code-review-workflow
Skill3 starsChanged 9 months agoApache-2.0View on GitHub
Complete code review workflow for PR/MR with multiple reviewers and automated checks. Triggers: PRW, 審查流程, review workflow, PR review, MR review, pull request, merge request, 程式碼審查流程, full review, 完整審查.
6 other projects use a version of this.
Adopted by
Most recently taken up by
- Resgrid/Coretheir own version, first seen Oct 8, 2026
- Abdox-menara/guard-skillstheir own version, first seen Aug 24, 2026
- 2702207741-dev/agent-skills-pipelinetheir own version, first seen Jul 9, 2026
- agent-packs/registrytheir own version, first seen Jun 15, 2026
- codecharmhq/claude-code-skillstheir own version, first seen May 17, 2026
- thoitiettxl-cyber/Claw-IItheir own version, first seen Apr 3, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- Resgrid/Core★ 238same name
- thoitiettxl-cyber/Claw-II★ 2same name
- 2702207741-dev/agent-skills-pipeline★ 1same name
- codecharmhq/claude-code-skills★ 1same name
- Abdox-menara/guard-skills★ 0same name
- agent-packs/registry★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository21 other files it gives its agents.
- .github/copilot-instructions.mdCopilot instructions
- bug-fixSkill
- changelog-updaterSkill
- code-auditSkill
- code-refactorSkill
- code-reviewerSkill
- ddd-architectSkill
- feature-developmentSkill
- git-doc-updaterSkill
- git-precommitSkill
- memory-checkpointSkill
- memory-updaterSkill
- project-initSkill
- readme-i18nSkill
- readme-updaterSkill
- releaseSkill
- roadmap-updaterSkill
- security-reviewerSkill
- skill-generatorSkill
- skill-health-checkSkill
- test-generatorSkill
The file
Files
程式碼審查工作流
描述
完整的 PR/MR 審查流程,整合自動化檢查和多維度審查。
觸發條件
- 「審查 PR」「review PR」「審查流程」
- 「PRW: [PR 連結或分支]」
🔍 審查流程
┌─────────────────────────────────────────────────────────────┐
│ Code Review Workflow │
├─────────────────────────────────────────────────────────────┤
│ Phase 1: 📋 概覽 (Overview) │
│ ├─ 列出變更檔案 │
│ ├─ 統計變更行數 │
│ └─ 識別變更範圍 │
├─────────────────────────────────────────────────────────────┤
│ Phase 2: 🤖 自動化檢查 (Automated) │
│ ├─ 靜態分析 (ruff, mypy) │
│ ├─ 死碼檢測 (vulture) │
│ ├─ 安全掃描 (bandit) │
│ └─ 測試執行 │
├─────────────────────────────────────────────────────────────┤
│ Phase 3: 🏗️ 架構審查 (Architecture) │
│ ├─ [ddd-architect] DDD 合規檢查 │
│ ├─ 依賴方向驗證 │
│ └─ 模組化評估 │
├─────────────────────────────────────────────────────────────┤
│ Phase 4: 🔒 安全審查 (Security) │
│ ├─ [security-reviewer] OWASP 檢查 │
│ ├─ 敏感資料偵測 │
│ └─ 認證/授權審查 │
├─────────────────────────────────────────────────────────────┤
│ Phase 5: 📝 程式碼審查 (Code) │
│ ├─ [code-reviewer] 品質審查 │
│ ├─ 可讀性評估 │
│ ├─ 效能考量 │
│ └─ 測試覆蓋率 │
├─────────────────────────────────────────────────────────────┤
│ Phase 6: 📊 總結 (Summary) │
│ ├─ 生成審查報告 │
│ ├─ 建議修改項目 │
│ └─ 批准/請求修改 │
└─────────────────────────────────────────────────────────────┘🚀 使用範例
基本用法
「審查 PR」
AI 執行:
1. 📋 取得變更檔案列表
2. 🤖 執行自動化檢查
3. 🏗️ 驗證 DDD 架構
4. 🔒 執行安全審查
5. 📝 逐檔案程式碼審查
6. 📊 生成審查報告指定檔案
「PRW: 審查 src/auth/ 目錄的變更」
AI 執行:
1. 僅審查指定目錄
2. 重點關注認證相關安全問題📊 輸出格式
## 📋 程式碼審查報告
### 變更概覽
| 項目 | 數量 |
|------|------|
| 變更檔案 | 8 |
| 新增行數 | +245 |
| 刪除行數 | -32 |
| 測試檔案 | 3 |
### 🤖 自動化檢查
| 檢查項目 | 狀態 | 詳情 |
|----------|------|------|
| ruff lint | ✅ | 0 issues |
| mypy | ⚠️ | 2 warnings |
| vulture | ✅ | 0 dead code |
| bandit | ✅ | 0 security issues |
| pytest | ✅ | 42/42 passed |
### 🏗️ 架構審查
- ✅ DDD 層級正確分離
- ✅ 依賴方向符合規範
- ⚠️ `UserService` 建議拆分 (180 行)
### 🔒 安全審查
- ✅ 無 OWASP Top 10 風險
- ✅ 無硬編碼敏感資料
- ⚠️ 建議加入 rate limiting
### 📝 程式碼審查
#### 必須修改 (Blocking)
1. **src/auth/service.py:45**
- 問題:缺少 None 檢查
- 建議:加入防禦性檢查
#### 建議修改 (Non-blocking)
1. **src/auth/dto.py:12**
- 問題:命名不夠清晰
- 建議:`data` → `user_credentials`
#### 優點 (Positive)
- 測試覆蓋完整 (92%)
- 錯誤處理得當
- 文檔清楚
### 📊 總結
| 項目 | 評分 |
|------|------|
| 品質 | ⭐⭐⭐⭐ |
| 安全 | ⭐⭐⭐⭐⭐ |
| 架構 | ⭐⭐⭐⭐ |
| 測試 | ⭐⭐⭐⭐⭐ |
**結論**: 🟡 **請求修改** - 修復 1 個 blocking issue 後可合併⚙️ 配置選項
| 參數 | 說明 | 預設值 |
--quick | 快速審查(僅自動化) | false |
--security-only | 僅安全審查 | false |
--skip-tests | 跳過測試執行 | false |
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

