一键导入
handling-code-review
Use when code review feedback requires fixes - emphasizes technical verification over performative agreement
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。
菜单
Use when code review feedback requires fixes - emphasizes technical verification over performative agreement
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
Execute a single phase with sequential task execution in an isolated worktree.
Execute implementation plan with autonomous subagent pipeline. Two-stage review (spec + quality). Flags only for critical blockers.
Use after /imagine completes to create an executable implementation plan (War Room phase).
Use when a user wants to develop a rough idea into a product design. Activates a virtual startup team that guides the user through Discovery, Definition, Validation, and Architecture phases. Creates session.yaml and four design documents.
Start the Office Dashboard to visualize /build progress in real-time
| name | handling-code-review |
| description | Use when code review feedback requires fixes - emphasizes technical verification over performative agreement |
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:
If there are open questions in the UNDERSTAND step, ask @office:team-lead who has more context on the project to explain it for you.
IF reviewer suggests "implementing properly":
FOR multi-item feedback:
Push back when:
How to push back:
When feedback IS correct:
Never use:
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:
No long apology. No defending why you pushed back. No 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 |
Performative Agreement (Bad):
Reviewer: "Remove legacy code"
"You're absolutely right! Let me remove that..."
Technical Verification (Good):
Reviewer: "Remove legacy code"
"Checking... build target is 10.15+, this API needs 13+. Need legacy for backward compat. Current impl has wrong bundle ID - fix it or drop pre-13 support?"
YAGNI (Good):
Reviewer: "Implement proper metrics tracking with database, date filters, CSV export"
"Grepped codebase - nothing calls this endpoint. Remove it (YAGNI)? Or is there usage I'm missing?"
Unclear Item (Good):
Human partner: "Fix items 1-6"
You understand 1,2,3,6. Unclear on 4,5.
"Understand 1,2,3,6. Need clarification on 4 and 5 before implementing."