Performs systematic code review using standardized checklists across 8 categories (functionality, design, quality, readability, tests, security, performance, error handling) with BLOCKING/IMPORTANT/SUGGESTION/QUESTION/NOTE prefixes.
How this skill is triggered — by the user, by Claude, or both
Slash command
/universal-dev-standards:code-review-assistant [file path or branch | 檔案路徑或分支名稱][file path or branch | 檔案路徑或分支名稱]This skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
<!-- DEPRECATION NOTICE (XSPEC-086 Phase 4, 2026-04-28):
⚠️ Status: Reference(參考用,非可執行流程) — 程式碼審查流程協調(4 步驟序列、outcome gating)已於 2026-04-28 移至 adoption layer(XSPEC-095)。此處保留 8 大審查類別定義、BLOCKING/IMPORTANT/SUGGESTION/QUESTION/NOTE 前綴語意供參考。 Lifecycle orchestration has moved to the adoption layer (XSPEC-095); this document is reference-only. For enforced execution, use your adoption layer's toolchain.
Perform systematic code review using standardized checklists and comment prefixes.
執行系統性的程式碼審查,使用標準化的檢查清單和評論前綴。
📖 以下為流程的參考結構,非可執行步驟;自動化/強制執行請用 adoption layer 工具鏈(XSPEC-095)。 The steps below are a reference structure, not an executable workflow.
git diff or git show| Prefix | Meaning | Action | 動作 |
|---|---|---|---|
| BLOCKING | Must fix before merge | Required | 必須修復 |
| IMPORTANT | Should fix | Recommended | 建議修復 |
| SUGGESTION | Nice-to-have | Optional | 可選改善 |
| QUESTION | Need clarification | Discuss | 需要討論 |
| NOTE | Informational | FYI | 僅供參考 |
/code-review - Review all changes in current branch/code-review src/auth.js - Review specific file/code-review feature/login - Review specific branchAfter /code-review completes, the AI assistant should suggest:
程式碼審查完成。建議下一步 / Code review complete. Suggested next steps:
- 有 ❗ BLOCKING 項目 → 修復後重新執行
/code-review— Fix issues then re-run/code-review- 全部通過 → 執行
/checkin品質關卡 ⭐ Recommended / 推薦 — All passed → Run/checkinquality gates- 僅有 💡 SUGGESTION → 執行
/commit提交變更 — Only suggestions → Run/commit- 審查中發現規範不實用或缺失 → 執行
/audit --report回報 — Found impractical or missing standards → Run/audit --report
完整的 AI 行為定義請參閱對應的命令文件:
/code-reviewFor complete AI agent behavior definition, see the corresponding command file:
/code-review
npx claudepluginhub asiaostrich/universal-dev-standards --plugin universal-dev-standardsProvides a systematic checklist for code reviews covering functionality, code quality, security, performance, and tests. Useful when reviewing pull requests, conducting audits, or training developers.
Code review with semantic diffs, expert routing by file type, and auto-task creation for critical issues. Works on staged changes, files, or PRs.
Systematically evaluates pull requests for correctness, design, readability, and tests, delivering actionable and kind feedback based on Google's engineering practices.