feat: enhance workflow planning with concept clarification and agent delegation

🎯 Major Enhancements:

1. Concept Clarification Quality Gate (concept-clarify.md)
   - Added dual-mode support: brainstorm & plan modes
   - Auto-detects mode based on artifact presence (ANALYSIS_RESULTS.md vs synthesis-specification.md)
   - Backward compatible with existing brainstorm workflow
   - Updates appropriate artifacts based on detected mode

2. Planning Workflow Enhancement (plan.md)
   - Added Phase 3.5: Concept Clarification as quality gate
   - Integrated Phase 3.5 between analysis and task generation
   - Enhanced with interactive Q&A to resolve ambiguities
   - Updated from 4-phase to 5-phase workflow model
   - Delegated Phase 3 (Intelligent Analysis) to cli-execution-agent
   - Autonomous context discovery and enhanced prompt generation

3. Documentation Updates (README.md, README_CN.md)
   - Added /workflow:test-cycle-execute command documentation
   - Explained dynamic task generation and iterative fix cycles
   - Included usage examples and key features
   - Updated both English and Chinese versions

🔧 Technical Details:
- concept-clarify now supports both ANALYSIS_RESULTS.md (plan) and synthesis-specification.md (brainstorm)
- plan.md Phase 3 now uses cli-execution-agent for MCP-powered context discovery
- Maintains auto-continue mechanism with one interactive quality gate (Phase 3.5)
- All changes preserve backward compatibility

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

.claude/commands/workflow/concept-clarify.md

@@ -15,9 +15,13 @@ You **MUST** consider the user input before proceeding (if not empty).
 
 ## Outline
 
-**Goal**: Detect and reduce ambiguity or missing decision points in brainstorming artifacts (synthesis-specification.md, topic-framework.md, role analyses) before moving to action planning phase.
+**Goal**: Detect and reduce ambiguity or missing decision points in planning artifacts before moving to task generation. Supports both brainstorm and plan workflows.
 
-**Timing**: This command runs AFTER `/workflow:brainstorm:synthesis` and BEFORE `/workflow:plan`. It serves as a quality gate to ensure conceptual clarity before detailed task planning.
+**Timing**:
+- **Brainstorm mode**: Runs AFTER `/workflow:brainstorm:synthesis` and BEFORE `/workflow:plan`
+- **Plan mode**: Runs AFTER Phase 3 (concept-enhanced) and BEFORE Phase 4 (task-generate) within `/workflow:plan`
+
+This serves as a quality gate to ensure conceptual clarity before detailed task planning or generation.
 
 **Execution steps**:
 
@@ -34,28 +38,40 @@ You **MUST** consider the user input before proceeding (if not empty).
            ERROR: "No active workflow session found. Use --session <session-id> or start a session."
            EXIT
 
-   # Validate brainstorming completion
+   # Mode detection: plan vs brainstorm
    brainstorm_dir = .workflow/WFS-{session}/.brainstorming/
+   process_dir = .workflow/WFS-{session}/.process/
 
-   CHECK: brainstorm_dir/synthesis-specification.md
-   IF NOT EXISTS:
-       ERROR: "synthesis-specification.md not found. Run /workflow:brainstorm:synthesis first"
+   IF EXISTS(process_dir/ANALYSIS_RESULTS.md):
+       clarify_mode = "plan"
+       primary_artifact = process_dir/ANALYSIS_RESULTS.md
+       INFO: "Plan mode: Analyzing ANALYSIS_RESULTS.md"
+   ELSE IF EXISTS(brainstorm_dir/synthesis-specification.md):
+       clarify_mode = "brainstorm"
+       primary_artifact = brainstorm_dir/synthesis-specification.md
+       INFO: "Brainstorm mode: Analyzing synthesis-specification.md"
+   ELSE:
+       ERROR: "No valid artifact found. Run /workflow:brainstorm:synthesis or /workflow:plan first"
        EXIT
 
-   CHECK: brainstorm_dir/topic-framework.md
-   IF NOT EXISTS:
-       WARN: "topic-framework.md not found. Verification will be limited."
+   # Mode-specific validation
+   IF clarify_mode == "brainstorm":
+       CHECK: brainstorm_dir/topic-framework.md
+       IF NOT EXISTS:
+           WARN: "topic-framework.md not found. Verification will be limited."
    ```
 
-2. **Load Brainstorming Artifacts**
+2. **Load Artifacts (Mode-Aware)**
    ```bash
-   # Load primary artifacts
-   synthesis_spec = Read(brainstorm_dir + "/synthesis-specification.md")
-   topic_framework = Read(brainstorm_dir + "/topic-framework.md") # if exists
+   # Load primary artifact (determined in step 1)
+   primary_content = Read(primary_artifact)
 
-   # Discover role analyses
-   role_analyses = Glob(brainstorm_dir + "/*/analysis.md")
-   participating_roles = extract_role_names(role_analyses)
+   # Load mode-specific supplementary artifacts
+   IF clarify_mode == "brainstorm":
+       topic_framework = Read(brainstorm_dir + "/topic-framework.md") # if exists
+       role_analyses = Glob(brainstorm_dir + "/*/analysis.md")
+       participating_roles = extract_role_names(role_analyses)
+   # Plan mode: primary_content (ANALYSIS_RESULTS.md) is self-contained
    ```
 
 3. **Ambiguity & Coverage Scan**
@@ -182,8 +198,8 @@ You **MUST** consider the user input before proceeding (if not empty).
 
    ```bash
    # Ensure Clarifications section exists
-   IF synthesis_spec NOT contains "## Clarifications":
-       Insert "## Clarifications" section after "# [Topic]" heading
+   IF primary_content NOT contains "## Clarifications":
+       Insert "## Clarifications" section after first heading
 
    # Create session subsection
    IF NOT contains "### Session YYYY-MM-DD":
@@ -194,20 +210,20 @@ You **MUST** consider the user input before proceeding (if not empty).
 
    # Apply clarification to appropriate section
    CASE category:
-       Functional Requirements → Update "## Requirements & Acceptance Criteria"
-       Architecture → Update "## Key Designs & Decisions" or "## Design Specifications"
-       User Experience → Update "## Design Specifications > UI/UX Guidelines"
-       Risk → Update "## Risk Assessment & Mitigation"
-       Process → Update "## Process & Collaboration Concerns"
-       Data Model → Update "## Key Designs & Decisions > Data Model Overview"
-       Non-Functional → Update "## Requirements & Acceptance Criteria > Non-Functional Requirements"
+       Functional Requirements → Update "## Requirements" or equivalent section
+       Architecture → Update "## Architecture" or "## Design" sections
+       User Experience → Update "## UI/UX" or "## User Experience" sections
+       Risk → Update "## Risks" or "## Risk Assessment" sections
+       Process → Update "## Process" or "## Implementation" sections
+       Data Model → Update "## Data Model" or "## Database" sections
+       Non-Functional → Update "## Non-Functional Requirements" or equivalent
 
    # Remove obsolete/contradictory statements
    IF clarification invalidates existing statement:
        Replace statement instead of duplicating
 
-   # Save immediately
-   Write(synthesis_specification.md)
+   # Save immediately to primary_artifact
+   Write(primary_artifact)
    ```
 
 7. **Validation After Each Write**
@@ -227,8 +243,9 @@ You **MUST** consider the user input before proceeding (if not empty).
    ## ✅ Concept Verification Complete
 
    **Session**: WFS-{session-id}
+   **Mode**: {clarify_mode}
    **Questions Asked**: {count}/5
-   **Artifacts Updated**: synthesis-specification.md
+   **Artifacts Updated**: {primary_artifact filename}
    **Sections Touched**: {list section names}
 
    ### Coverage Summary
@@ -261,18 +278,26 @@ You **MUST** consider the user input before proceeding (if not empty).
 
 9. **Update Session Metadata**
 
-   ```json
+   ```bash
+   # Update metadata based on mode
+   IF clarify_mode == "brainstorm":
+       phase_key = "BRAINSTORM"
+   ELSE: # plan mode
+       phase_key = "PLAN"
+
+   # Update session metadata
    {
      "phases": {
-       "BRAINSTORM": {
-         "status": "completed",
+       "{phase_key}": {
+         "status": "concept_verified",
          "concept_verification": {
            "completed": true,
            "completed_at": "timestamp",
-           "questions_asked": 3,
-           "categories_clarified": ["Requirements", "Risk", "Architecture"],
+           "mode": "{clarify_mode}",
+           "questions_asked": {count},
+           "categories_clarified": [{list}],
            "outstanding_items": [],
-           "recommendation": "PROCEED_TO_PLANNING"
+           "recommendation": "PROCEED" # or "ADDRESS_OUTSTANDING"
          }
        }
      }

.claude/commands/workflow/plan.md

@@ -1,6 +1,6 @@
 ---
 name: plan
-description: Orchestrate 4-phase planning workflow by executing commands and passing context between phases
+description: Orchestrate 5-phase planning workflow with quality gate, executing commands and passing context between phases
 argument-hint: "[--agent] [--cli-execute] \"text description\"|file.md"
 allowed-tools: SlashCommand(*), TodoWrite(*), Read(*), Bash(*)
 ---
@@ -9,22 +9,24 @@ allowed-tools: SlashCommand(*), TodoWrite(*), Read(*), Bash(*)
 
 ## Coordinator Role
 
-**This command is a pure orchestrator**: Execute 4 slash commands in sequence, parse their outputs, pass context between them, and ensure complete execution through **automatic continuation**.
+**This command is a pure orchestrator**: Execute 5 slash commands in sequence (including a quality gate), parse their outputs, pass context between them, and ensure complete execution through **automatic continuation**.
 
-**Execution Model - Auto-Continue Workflow**:
+**Execution Model - Auto-Continue Workflow with Quality Gate**:
 
-This workflow runs **fully autonomously** once triggered. Each phase completes, reports its output to you, then **immediately and automatically** proceeds to the next phase without requiring any user intervention.
+This workflow runs **mostly autonomously** once triggered, with one interactive quality gate (Phase 3.5). Phases 3 and 4 are delegated to specialized agents for complex analysis and task generation.
 
 1. **User triggers**: `/workflow:plan "task"`
-2. **Phase 1 executes** → Reports output to user → Auto-continues
-3. **Phase 2 executes** → Reports output to user → Auto-continues
-4. **Phase 3 executes** → Reports output to user → Auto-continues
-5. **Phase 4 executes** → Reports final summary
+2. **Phase 1 executes** → Session discovery → Auto-continues
+3. **Phase 2 executes** → Context gathering → Auto-continues
+4. **Phase 3 executes** (cli-execution-agent) → Intelligent analysis → Auto-continues
+5. **Phase 3.5 executes** → **Pauses for user Q&A** → User answers clarification questions → Auto-continues
+6. **Phase 4 executes** (task-generate-agent if --agent) → Task generation → Reports final summary
 
 **Auto-Continue Mechanism**:
 - TodoList tracks current phase status
 - After each phase completion, automatically executes next pending phase
-- **No user action required** - workflow runs end-to-end autonomously
+- **Phase 3.5 requires user interaction** - answers clarification questions (up to 5)
+- If no ambiguities found, Phase 3.5 auto-skips and continues to Phase 4
 - Progress updates shown at each phase for visibility
 
 **Execution Modes**:
@@ -36,11 +38,12 @@ This workflow runs **fully autonomously** once triggered. Each phase completes,
 
 1. **Start Immediately**: First action is TodoWrite initialization, second action is Phase 1 command execution
 2. **No Preliminary Analysis**: Do not read files, analyze structure, or gather context before Phase 1
-3. **Parse Every Output**: Extract required data from each command's output for next phase
+3. **Parse Every Output**: Extract required data from each command/agent output for next phase
 4. **Auto-Continue via TodoList**: Check TodoList status to execute next pending phase automatically
 5. **Track Progress**: Update TodoWrite after every phase completion
+6. **Agent Delegation**: Phase 3 uses cli-execution-agent for autonomous intelligent analysis
 
-## 4-Phase Execution
+## 5-Phase Execution
 
 ### Phase 1: Session Discovery
 **Command**: `SlashCommand(command="/workflow:session:start --auto \"[structured-task-description]\"")`
@@ -93,32 +96,92 @@ CONTEXT: Existing user database schema, REST API endpoints
 
 ---
 
-### Phase 3: Intelligent Analysis
-**Command**: `SlashCommand(command="/workflow:tools:concept-enhanced --session [sessionId] --context [contextPath]")`
+### Phase 3: Intelligent Analysis (Agent-Delegated)
+
+**Command**: `Task(subagent_type="cli-execution-agent", description="Intelligent Analysis", prompt="...")`
+
+**Agent Task Prompt**:
+```
+Analyze project requirements and generate comprehensive solution blueprint for session [sessionId].
+
+Context: Load context package from [contextPath]
+Output: Generate ANALYSIS_RESULTS.md in .workflow/[sessionId]/.process/
+
+Requirements:
+- Review context-package.json and discover additional relevant files
+- Analyze architecture patterns, data models, and dependencies
+- Identify technical constraints and risks
+- Generate comprehensive solution blueprint
+- Include task breakdown recommendations
+
+Session: [sessionId]
+Mode: analysis (read-only during discovery, write for ANALYSIS_RESULTS.md)
+```
 
 **Input**: `sessionId` from Phase 1, `contextPath` from Phase 2
 
+**Agent Execution**:
+- Phase 1: Understands analysis intent, extracts keywords
+- Phase 2: Discovers additional context via MCP code-index
+- Phase 3: Enhances prompt with discovered patterns
+- Phase 4: Executes with Gemini (analysis mode), generates ANALYSIS_RESULTS.md
+- Phase 5: Routes output to session directory
+
 **Parse Output**:
-- Verify ANALYSIS_RESULTS.md created
+- Agent returns execution log path
+- Verify ANALYSIS_RESULTS.md created by agent
 
 **Validation**:
-- File `.workflow/[sessionId]/ANALYSIS_RESULTS.md` exists
+- File `.workflow/[sessionId]/.process/ANALYSIS_RESULTS.md` exists
 - Contains task recommendations section
+- Agent execution log saved to `.workflow/[sessionId]/.chat/`
 
-**TodoWrite**: Mark phase 3 completed, phase 4 in_progress
+**TodoWrite**: Mark phase 3 completed, phase 3.5 in_progress
 
-**After Phase 3**: Return to user showing Phase 3 results, then auto-continue to Phase 4
+**After Phase 3**: Return to user showing Phase 3 results, then auto-continue to Phase 3.5
 
 **Memory State Check**:
 - Evaluate current context window usage and memory state
 - If memory usage is high (>110K tokens or approaching context limits):
   - **Command**: `SlashCommand(command="/compact")`
-  - This optimizes memory before proceeding to Phase 4
+  - This optimizes memory before proceeding to Phase 3.5
 - Memory compaction is particularly important after analysis phase which may generate extensive documentation
 - Ensures optimal performance and prevents context overflow
 
 ---
 
+### Phase 3.5: Concept Clarification (Quality Gate)
+
+**Command**: `SlashCommand(command="/workflow:concept-clarify --session [sessionId]")`
+
+**Purpose**: Quality gate to verify and clarify analysis results before task generation
+
+**Input**: `sessionId` from Phase 1
+
+**Behavior**:
+- Auto-detects plan mode (ANALYSIS_RESULTS.md exists)
+- Interactively asks up to 5 targeted questions to resolve ambiguities
+- Updates ANALYSIS_RESULTS.md with clarifications
+- Pauses workflow for user input (breaks auto-continue temporarily)
+
+**Parse Output**:
+- Verify clarifications added to ANALYSIS_RESULTS.md
+- Check recommendation: "PROCEED" or "ADDRESS_OUTSTANDING"
+
+**Validation**:
+- ANALYSIS_RESULTS.md updated with `## Clarifications` section
+- All critical ambiguities resolved or documented as outstanding
+
+**TodoWrite**: Mark phase 3.5 completed, phase 4 in_progress
+
+**After Phase 3.5**: Return to user showing clarification summary, then auto-continue to Phase 4
+
+**Skip Conditions**:
+- If `/workflow:concept-clarify` reports "No critical ambiguities detected", automatically proceed to Phase 4
+- User can skip by responding "skip" or "proceed" immediately
+
+---
+
 ### Phase 4: Task Generation
 
 **Relationship with Brainstorm Phase**:
@@ -176,6 +239,7 @@ TodoWrite({todos: [
   {"content": "Execute session discovery", "status": "in_progress", "activeForm": "Executing session discovery"},
   {"content": "Execute context gathering", "status": "pending", "activeForm": "Executing context gathering"},
   {"content": "Execute intelligent analysis", "status": "pending", "activeForm": "Executing intelligent analysis"},
+  {"content": "Execute concept clarification", "status": "pending", "activeForm": "Executing concept clarification"},
   {"content": "Execute task generation", "status": "pending", "activeForm": "Executing task generation"}
 ]})
 
@@ -184,10 +248,11 @@ TodoWrite({todos: [
   {"content": "Execute session discovery", "status": "completed", "activeForm": "Executing session discovery"},
   {"content": "Execute context gathering", "status": "in_progress", "activeForm": "Executing context gathering"},
   {"content": "Execute intelligent analysis", "status": "pending", "activeForm": "Executing intelligent analysis"},
+  {"content": "Execute concept clarification", "status": "pending", "activeForm": "Executing concept clarification"},
   {"content": "Execute task generation", "status": "pending", "activeForm": "Executing task generation"}
 ]})
 
-// Continue pattern for Phase 2, 3, 4...
+// Continue pattern for Phase 2, 3, 3.5, 4...
 ```
 
 ## Input Processing
@@ -238,12 +303,18 @@ Phase 2: context-gather --session sessionId "structured-description"
     ↓ Input: sessionId + session memory + structured description
     ↓ Output: contextPath (context-package.json)
     ↓
-Phase 3: concept-enhanced --session sessionId --context contextPath
-    ↓ Input: sessionId + contextPath + session memory
-    ↓ Output: ANALYSIS_RESULTS.md
+Phase 3: cli-execution-agent (Intelligent Analysis)
+    ↓ Input: sessionId + contextPath + task description
+    ↓ Agent discovers context, enhances prompt, executes with Gemini
+    ↓ Output: ANALYSIS_RESULTS.md + execution log
+    ↓
+Phase 3.5: concept-clarify --session sessionId (Quality Gate)
+    ↓ Input: sessionId + ANALYSIS_RESULTS.md (auto-detected)
+    ↓ Interactive: User answers clarification questions
+    ↓ Output: Updated ANALYSIS_RESULTS.md with clarifications
     ↓
 Phase 4: task-generate[--agent] --session sessionId
-    ↓ Input: sessionId + ANALYSIS_RESULTS.md + session memory
+    ↓ Input: sessionId + clarified ANALYSIS_RESULTS.md + session memory
     ↓ Output: IMPL_PLAN.md, task JSONs, TODO_LIST.md
     ↓
 Return summary to user
@@ -270,13 +341,18 @@ Return summary to user
 ## Coordinator Checklist
 
 ✅ **Pre-Phase**: Convert user input to structured format (GOAL/SCOPE/CONTEXT)
-✅ Initialize TodoWrite before any command
+✅ Initialize TodoWrite before any command (include Phase 3.5)
 ✅ Execute Phase 1 immediately with structured description
 ✅ Parse session ID from Phase 1 output, store in memory
 ✅ Pass session ID and structured description to Phase 2 command
 ✅ Parse context path from Phase 2 output, store in memory
-✅ Pass session ID and context path to Phase 3 command
-✅ Verify ANALYSIS_RESULTS.md after Phase 3
+✅ **Launch Phase 3 agent**: Build Task prompt with sessionId and contextPath
+✅ Wait for agent completion, parse execution log path
+✅ Verify ANALYSIS_RESULTS.md created by agent
+✅ **Execute Phase 3.5**: Pass session ID to `/workflow:concept-clarify`
+✅ Wait for user interaction (clarification Q&A)
+✅ Verify ANALYSIS_RESULTS.md updated with clarifications
+✅ Check recommendation: proceed if "PROCEED", otherwise alert user
 ✅ **Build Phase 4 command** based on flags:
   - Base command: `/workflow:tools:task-generate` (or `-agent` if `--agent` flag)
   - Add `--session [sessionId]`

.claude/commands/workflow/tools/concept-enhanced.md

@@ -137,6 +137,8 @@ Advanced solution design and feasibility analysis engine with parallel CLI execu
 
 3. **Parallel Execution**: Launch tools simultaneously, monitor progress, handle completion/errors, maintain logs
 
+   **⚠️ IMPORTANT**: CLI commands MUST execute in foreground (NOT background). Do NOT use `run_in_background` parameter for Gemini/Codex execution.
+
 ### Phase 4: Results Collection & Synthesis
 1. **Output Validation**: Validate gemini-solution-design.md (all), codex-feasibility-validation.md (complex), use logs if incomplete, classify status
 2. **Quality Assessment**: Verify design rationale, insight depth, feasibility rigor, optimization value

README.md

@@ -400,13 +400,23 @@ cd .workflow/WFS-auth/.design/prototypes && python -m http.server 8080
 **Phase 5: Testing & Quality Assurance**
 ```bash
 # Generate independent test-fix workflow (v3.2.2+)
-/workflow:test-gen WFS-auth         # Creates WFS-test-auth session
-/workflow:test-cycle-execute        # Execute test-fix cycle with iterative validation
+/workflow:test-gen WFS-auth          # Creates WFS-test-auth session
+/workflow:test-cycle-execute         # Execute test-fix cycle with dynamic iteration
+
+# Resume interrupted test session
+/workflow:test-cycle-execute --resume-session="WFS-test-auth"
 
 # OR verify TDD compliance (TDD workflow)
 /workflow:tdd-verify
 ```
 
+**What is `/workflow:test-cycle-execute`?**
+- **Dynamic Task Generation**: Creates intermediate fix tasks based on test failures during execution
+- **Iterative Testing**: Automatically runs test-fix cycles until all tests pass or max iterations reached
+- **CLI-Driven Analysis**: Uses Gemini/Qwen to analyze failures and generate fix strategies
+- **Agent Coordination**: Delegates test execution and fixes to `@test-fix-agent`
+- **Autonomous Completion**: Continues until success without user interruption
+
 ### Quick Start for Simple Tasks
 
 **Feature Development:**
@@ -484,6 +494,7 @@ cd .workflow/WFS-auth/.design/prototypes && python -m http.server 8080
 | `/workflow:execute` | Execute the current workflow plan autonomously. |
 | `/workflow:status` | Display the current status of the workflow. |
 | `/workflow:test-gen [--use-codex] <session>` | Create test generation workflow with auto-diagnosis and fix cycle for completed implementations. |
+| `/workflow:test-cycle-execute` | **v4.5.0** Execute test-fix workflow with dynamic task generation and iterative fix cycles. Runs tests → analyzes failures with CLI → generates fix tasks → retests until success. |
 | `/workflow:tdd-verify` | Verify TDD compliance and generate quality report. |
 | `/workflow:review` | **Optional** manual review (only use when explicitly needed - passing tests = approved code). |
 | `/workflow:tools:test-context-gather` | Analyze test coverage and identify missing test files. |

README_CN.md

@@ -400,13 +400,23 @@ cd .workflow/WFS-auth/.design/prototypes && python -m http.server 8080
 **阶段 5：测试与质量保证**
 ```bash
 # 生成独立测试修复工作流（v3.2.2+）
-/workflow:test-gen WFS-auth  # 创建 WFS-test-auth 会话
-/workflow:execute            # 运行测试验证
+/workflow:test-gen WFS-auth          # 创建 WFS-test-auth 会话
+/workflow:test-cycle-execute         # 执行测试修复循环，包含动态迭代
+
+# 恢复中断的测试会话
+/workflow:test-cycle-execute --resume-session="WFS-test-auth"
 
 # 或验证 TDD 合规性（TDD 工作流）
 /workflow:tdd-verify
 ```
 
+**什么是 `/workflow:test-cycle-execute`？**
+- **动态任务生成**：基于测试失败在执行过程中创建中间修复任务
+- **迭代测试**：自动运行测试修复循环，直到所有测试通过或达到最大迭代次数
+- **CLI 驱动分析**：使用 Gemini/Qwen 分析失败并生成修复策略
+- **智能体协调**：将测试执行和修复委托给 `@test-fix-agent`
+- **自主完成**：持续直到成功，无需用户干预
+
 ### 简单任务快速入门
 
 **功能开发：**
@@ -484,6 +494,7 @@ cd .workflow/WFS-auth/.design/prototypes && python -m http.server 8080
 | `/workflow:execute` | 自主执行当前的工作流计划。 |
 | `/workflow:status` | 显示工作流的当前状态。 |
 | `/workflow:test-gen [--use-codex] <session>` | 为已完成实现创建独立测试生成工作流，支持自动诊断和修复。 |
+| `/workflow:test-cycle-execute` | **v4.5.0** 执行测试修复工作流，包含动态任务生成和迭代修复循环。运行测试 → 使用 CLI 分析失败 → 生成修复任务 → 重新测试直至成功。 |
 | `/workflow:tdd-verify` | 验证 TDD 合规性并生成质量报告。 |
 | `/workflow:review` | **可选** 手动审查（仅在明确需要时使用，测试通过即代表代码已批准）。 |
 | `/workflow:tools:test-context-gather` | 分析测试覆盖率，识别缺失的测试文件。 |