMemory.discovered_issues || []
+const historicalPatterns = sharedMemory.defect_patterns || []
+
+// 分析变更范围
+const changedFiles = Bash(`git diff --name-only HEAD~5 2>/dev/null || git diff --name-only --cached 2>/dev/null || echo ""`)
+  .split('\n').filter(Boolean)
+
+// 分类变更文件
+const fileCategories = {
+  source: changedFiles.filter(f => /\.(ts|tsx|js|jsx|py|java|go|rs)$/.test(f)),
+  test: changedFiles.filter(f => /\.(test|spec)\.(ts|tsx|js|jsx)$/.test(f) || /test_/.test(f)),
+  config: changedFiles.filter(f => /\.(json|yaml|yml|toml|env)$/.test(f)),
+  style: changedFiles.filter(f => /\.(css|scss|less)$/.test(f))
+}
+
+// 检测项目测试框架
+const testFramework = Bash(`ls package.json 2>/dev/null && (cat package.json | grep -o '"jest"\\|"vitest"\\|"mocha"\\|"pytest"' | head -1) || echo "unknown"`)
+  .trim().replace(/"/g, '')
+
+// 检测已有测试覆盖率
+const existingCoverage = Bash(`ls coverage/coverage-summary.json 2>/dev/null && cat coverage/coverage-summary.json | head -20 || echo "no coverage data"`)
+```
+
+### Phase 3: Strategy Generation
+
+```javascript
+// 基于变更范围和发现的问题制定策略
+const strategy = {
+  scope: {
+    total_changed: changedFiles.length,
+    source_files: fileCategories.source.length,
+    test_files: fileCategories.test.length,
+    issue_count: discoveredIssues.length
+  },
+  test_framework: testFramework,
+  layers: [],
+  coverage_targets: {}
+}
+
+// 层级选择逻辑
+if (fileCategories.source.length > 0) {
+  strategy.layers.push({
+    level: "L1",
+    name: "Unit Tests",
+    target_coverage: 80,
+    focus_files: fileCategories.source,
+    rationale: "所有变更的源文件需要单元测试覆盖"
+  })
+}
+
+if (fileCategories.source.length >= 3 || discoveredIssues.some(i => i.severity === 'critical')) {
+  strategy.layers.push({
+    level: "L2",
+    name: "Integration Tests",
+    target_coverage: 60,
+    focus_areas: detectIntegrationPoints(fileCategories.source),
+    rationale: "多文件变更或关键问题需要集成测试"
+  })
+}
+
+if (discoveredIssues.filter(i => i.severity === 'critical' || i.severity === 'high').length >= 3) {
+  strategy.layers.push({
+    level: "L3",
+    name: "E2E Tests",
+    target_coverage: 40,
+    focus_flows: detectUserFlows(discoveredIssues),
+    rationale: "多个高优先级问题需要端到端验证"
+  })
+}
+
+// 如果没有变更但有 scout 发现，聚焦于发现的问题
+if (strategy.layers.length === 0 && discoveredIssues.length > 0) {
+  strategy.layers.push({
+    level: "L1",
+    name: "Unit Tests",
+    target_coverage: 80,
+    focus_files: [...new Set(discoveredIssues.map(i => i.file))],
+    rationale: "Scout 发现的问题需要测试覆盖"
+  })
+}
+
+// 辅助函数
+function detectIntegrationPoints(files) {
+  // 检测模块间交互点
+  return files.filter(f => /service|controller|handler|middleware|route/.test(f))
+}
+
+function detectUserFlows(issues) {
+  // 从问题中推断用户流程
+  return [...new Set(issues.map(i => i.file.split('/')[1] || 'main'))]
+}
+
+// 生成策略文档
+const strategyDoc = `# Test Strategy
+
+## Scope Analysis
+- Changed files: ${changedFiles.length}
+- Source files: ${fileCategories.source.length}
+- Scout issues: ${discoveredIssues.length}
+- Test framework: ${testFramework}
+
+## Test Layers
+${strategy.layers.map(l => `### ${l.level}: ${l.name}
+- Coverage target: ${l.target_coverage}%
+- Focus: ${l.focus_files?.join(', ') || l.focus_areas?.join(', ') || l.focus_flows?.join(', ')}
+- Rationale: ${l.rationale}`).join('\n\n')}
+
+## Priority Issues
+${discoveredIssues.slice(0, 10).map(i => `- [${i.severity}] ${i.file}:${i.line} - ${i.description}`).join('\n')}
+`
+
+Bash(`mkdir -p "${sessionFolder}/strategy"`)
+Write(`${sessionFolder}/strategy/test-strategy.md`, strategyDoc)
+
+// 更新 shared memory
+sharedMemory.test_strategy = strategy
+Write(`${sessionFolder}/shared-memory.json`, JSON.stringify(sharedMemory, null, 2))
+```
+
+### Phase 4: Strategy Validation
+
+```javascript
+// 验证策略合理性
+const validationChecks = {
+  has_layers: strategy.layers.length > 0,
+  has_targets: strategy.layers.every(l => l.target_coverage > 0),
+  covers_issues: discoveredIssues.length === 0 ||
+    discoveredIssues.some(i => strategy.layers.some(l =>
+      l.focus_files?.includes(i.file)
+    )),
+  framework_detected: testFramework !== 'unknown'
+}
+
+const isValid = Object.values(validationChecks).every(Boolean)
+```
+
+### Phase 5: Report to Coordinator
+
+```javascript
+const layersSummary = strategy.layers.map(l => `${l.level}(${l.target_coverage}%)`).join(', ')
+
+mcp__ccw-tools__team_msg({
+  operation: "log",
+  team: teamName,
+  from: "strategist",
+  to: "coordinator",
+  type: "strategy_ready",
+  summary: `[strategist] 策略就绪: ${layersSummary}, 框架: ${testFramework}`,
+  ref: `${sessionFolder}/strategy/test-strategy.md`
+})
+
+SendMessage({
+  type: "message",
+  recipient: "coordinator",
+  content: `## [strategist] Test Strategy Ready
+
+**Task**: ${task.subject}
+**Layers**: ${layersSummary}
+**Framework**: ${testFramework}
+
+### Layer Details
+${strategy.layers.map(l => `- **${l.level}**: ${l.name} (target: ${l.target_coverage}%, ${l.focus_files?.length || '?'} files)`).join('\n')}
+
+### Strategy Document
+${sessionFolder}/strategy/test-strategy.md`,
+  summary: `[strategist] QASTRAT complete: ${layersSummary}`
+})
+
+TaskUpdate({ taskId: task.id, status: 'completed' })
+
+const nextTasks = TaskList().filter(t =>
+  t.subject.startsWith('QASTRAT-') && t.owner === 'strategist' &&
+  t.status === 'pending' && t.blockedBy.length === 0
+)
+if (nextTasks.length > 0) { /* back to Phase 1 */ }
+```
+
+## Error Handling
+
+| Scenario | Resolution |
+|----------|------------|
+| No QASTRAT-* tasks available | Idle, wait for coordinator |
+| No changed files detected | Use scout issues as scope, or scan full project |
+| Test framework unknown | Default to Jest/Vitest for JS/TS, pytest for Python |
+| Shared memory not found | Create with defaults, proceed |
+| Critical issue beyond scope | SendMessage error to coordinator |

.claude/skills/team-quality-assurance/specs/team-config.json

@@ -0,0 +1,131 @@
+{
+  "team_name": "quality-assurance",
+  "version": "1.0.0",
+  "description": "质量保障团队 - 融合\"软件测试\"和\"问题发现\"两大能力域，形成发现→验证→修复→回归的闭环",
+  "skill_entry": "team-quality-assurance",
+  "invocation": "Skill(skill=\"team-quality-assurance\", args=\"--role=coordinator ...\")",
+
+  "roles": {
+    "coordinator": {
+      "name": "coordinator",
+      "responsibility": "Orchestration",
+      "task_prefix": null,
+      "description": "QA 团队协调者。编排 pipeline：需求澄清 → 模式选择 → 团队创建 → 任务分发 → 监控协调 → 质量门控 → 结果汇报",
+      "message_types_sent": ["mode_selected", "gc_loop_trigger", "quality_gate", "task_unblocked", "error", "shutdown"],
+      "message_types_received": ["scan_ready", "issues_found", "strategy_ready", "tests_generated", "tests_revised", "tests_passed", "tests_failed", "analysis_ready", "quality_report", "error"],
+      "commands": ["dispatch", "monitor"]
+    },
+    "scout": {
+      "name": "scout",
+      "responsibility": "Orchestration (多视角扫描编排)",
+      "task_prefix": "SCOUT-*",
+      "description": "多视角问题侦察员。主动扫描代码库，从 bug、安全、UX、测试覆盖、代码质量等多个视角发现潜在问题",
+      "message_types_sent": ["scan_ready", "issues_found", "error"],
+      "message_types_received": [],
+      "commands": ["scan"],
+      "cli_tools": ["gemini"],
+      "subagents": ["cli-explore-agent"]
+    },
+    "strategist": {
+      "name": "strategist",
+      "responsibility": "Orchestration (策略制定)",
+      "task_prefix": "QASTRAT-*",
+      "description": "测试策略师。分析变更范围，确定测试层级（L1-L3），定义覆盖率目标",
+      "message_types_sent": ["strategy_ready", "error"],
+      "message_types_received": [],
+      "commands": ["analyze-scope"],
+      "cli_tools": ["gemini"],
+      "subagents": ["cli-explore-agent"]
+    },
+    "generator": {
+      "name": "generator",
+      "responsibility": "Code generation (测试代码生成)",
+      "task_prefix": "QAGEN-*",
+      "description": "测试用例生成器。按策略和层级生成测试代码，支持 L1/L2/L3",
+      "message_types_sent": ["tests_generated", "tests_revised", "error"],
+      "message_types_received": [],
+      "commands": ["generate-tests"],
+      "cli_tools": ["gemini"],
+      "subagents": ["code-developer"]
+    },
+    "executor": {
+      "name": "executor",
+      "responsibility": "Validation (测试执行与修复)",
+      "task_prefix": "QARUN-*",
+      "description": "测试执行者。运行测试套件，收集覆盖率数据，失败时自动修复循环",
+      "message_types_sent": ["tests_passed", "tests_failed", "coverage_report", "error"],
+      "message_types_received": [],
+      "commands": ["run-fix-cycle"],
+      "subagents": ["code-developer"]
+    },
+    "analyst": {
+      "name": "analyst",
+      "responsibility": "Read-only analysis (质量分析)",
+      "task_prefix": "QAANA-*",
+      "description": "质量分析师。分析缺陷模式、覆盖率差距、测试有效性，生成综合质量报告",
+      "message_types_sent": ["analysis_ready", "quality_report", "error"],
+      "message_types_received": [],
+      "commands": ["quality-report"],
+      "cli_tools": ["gemini"]
+    }
+  },
+
+  "pipeline_modes": {
+    "discovery": {
+      "description": "Scout先行扫描 → 全流程",
+      "stages": ["SCOUT", "QASTRAT", "QAGEN", "QARUN", "QAANA"],
+      "entry_role": "scout"
+    },
+    "testing": {
+      "description": "跳过 Scout → 直接测试",
+      "stages": ["QASTRAT", "QAGEN-L1", "QARUN-L1", "QAGEN-L2", "QARUN-L2", "QAANA"],
+      "entry_role": "strategist"
+    },
+    "full": {
+      "description": "完整 QA 闭环 + 回归扫描",
+      "stages": ["SCOUT", "QASTRAT", "QAGEN-L1", "QAGEN-L2", "QARUN-L1", "QARUN-L2", "QAANA", "SCOUT-REG"],
+      "entry_role": "scout",
+      "parallel_stages": [["QAGEN-L1", "QAGEN-L2"], ["QARUN-L1", "QARUN-L2"]]
+    }
+  },
+
+  "gc_loop": {
+    "max_iterations": 3,
+    "trigger": "coverage < target",
+    "participants": ["generator", "executor"],
+    "flow": "QAGEN-fix → QARUN-gc → evaluate"
+  },
+
+  "shared_memory": {
+    "file": "shared-memory.json",
+    "fields": {
+      "discovered_issues": { "owner": "scout", "type": "array" },
+      "test_strategy": { "owner": "strategist", "type": "object" },
+      "generated_tests": { "owner": "generator", "type": "object" },
+      "execution_results": { "owner": "executor", "type": "object" },
+      "defect_patterns": { "owner": "analyst", "type": "array" },
+      "coverage_history": { "owner": "analyst", "type": "array" },
+      "quality_score": { "owner": "analyst", "type": "number" }
+    }
+  },
+
+  "collaboration_patterns": [
+    "CP-1: Linear Pipeline (Discovery/Testing mode)",
+    "CP-2: Review-Fix Cycle (GC loop: Generator ↔ Executor)",
+    "CP-3: Fan-out (Scout multi-perspective scan)",
+    "CP-5: Escalation (Worker → Coordinator → User)",
+    "CP-9: Dual-Track (Full mode: L1 + L2 parallel)",
+    "CP-10: Post-Mortem (Analyst quality report)"
+  ],
+
+  "session_directory": {
+    "pattern": ".workflow/.team/QA-{slug}-{date}",
+    "subdirectories": ["scan", "strategy", "results", "analysis"]
+  },
+
+  "test_layers": {
+    "L1": { "name": "Unit Tests", "default_target": 80 },
+    "L2": { "name": "Integration Tests", "default_target": 60 },
+    "L3": { "name": "E2E Tests", "default_target": 40 }
+  }
+}

ccw/frontend/src/test/i18n.tsx

@@ -157,6 +157,7 @@ const mockMessages: Record<Locale, Record<string, string>> = {
     'codexlens.envGroup.reranker': 'Reranker',
     'codexlens.envGroup.concurrency': 'Concurrency',
     'codexlens.envGroup.cascade': 'Cascade Search',
+    'codexlens.envGroup.indexing': 'Indexing',
     'codexlens.envGroup.chunking': 'Chunking',
     'codexlens.envField.backend': 'Backend',
     'codexlens.envField.model': 'Model',
@@ -175,6 +176,9 @@ const mockMessages: Record<Locale, Record<string, string>> = {
     'codexlens.envField.searchStrategy': 'Search Strategy',
     'codexlens.envField.coarseK': 'Coarse K',
     'codexlens.envField.fineK': 'Fine K',
+    'codexlens.envField.useAstGrep': 'Use ast-grep',
+    'codexlens.envField.staticGraphEnabled': 'Static Graph',
+    'codexlens.envField.staticGraphRelationshipTypes': 'Relationship Types',
     'codexlens.envField.stripComments': 'Strip Comments',
     'codexlens.envField.stripDocstrings': 'Strip Docstrings',
     'codexlens.envField.testFilePenalty': 'Test File Penalty',
@@ -421,6 +425,7 @@ const mockMessages: Record<Locale, Record<string, string>> = {
     'codexlens.envGroup.reranker': '重排序',
     'codexlens.envGroup.concurrency': '并发',
     'codexlens.envGroup.cascade': '级联搜索',
+    'codexlens.envGroup.indexing': '索引与解析',
     'codexlens.envGroup.chunking': '分块',
     'codexlens.envField.backend': '后端',
     'codexlens.envField.model': '模型',
@@ -439,6 +444,9 @@ const mockMessages: Record<Locale, Record<string, string>> = {
     'codexlens.envField.searchStrategy': '搜索策略',
     'codexlens.envField.coarseK': '粗筛 K 值',
     'codexlens.envField.fineK': '精筛 K 值',
+    'codexlens.envField.useAstGrep': '使用 ast-grep',
+    'codexlens.envField.staticGraphEnabled': '启用静态图',
+    'codexlens.envField.staticGraphRelationshipTypes': '关系类型',
     'codexlens.envField.stripComments': '去除注释',
     'codexlens.envField.stripDocstrings': '去除文档字符串',
     'codexlens.envField.testFilePenalty': '测试文件惩罚',

ccw/src/core/routes/codexlens/config-handlers.ts

@@ -915,6 +915,21 @@ export async function handleCodexLensConfigRoutes(ctx: RouteContext): Promise<bo
         settingsDefaults['CODEXLENS_LLM_BATCH_SIZE'] = String(settings.llm.batch_size);
       }
 
+      // Parsing / indexing settings
+      if (settings.parsing?.use_astgrep !== undefined) {
+        settingsDefaults['CODEXLENS_USE_ASTGREP'] = String(settings.parsing.use_astgrep);
+      }
+      if (settings.indexing?.static_graph_enabled !== undefined) {
+        settingsDefaults['CODEXLENS_STATIC_GRAPH_ENABLED'] = String(settings.indexing.static_graph_enabled);
+      }
+      if (settings.indexing?.static_graph_relationship_types !== undefined) {
+        if (Array.isArray(settings.indexing.static_graph_relationship_types)) {
+          settingsDefaults['CODEXLENS_STATIC_GRAPH_RELATIONSHIP_TYPES'] = settings.indexing.static_graph_relationship_types.join(',');
+        } else if (typeof settings.indexing.static_graph_relationship_types === 'string') {
+          settingsDefaults['CODEXLENS_STATIC_GRAPH_RELATIONSHIP_TYPES'] = settings.indexing.static_graph_relationship_types;
+        }
+      }
+
       res.writeHead(200, { 'Content-Type': 'application/json' });
       res.end(JSON.stringify({
         success: true,
@@ -1080,7 +1095,7 @@ export async function handleCodexLensConfigRoutes(ctx: RouteContext): Promise<bo
           settings = JSON.parse(settingsContent);
         } catch {
           // File doesn't exist, create default structure
-          settings = { embedding: {}, reranker: {}, api: {}, cascade: {}, llm: {} };
+          settings = { embedding: {}, reranker: {}, api: {}, cascade: {}, llm: {}, parsing: {}, indexing: {} };
         }
 
         // Map env vars to settings.json structure
@@ -1105,6 +1120,15 @@ export async function handleCodexLensConfigRoutes(ctx: RouteContext): Promise<bo
           'CODEXLENS_CASCADE_FINE_K': { path: ['cascade', 'fine_k'], transform: v => parseInt(v, 10) },
           'CODEXLENS_LLM_ENABLED': { path: ['llm', 'enabled'], transform: v => v === 'true' },
           'CODEXLENS_LLM_BATCH_SIZE': { path: ['llm', 'batch_size'], transform: v => parseInt(v, 10) },
+          'CODEXLENS_USE_ASTGREP': { path: ['parsing', 'use_astgrep'], transform: v => v === 'true' },
+          'CODEXLENS_STATIC_GRAPH_ENABLED': { path: ['indexing', 'static_graph_enabled'], transform: v => v === 'true' },
+          'CODEXLENS_STATIC_GRAPH_RELATIONSHIP_TYPES': {
+            path: ['indexing', 'static_graph_relationship_types'],
+            transform: v => v
+              .split(',')
+              .map((t) => t.trim())
+              .filter((t) => t.length > 0),
+          },
           'LITELLM_EMBEDDING_MODEL': { path: ['embedding', 'model'] },
           'LITELLM_RERANKER_MODEL': { path: ['reranker', 'model'] }
         };

ccw/src/core/routes/files-routes.ts

@@ -102,10 +102,206 @@ interface UpdateClaudeMdResult {
   path?: string;
 }
 
+// ========================================
+// Explorer API Types (matching frontend)
+// ========================================
+
+interface FileSystemNode {
+  name: string;
+  path: string;
+  type: 'file' | 'directory';
+  children?: FileSystemNode[];
+  hasClaudeMd?: boolean;
+  size?: number;
+  modifiedTime?: string;
+  extension?: string;
+  language?: string;
+}
+
+interface FileTreeResponse {
+  rootNodes: FileSystemNode[];
+  fileCount: number;
+  directoryCount: number;
+  totalSize: number;
+  buildTime: number;
+}
+
+interface RootDirectory {
+  path: string;
+  name: string;
+  isWorkspace: boolean;
+  isGitRoot: boolean;
+}
+
 // ========================================
 // Helper Functions
 // ========================================
 
+/**
+ * Build recursive file tree
+ * @param {string} dirPath - Directory path to build tree from
+ * @param {number} maxDepth - Maximum depth (0 = unlimited)
+ * @param {boolean} includeHidden - Include hidden files
+ * @param {number} currentDepth - Current recursion depth
+ * @returns {Promise<{ node: FileSystemNode, fileCount: number, directoryCount: number, totalSize: number }>}
+ */
+async function buildFileTree(
+  dirPath: string,
+  maxDepth: number = 6,
+  includeHidden: boolean = false,
+  currentDepth: number = 0
+): Promise<{ node: FileSystemNode | null; fileCount: number; directoryCount: number; totalSize: number }> {
+  const result = { node: null as FileSystemNode | null, fileCount: 0, directoryCount: 0, totalSize: 0 };
+
+  try {
+    // Normalize path
+    let normalizedPath = dirPath.replace(/\\/g, '/');
+    if (normalizedPath.match(/^\/[a-zA-Z]\//)) {
+      normalizedPath = normalizedPath.charAt(1).toUpperCase() + ':' + normalizedPath.slice(2);
+    }
+
+    if (!existsSync(normalizedPath) || !statSync(normalizedPath).isDirectory()) {
+      return result;
+    }
+
+    const dirName = normalizedPath.split('/').pop() || normalizedPath;
+    const node: FileSystemNode = {
+      name: dirName,
+      path: normalizedPath,
+      type: 'directory',
+      children: []
+    };
+
+    // Check for CLAUDE.md
+    const claudeMdPath = join(normalizedPath, 'CLAUDE.md');
+    node.hasClaudeMd = existsSync(claudeMdPath);
+
+    // Parse .gitignore patterns
+    const gitignorePath = join(normalizedPath, '.gitignore');
+    const gitignorePatterns = parseGitignore(gitignorePath);
+
+    // Read directory entries
+    const entries = readdirSync(normalizedPath, { withFileTypes: true });
+
+    for (const entry of entries) {
+      const isDirectory = entry.isDirectory();
+
+      // Check if should be ignored
+      if (shouldIgnore(entry.name, gitignorePatterns, isDirectory)) {
+        // Allow hidden files if includeHidden is true and it's .claude or .workflow
+        if (!includeHidden || (!entry.name.startsWith('.claude') && !entry.name.startsWith('.workflow'))) {
+          continue;
+        }
+      }
+
+      const entryPath = join(normalizedPath, entry.name);
+
+      if (isDirectory) {
+        // Recursively build tree for directories
+        if (maxDepth === 0 || currentDepth < maxDepth - 1) {
+          const childResult = await buildFileTree(entryPath, maxDepth, includeHidden, currentDepth + 1);
+          if (childResult.node) {
+            node.children!.push(childResult.node);
+            result.fileCount += childResult.fileCount;
+            result.directoryCount += childResult.directoryCount + 1;
+            result.totalSize += childResult.totalSize;
+          }
+        } else {
+          // At max depth, just add directory without children
+          const childNode: FileSystemNode = {
+            name: entry.name,
+            path: entryPath.replace(/\\/g, '/'),
+            type: 'directory'
+          };
+          const childClaudeMdPath = join(entryPath, 'CLAUDE.md');
+          childNode.hasClaudeMd = existsSync(childClaudeMdPath);
+          node.children!.push(childNode);
+          result.directoryCount += 1;
+        }
+      } else {
+        // Add file node
+        const stats = statSync(entryPath);
+        const ext = entry.name.includes('.') ? entry.name.split('.').pop()?.toLowerCase() : '';
+        const language = ext && Object.prototype.hasOwnProperty.call(EXT_TO_LANGUAGE, `.${ext}`)
+          ? EXT_TO_LANGUAGE[`.${ext}` as keyof typeof EXT_TO_LANGUAGE]
+          : undefined;
+
+        const fileNode: FileSystemNode = {
+          name: entry.name,
+          path: entryPath.replace(/\\/g, '/'),
+          type: 'file',
+          size: stats.size,
+          modifiedTime: stats.mtime.toISOString(),
+          extension: ext,
+          language
+        };
+        node.children!.push(fileNode);
+        result.fileCount += 1;
+        result.totalSize += stats.size;
+      }
+    }
+
+    // Sort: directories first, then alphabetically
+    node.children!.sort((a, b) => {
+      if (a.type === 'directory' && b.type !== 'directory') return -1;
+      if (a.type !== 'directory' && b.type === 'directory') return 1;
+      return a.name.localeCompare(b.name);
+    });
+
+    result.node = node;
+    return result;
+  } catch (error: unknown) {
+    console.error('Error building file tree:', error);
+    return result;
+  }
+}
+
+/**
+ * Get available root directories
+ * @param {string} workspacePath - Current workspace path
+ * @returns {Promise<RootDirectory[]>}
+ */
+async function getRootDirectories(workspacePath: string): Promise<RootDirectory[]> {
+  const roots: RootDirectory[] = [];
+
+  // Add workspace root
+  let normalizedWorkspace = workspacePath.replace(/\\/g, '/');
+  if (normalizedWorkspace.match(/^\/[a-zA-Z]\//)) {
+    normalizedWorkspace = normalizedWorkspace.charAt(1).toUpperCase() + ':' + normalizedWorkspace.slice(2);
+  }
+
+  const workspaceName = normalizedWorkspace.split('/').pop() || 'Workspace';
+  const isGitRoot = existsSync(join(normalizedWorkspace, '.git'));
+
+  roots.push({
+    path: normalizedWorkspace,
+    name: workspaceName,
+    isWorkspace: true,
+    isGitRoot
+  });
+
+  // On Windows, also add drive roots
+  if (process.platform === 'win32') {
+    // Get the drive letter from workspace path
+    const driveMatch = normalizedWorkspace.match(/^([A-Z]):/);
+    if (driveMatch) {
+      const driveLetter = driveMatch[1];
+      // Add drive root if not already the workspace
+      const driveRoot = `${driveLetter}:/`;
+      if (driveRoot !== normalizedWorkspace) {
+        roots.push({
+          path: driveRoot,
+          name: `${driveLetter}: Drive`,
+          isWorkspace: false,
+          isGitRoot: false
+        });
+      }
+    }
+  }
+
+  return roots;
+}
+
 /**
  * Parse .gitignore file and return patterns
  * @param {string} gitignorePath - Path to .gitignore file
@@ -420,6 +616,166 @@ async function triggerUpdateClaudeMd(targetPath: string, tool: string, strategy:
 export async function handleFilesRoutes(ctx: RouteContext): Promise<boolean> {
   const { pathname, url, req, res, initialPath, handlePostRequest } = ctx;
 
+  // ========================================
+  // Explorer API Routes (/api/explorer/*)
+  // ========================================
+
+  // API: Get file tree (Explorer view)
+  if (pathname === '/api/explorer/tree') {
+    const rootPath = url.searchParams.get('rootPath') || initialPath;
+    const maxDepth = parseInt(url.searchParams.get('maxDepth') || '6', 10);
+    const includeHidden = url.searchParams.get('includeHidden') === 'true';
+
+    const startTime = Date.now();
+
+    try {
+      const validatedPath = await validateAllowedPath(rootPath, { mustExist: true, allowedDirectories: [initialPath] });
+      const treeResult = await buildFileTree(validatedPath, maxDepth, includeHidden);
+
+      const response: FileTreeResponse = {
+        rootNodes: treeResult.node ? [treeResult.node] : [],
+        fileCount: treeResult.fileCount,
+        directoryCount: treeResult.directoryCount,
+        totalSize: treeResult.totalSize,
+        buildTime: Date.now() - startTime
+      };
+
+      res.writeHead(200, { 'Content-Type': 'application/json' });
+      res.end(JSON.stringify(response));
+    } catch (err) {
+      const message = err instanceof Error ? err.message : String(err);
+      const status = message.includes('Access denied') ? 403 : 400;
+      console.error(`[Explorer] Tree path validation failed: ${message}`);
+      res.writeHead(status, { 'Content-Type': 'application/json' });
+      res.end(JSON.stringify({
+        rootNodes: [],
+        fileCount: 0,
+        directoryCount: 0,
+        totalSize: 0,
+        buildTime: 0,
+        error: status === 403 ? 'Access denied' : 'Invalid path'
+      }));
+    }
+    return true;
+  }
+
+  // API: Get root directories (Explorer view)
+  if (pathname === '/api/explorer/roots') {
+    try {
+      const roots = await getRootDirectories(initialPath);
+      res.writeHead(200, { 'Content-Type': 'application/json' });
+      res.end(JSON.stringify(roots));
+    } catch (err) {
+      const message = err instanceof Error ? err.message : String(err);
+      console.error(`[Explorer] Failed to get roots: ${message}`);
+      res.writeHead(500, { 'Content-Type': 'application/json' });
+      res.end(JSON.stringify({ error: 'Failed to get root directories' }));
+    }
+    return true;
+  }
+
+  // API: Get file content (Explorer view)
+  if (pathname === '/api/explorer/file') {
+    const filePath = url.searchParams.get('path');
+    if (!filePath) {
+      res.writeHead(400, { 'Content-Type': 'application/json' });
+      res.end(JSON.stringify({ error: 'File path is required' }));
+      return true;
+    }
+
+    try {
+      const validatedFile = await validateAllowedPath(filePath, { mustExist: true, allowedDirectories: [initialPath] });
+      const fileData = await getFileContent(validatedFile);
+
+      if (fileData.error) {
+        res.writeHead(404, { 'Content-Type': 'application/json' });
+        res.end(JSON.stringify(fileData));
+      } else {
+        res.writeHead(200, { 'Content-Type': 'application/json' });
+        res.end(JSON.stringify(fileData));
+      }
+    } catch (err) {
+      const message = err instanceof Error ? err.message : String(err);
+      const status = message.includes('Access denied') ? 403 : 400;
+      console.error(`[Explorer] File path validation failed: ${message}`);
+      res.writeHead(status, { 'Content-Type': 'application/json' });
+      res.end(JSON.stringify({ error: status === 403 ? 'Access denied' : 'Invalid path' }));
+    }
+    return true;
+  }
+
+  // API: Search files (Explorer view)
+  if (pathname === '/api/explorer/search' && req.method === 'POST') {
+    handlePostRequest(req, res, async (body) => {
+      if (typeof body !== 'object' || body === null) {
+        return { error: 'Invalid request body', status: 400 };
+      }
+
+      const { query, rootPath, maxResults = 50 } = body as { query?: unknown; rootPath?: unknown; maxResults?: unknown };
+
+      if (typeof query !== 'string' || query.trim().length === 0) {
+        return { error: 'query is required', status: 400 };
+      }
+
+      try {
+        const validatedPath = await validateAllowedPath(
+          typeof rootPath === 'string' ? rootPath : initialPath,
+          { mustExist: true, allowedDirectories: [initialPath] }
+        );
+
+        // Simple file search - walk directory tree and match by name
+        const results: Array<{ path: string; name: string; type: 'file' | 'directory' }> = [];
+        const searchQuery = query.toLowerCase();
+
+        const searchDir = (dirPath: string, depth: number = 0) => {
+          if (depth > 10 || results.length >= (typeof maxResults === 'number' ? maxResults : 50)) return;
+
+          try {
+            const entries = readdirSync(dirPath, { withFileTypes: true });
+            const gitignorePath = join(dirPath, '.gitignore');
+            const gitignorePatterns = parseGitignore(gitignorePath);
+
+            for (const entry of entries) {
+              if (results.length >= (typeof maxResults === 'number' ? maxResults : 50)) break;
+
+              if (shouldIgnore(entry.name, gitignorePatterns, entry.isDirectory())) continue;
+
+              const entryPath = join(dirPath, entry.name);
+
+              if (entry.name.toLowerCase().includes(searchQuery)) {
+                results.push({
+                  path: entryPath.replace(/\\/g, '/'),
+                  name: entry.name,
+                  type: entry.isDirectory() ? 'directory' : 'file'
+                });
+              }
+
+              if (entry.isDirectory()) {
+                searchDir(entryPath, depth + 1);
+              }
+            }
+          } catch {
+            // Skip directories we can't read
+          }
+        };
+
+        searchDir(validatedPath);
+
+        return { results, total: results.length };
+      } catch (err) {
+        const message = err instanceof Error ? err.message : String(err);
+        const status = message.includes('Access denied') ? 403 : 400;
+        console.error(`[Explorer] Search path validation failed: ${message}`);
+        return { error: status === 403 ? 'Access denied' : 'Invalid path', status };
+      }
+    });
+    return true;
+  }
+
+  // ========================================
+  // Legacy Files API Routes (/api/files/*)
+  // ========================================
+
   // API: List directory files with .gitignore filtering (Explorer view)
   if (pathname === '/api/files') {
     const dirPath = url.searchParams.get('path') || initialPath;