fix(claude): 修复 ccw tool exec 命令格式 - 位置参数改为JSON格式

修复内容: - 将位置参数格式改为JSON格式: ccw tool exec tool '{"param":"value"}' - 修复双引号字符串内的JSON引号转义问题 - 更新deprecated脚本的使用示例受影响文件: - commands/memory/update-full.md, docs-full-cli.md, docs-related-cli.md, update-related.md - commands/workflow/ui-design/generate.md, import-from-code.md - scripts/*.sh (9个deprecated脚本) - skills/command-guide/reference/* (通过analyze_commands.py自动同步) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-02-12 02:37:45 +08:00 · 2025-12-08 21:09:21 +08:00
parent 8b29f6bb7c
commit 813bfa8f97
67 changed files with 1311 additions and 1737 deletions
--- a/.claude/skills/command-guide/reference/commands/workflow/review-module-cycle.md
+++ b/.claude/skills/command-guide/reference/commands/workflow/review-module-cycle.md
@@ -51,14 +51,12 @@ Independent multi-dimensional code review orchestrator with **hybrid parallel-it
 2. **Session-Integrated**: Review results tracked within workflow session for unified management
 3. **Comprehensive Coverage**: Same 7 specialized dimensions as session review
 4. **Intelligent Prioritization**: Automatic identification of critical issues and cross-cutting concerns
-5. **Real-time Visibility**: JSON-based progress tracking with interactive HTML dashboard
-6. **Unified Archive**: Review results archived with session for historical reference
+5. **Unified Archive**: Review results archived with session for historical reference

 ### Orchestrator Boundary (CRITICAL)
 - **ONLY command** for independent multi-dimensional module review
 - Manages: dimension coordination, aggregation, iteration control, progress tracking
 - Delegates: Code exploration and analysis to @cli-explore-agent, dimension-specific reviews via Deep Scan mode
- **⚠️ DASHBOARD CONSTRAINT**: Dashboard is generated ONCE during Phase 1 initialization. After initialization, orchestrator and agents MUST NOT read, write, or modify dashboard.html - it remains static for user interaction only.

 ## How It Works

@@ -66,7 +64,7 @@ Independent multi-dimensional code review orchestrator with **hybrid parallel-it

 ```
 Phase 1: Discovery & Initialization
-   └─ Resolve file patterns, validate paths, initialize state, create output structure → Generate dashboard.html
+   └─ Resolve file patterns, validate paths, initialize state, create output structure

 Phase 2: Parallel Reviews (for each dimension)
   ├─ Launch 7 review agents simultaneously
@@ -90,7 +88,7 @@ Phase 4: Iterative Deep-Dive (optional)
   └─ Loop until no critical findings OR max iterations

 Phase 5: Completion
-   └─ Finalize review-progress.json → Output dashboard path
+   └─ Finalize review-progress.json
 ```

 ### Agent Roles
@@ -188,8 +186,8 @@ const CATEGORIES = {

 **Step 1: Session Creation**
 ```javascript
-// Create workflow session for this review
-SlashCommand(command="/workflow:session:start \"Code review for [target_pattern]\"")
+// Create workflow session for this review (type: review)
+SlashCommand(command="/workflow:session:start --type review \"Code review for [target_pattern]\"")

 // Parse output
 const sessionId = output.match(/SESSION_ID: (WFS-[^\s]+)/)[1];
@@ -219,37 +217,9 @@ done

 **Step 4: Initialize Review State**
 - State initialization: Create `review-state.json` with metadata, dimensions, max_iterations, resolved_files (merged metadata + state)
- Progress tracking: Create `review-progress.json` for dashboard polling
+- Progress tracking: Create `review-progress.json` for progress tracking

-**Step 5: Dashboard Generation**
-
-**Constraints**:
- **MANDATORY**: Dashboard MUST be generated from template: `~/.claude/templates/review-cycle-dashboard.html`
- **PROHIBITED**: Direct creation or custom generation without template
- **POST-GENERATION**: Orchestrator and agents MUST NOT read/write/modify dashboard.html after creation
-
-**Generation Commands** (3 independent steps):
-```bash
-# Step 1: Copy template to output location
-cp ~/.claude/templates/review-cycle-dashboard.html ${sessionDir}/.review/dashboard.html
-
-# Step 2: Replace SESSION_ID placeholder
-sed -i "s|{{SESSION_ID}}|${sessionId}|g" ${sessionDir}/.review/dashboard.html
-
-# Step 3: Replace REVIEW_TYPE placeholder
-sed -i "s|{{REVIEW_TYPE}}|module|g" ${sessionDir}/.review/dashboard.html
-
-# Step 4: Replace REVIEW_DIR placeholder
-sed -i "s|{{REVIEW_DIR}}|${reviewDir}|g" ${sessionDir}/.review/dashboard.html
-
-# Output: Start local server and output dashboard URL
-# Use Python HTTP server (available on most systems)
-cd ${sessionDir}/.review && python -m http.server 8765 --bind 127.0.0.1 &
-echo "📊 Dashboard: http://127.0.0.1:8765/dashboard.html"
-echo "   (Press Ctrl+C to stop server when done)"
-```
-
-**Step 6: TodoWrite Initialization**
+**Step 5: TodoWrite Initialization**
 - Set up progress tracking with hierarchical structure
 - Mark Phase 1 completed, Phase 2 in_progress

@@ -280,7 +250,6 @@ echo "   (Press Ctrl+C to stop server when done)"
 - Finalize review-progress.json with completion statistics
 - Update review-state.json with completion_time and phase=complete
 - TodoWrite completion: Mark all tasks done
- Output: Dashboard path to user



@@ -301,12 +270,11 @@ echo "   (Press Ctrl+C to stop server when done)"
 ├── iterations/                          # Deep-dive results
 │   ├── iteration-1-finding-{uuid}.json
 │   └── iteration-2-finding-{uuid}.json
-├── reports/                             # Human-readable reports
-│   ├── security-analysis.md
-│   ├── security-cli-output.txt
-│   ├── deep-dive-1-{uuid}.md
-│   └── ...
-└── dashboard.html                       # Interactive dashboard (primary output)
+└── reports/                             # Human-readable reports
+    ├── security-analysis.md
+    ├── security-cli-output.txt
+    ├── deep-dive-1-{uuid}.md
+    └── ...
 ```

 **Session Context**:
@@ -772,23 +740,25 @@ TodoWrite({
 3. **Use Glob Wisely**: `src/auth/**` is more efficient than `src/**` with lots of irrelevant files
 4. **Trust Aggregation Logic**: Auto-selection based on proven heuristics
 5. **Monitor Logs**: Check reports/ directory for CLI analysis insights
-6. **Dashboard Polling**: Refresh every 5 seconds for real-time updates
-7. **Export Results**: Use dashboard export for external tracking tools

 ## Related Commands

+### View Review Progress
+Use `ccw view` to open the review dashboard in browser:
+
+```bash
+ccw view
+```
+
 ### Automated Fix Workflow
-After completing a module review, use the dashboard to select findings and export them for automated fixing:
+After completing a module review, use the generated findings JSON for automated fixing:

 ```bash
 # Step 1: Complete review (this command)
 /workflow:review-module-cycle src/auth/**

-# Step 2: Open dashboard, select findings, and export
-# Dashboard generates: fix-export-{timestamp}.json
-
-# Step 3: Run automated fixes
-/workflow:review-fix .workflow/active/WFS-{session-id}/.review/fix-export-{timestamp}.json
+# Step 2: Run automated fixes using dimension findings
+/workflow:review-fix .workflow/active/WFS-{session-id}/.review/
 ```

 See `/workflow:review-fix` for automated fixing with smart grouping, parallel execution, and test verification.