菜单
Guides agents in rigorously evaluating and applying code review feedback. Use when receiving code review comments, PR feedback, or external suggestions that may affect code correctness, architecture, or scope.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | receiving-code-review |
| description | Guides agents in rigorously evaluating and applying code review feedback. Use when receiving code review comments, PR feedback, or external suggestions that may affect code correctness, architecture, or scope. |
Code review requires technical evaluation, not emotional performance.
Core principle: Verify before implementing. Ask before assuming. Technical correctness over social comfort.
WHEN receiving code review feedback:
NEVER:
INSTEAD:
IF any item is unclear:
WHY: Items may be related. Partial understanding = wrong implementation.
Example:
your human partner: "Fix 1-6" You understand 1,2,3,6. Unclear on 4,5.
❌ WRONG: Implement 1,2,3,6 now, ask about 4,5 later ✅ RIGHT: "I understand items 1,2,3,6. Need clarification on 4 and 5 before proceeding."
BEFORE implementing:
IF suggestion seems wrong:
IF can't easily verify:
IF conflicts with your human partner's prior decisions:
your human partner's rule: "External feedback - be skeptical, but check carefully"
IF reviewer suggests "implementing properly":
IF unused: "This endpoint isn't called. Remove it (YAGNI)?" IF used: Then implement properly
your human partner's rule: "You and reviewer both report to me. If we don't need this feature, don't add it."
FOR multi-item feedback:
Push back when:
How to push back:
Signal if uncomfortable pushing back out loud: "Strange things are afoot at the Circle K"
When feedback IS correct:
✅ "Fixed. [Brief description of what changed]" ✅ "Good catch - [specific issue]. Fixed in [location]." ✅ [Just fix it and show in the code]
❌ "You're absolutely right!" ❌ "Great point!" ❌ "Let me implement that now" ❌ ANY gratitude expression
Why no thanks: Actions speak. Just fix it. The code itself shows you heard the feedback.
If you catch yourself about to write "Thanks": DELETE IT. State the fix instead.
If you pushed back and were wrong:
✅ "You were right - I checked [X] and it does [Y]. Implementing now." ✅ "Verified this and you're correct. My initial understanding was wrong because [reason]. Fixing."
❌ Long apology ❌ Defending why you pushed back ❌ Over-explaining
State the correction factually and move on.
| Mistake | Fix |
|---|---|
| Performative agreement | State requirement or just act |
| Blind implementation | Verify against codebase first |
| Batch without testing | One at a time, test each |
| Assuming reviewer is right | Check if breaks things |
| Avoiding pushback | Technical correctness > comfort |
| Partial implementation | Clarify all items first |
| Can't verify, proceed anyway | State limitation, ask for direction |
When replying to inline review comments on GitHub, reply in the comment thread (gh api repos/{owner}/{repo}/pulls/{pr}/comments/{id}/replies), not as a top-level PR comment.
External feedback = suggestions to evaluate, not orders to follow.
Verify. Question. Then implement.
No performative agreement. Technical rigor always.
Adds purposeful debug logging for observability without changing behavior. Use when adding or improving logs around flow, branching, external calls, or error context.
Generates and reviews conventional git commit messages. Use when drafting or refining commit messages for staged changes, or checking commit quality.
Writes and reviews Python docstrings in Google style. Use when creating or updating docstrings for Python functions, methods, classes, or modules.
Help write and review focused pytest tests as standalone functions (one behavior per test), avoiding test classes. Use when the user mentions pytest, tests, coverage, or wants help improving or generating tests.
Manages Python dependencies and scripts using uv only. Use when adding, upgrading, removing, or syncing Python packages, or when running Python scripts and managing their dependencies.
