catlog22/Claude-Code-Workflow
1
0
Fork 0
mirror of https://github.com/catlog22/Claude-Code-Workflow.git synced 2026-02-12 02:37:45 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix: Standardize Execution Flow phase naming and remove redundant REVIEW-SUMMARY.md output

Browse Source 
- Unify phase numbering format to "Phase X:" across all review workflow commands
- Add missing Phase 5: Session Completion to review-fix.md
- Replace "Update dashboard" with "Generate fix-dashboard.html" to clarify initialization vs polling
- Remove REVIEW-SUMMARY.md generation (dashboard serves as primary output)
- Align phase names with Orchestrator section (e.g., "Planning Coordination", "Execution Orchestration")

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

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
catlog22
2025-11-26 20:16:35 +08:00
parent 2f4ecf9ae3
commit ef09914f94
3 changed files with 27 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
.claude/commands/workflow/review-fix.md
View File

@@ -58,17 +58,17 @@ Automated fix orchestrator with **two-phase architecture**: AI-powered planning
### Execution Flow ### Execution Flow
``` ```
1. Discovery & Initialization Phase 1: Discovery & Initialization
└─ Validate export file, create fix session structure, initialize state files → Generate fix-dashboard.html └─ Validate export file, create fix session structure, initialize state files → Generate fix-dashboard.html
2. Phase 2: Planning (@cli-planning-agent): Phase 2: Planning Coordination (@cli-planning-agent)
├─ Analyze findings for patterns and dependencies ├─ Analyze findings for patterns and dependencies
├─ Group by file + dimension + root cause similarity ├─ Group by file + dimension + root cause similarity
├─ Determine execution strategy (parallel/serial/hybrid) ├─ Determine execution strategy (parallel/serial/hybrid)
├─ Generate fix timeline with stages ├─ Generate fix timeline with stages
└─ Output: fix-plan.json (dashboard auto-polls for status) └─ Output: fix-plan.json (dashboard auto-polls for status)
3. Phase 3: Execution (Stage-based): Phase 3: Execution Orchestration (Stage-based)
For each timeline stage: For each timeline stage:
├─ Load groups for this stage ├─ Load groups for this stage
├─ If parallel: Launch all group agents simultaneously ├─ If parallel: Launch all group agents simultaneously
@@ -81,8 +81,11 @@ Automated fix orchestrator with **two-phase architecture**: AI-powered planning
│ └─ On success: Commit, update fix-progress-{N}.json │ └─ On success: Commit, update fix-progress-{N}.json
└─ Advance to next stage └─ Advance to next stage
4. Phase 4: Completion Phase 4: Completion & Aggregation
└─ Aggregate results → Generate fix-summary.md → Update history → Output summary └─ Aggregate results → Generate fix-summary.md → Update history → Output summary
Phase 5: Session Completion (Optional)
└─ If all fixes successful → Prompt to complete workflow session
``` ```
### Agent Roles ### Agent Roles

19
.claude/commands/workflow/review-module-cycle.md
View File

@@ -65,16 +65,16 @@ Independent multi-dimensional code review orchestrator with **hybrid parallel-it
### Execution Flow ### Execution Flow
``` ```
1. Discovery & Initialization 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 → Generate dashboard.html
2. Phase 2: Parallel Reviews (for each dimension): Phase 2: Parallel Reviews (for each dimension)
├─ Launch 7 review agents simultaneously ├─ Launch 7 review agents simultaneously
├─ Each executes CLI analysis via Gemini/Qwen on specified files ├─ Each executes CLI analysis via Gemini/Qwen on specified files
├─ Generate dimension JSON + markdown reports ├─ Generate dimension JSON + markdown reports
└─ Update review-progress.json └─ Update review-progress.json
3. Phase 3: Aggregation: Phase 3: Aggregation
├─ Load all dimension JSON files ├─ Load all dimension JSON files
├─ Calculate severity distribution (critical/high/medium/low) ├─ Calculate severity distribution (critical/high/medium/low)
├─ Identify cross-cutting concerns (files in 3+ dimensions) ├─ Identify cross-cutting concerns (files in 3+ dimensions)
@@ -82,15 +82,15 @@ Independent multi-dimensional code review orchestrator with **hybrid parallel-it
├─ Critical findings OR high > 5 OR critical files → Phase 4 (Iterate) ├─ Critical findings OR high > 5 OR critical files → Phase 4 (Iterate)
└─ Else → Phase 5 (Complete) └─ Else → Phase 5 (Complete)
4. Phase 4: Iterative Deep-Dive (optional): Phase 4: Iterative Deep-Dive (optional)
├─ Select critical findings (max 5 per iteration) ├─ Select critical findings (max 5 per iteration)
├─ Launch deep-dive agents for root cause analysis ├─ Launch deep-dive agents for root cause analysis
├─ Generate remediation plans with impact assessment ├─ Generate remediation plans with impact assessment
├─ Re-assess severity based on analysis ├─ Re-assess severity based on analysis
└─ Loop until no critical findings OR max iterations └─ Loop until no critical findings OR max iterations
5. Phase 5: Completion Phase 5: Completion
└─ Generate REVIEW-SUMMARY.md → Output path └─ Finalize review-progress.json → Output dashboard path
``` ```
### Agent Roles ### Agent Roles
@@ -274,10 +274,10 @@ echo "📊 Dashboard: file://$(cd ${sessionDir} && pwd)/.review/dashboard.html"
- Loop back to aggregation if still have critical/high findings - Loop back to aggregation if still have critical/high findings
**Phase 5: Completion** **Phase 5: Completion**
- Generate REVIEW-SUMMARY.md with all findings and statistics - Finalize review-progress.json with completion statistics
- Update review-state.json with completion_time and phase=complete - Update review-state.json with completion_time and phase=complete
- TodoWrite completion: Mark all tasks done - TodoWrite completion: Mark all tasks done
- Output: Dashboard path and REVIEW-SUMMARY.md path to user - Output: Dashboard path to user
@@ -303,8 +303,7 @@ echo "📊 Dashboard: file://$(cd ${sessionDir} && pwd)/.review/dashboard.html"
│ ├── security-cli-output.txt │ ├── security-cli-output.txt
│ ├── deep-dive-1-{uuid}.md │ ├── deep-dive-1-{uuid}.md
│ └── ... │ └── ...
├── REVIEW-SUMMARY.md # Final summary └── dashboard.html # Interactive dashboard (primary output)
└── dashboard.html # Interactive dashboard
``` ```
**Session Context**: **Session Context**:

19
.claude/commands/workflow/review-session-cycle.md
View File

@@ -58,16 +58,16 @@ Session-based multi-dimensional code review orchestrator with **hybrid parallel-
### Execution Flow (Simplified) ### Execution Flow (Simplified)
``` ```
1. Discovery & Initialization Phase 1: Discovery & Initialization
└─ Validate session, initialize state, create output structure → Generate dashboard.html └─ Validate session, initialize state, create output structure → Generate dashboard.html
2. Phase 2: Parallel Reviews (for each dimension): Phase 2: Parallel Reviews (for each dimension)
├─ Launch 7 review agents simultaneously ├─ Launch 7 review agents simultaneously
├─ Each executes CLI analysis via Gemini/Qwen ├─ Each executes CLI analysis via Gemini/Qwen
├─ Generate dimension JSON + markdown reports ├─ Generate dimension JSON + markdown reports
└─ Update review-progress.json └─ Update review-progress.json
3. Phase 3: Aggregation: Phase 3: Aggregation
├─ Load all dimension JSON files ├─ Load all dimension JSON files
├─ Calculate severity distribution (critical/high/medium/low) ├─ Calculate severity distribution (critical/high/medium/low)
├─ Identify cross-cutting concerns (files in 3+ dimensions) ├─ Identify cross-cutting concerns (files in 3+ dimensions)
@@ -75,15 +75,15 @@ Session-based multi-dimensional code review orchestrator with **hybrid parallel-
├─ Critical findings OR high > 5 OR critical files → Phase 4 (Iterate) ├─ Critical findings OR high > 5 OR critical files → Phase 4 (Iterate)
└─ Else → Phase 5 (Complete) └─ Else → Phase 5 (Complete)
4. Phase 4: Iterative Deep-Dive (optional): Phase 4: Iterative Deep-Dive (optional)
├─ Select critical findings (max 5 per iteration) ├─ Select critical findings (max 5 per iteration)
├─ Launch deep-dive agents for root cause analysis ├─ Launch deep-dive agents for root cause analysis
├─ Generate remediation plans with impact assessment ├─ Generate remediation plans with impact assessment
├─ Re-assess severity based on analysis ├─ Re-assess severity based on analysis
└─ Loop until no critical findings OR max iterations └─ Loop until no critical findings OR max iterations
5. Phase 5: Completion Phase 5: Completion
└─ Generate REVIEW-SUMMARY.md → Output path └─ Finalize review-progress.json → Output dashboard path
``` ```
### Agent Roles ### Agent Roles
@@ -254,10 +254,10 @@ echo "📊 Dashboard: file://$(cd ${sessionDir} && pwd)/.review/dashboard.html"
- Loop back to aggregation if still have critical/high findings - Loop back to aggregation if still have critical/high findings
**Phase 5: Completion** **Phase 5: Completion**
- Generate REVIEW-SUMMARY.md with all findings and statistics - Finalize review-progress.json with completion statistics
- Update review-state.json with completion_time and phase=complete - Update review-state.json with completion_time and phase=complete
- TodoWrite completion: Mark all tasks done - TodoWrite completion: Mark all tasks done
- Output: Dashboard path and REVIEW-SUMMARY.md path to user - Output: Dashboard path to user
@@ -283,8 +283,7 @@ echo "📊 Dashboard: file://$(cd ${sessionDir} && pwd)/.review/dashboard.html"
│ ├── security-cli-output.txt │ ├── security-cli-output.txt
│ ├── deep-dive-1-{uuid}.md │ ├── deep-dive-1-{uuid}.md
│ └── ... │ └── ...
├── REVIEW-SUMMARY.md # Final summary └── dashboard.html # Interactive dashboard (primary output)
└── dashboard.html # Interactive dashboard
``` ```
**Session Context**: **Session Context**: