oimiragieo
oimiragieo/agent-studio
相关职业SOC
基于 SOC 职业分类
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。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/oimiragieo/agent-studio --skill receiving-code-review命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
| name | receiving-code-review |
| description | Process and act on code review feedback. Use when receiving review results. |
| version | 1.1.0 |
| category | Development Workflow |
| agents | ["developer","code-reviewer"] |
| tags | ["code-review","feedback","fixes","resolution","sign-off"] |
| model | sonnet |
| invoked_by | both |
| user_invocable | true |
| tools | ["Read","Write","Edit","Bash"] |
| best_practices | ["Fix Critical issues immediately","Fix Important issues before proceeding","Note Minor issues for later","Push back with reasoning if reviewer is wrong"] |
| error_handling | graceful |
| streaming | supported |
| verified | true |
| lastVerifiedAt | "2026-02-22T00:00:00.000Z" |
| source | builtin |
| trust_score | 100 |
| provenance_sha | 4dc598146d71ebf4 |
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:
1. READ: Complete feedback without reacting
2. UNDERSTAND: Restate requirement in own words (or ask)
3. VERIFY: Check against codebase reality
4. EVALUATE: Technically sound for THIS codebase?
5. RESPOND: Technical acknowledgment or reasoned pushback
6. IMPLEMENT: One item at a time, test each
NEVER:
INSTEAD:
IF any item is unclear:
STOP - do not implement anything yet
ASK for clarification on unclear items
WHY: Items may be related. Partial understanding = wrong implementation.
Example:
Human: "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:
1. Check: Technically correct for THIS codebase?
2. Check: Breaks existing functionality?
3. Check: Reason for current implementation?
4. Check: Works on all platforms/versions?
5. Check: Does reviewer understand full context?
IF suggestion seems wrong:
Push back with technical reasoning
IF can't easily verify:
Say so: "I can't verify this without [X]. Should I [investigate/ask/proceed]?"
IF conflicts with human partner's prior decisions:
Stop and discuss with human partner first
Rule: "External feedback - be skeptical, but check carefully"
IF reviewer suggests "implementing properly":
grep codebase for actual usage
IF unused: "This endpoint isn't called. Remove it (YAGNI)?"
IF used: Then implement properly
Rule: "You and reviewer both report to me. If we don't need this feature, don't add it."
FOR multi-item feedback:
1. Clarify anything unclear FIRST
2. Then implement in this order:
- Blocking issues (breaks, security)
- Simple fixes (typos, imports)
- Complex fixes (refactoring, logic)
3. Test each fix individually
4. Verify no regressions
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]
NOT:
"You're absolutely right!"
"Great point!"
"Thanks for catching that!"
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."
NOT:
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 |
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: "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."
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.
| Anti-Pattern | Why It Fails | Correct Approach |
|---|---|---|
| Implementing all feedback without verification | Reviewer may lack full context; suggestion may break existing functionality | Verify each item against codebase before implementing |
| Starting implementation with unclear items | Missing context on item 4 corrupts items 1-3 that depend on it | Clarify all unclear items first; implement nothing until all items are understood |
| Expressing gratitude for feedback | Performative responses waste tokens and add no technical value | Respond with the technical fact (what was wrong, what was fixed) or just the code change |
| Batch-implementing without testing | One wrong fix corrupts the entire batch; regressions become invisible | Implement and test each item individually; commit checkpoints after each |
| Adding suggested features without checking usage | Implements dead code that must be maintained forever | Grep for actual usage first; if unused, confirm removal is the right answer |
Before starting:
Read .claude/context/memory/learnings.md
After completing:
.claude/context/memory/learnings.md.claude/context/memory/issues.md.claude/context/memory/decisions.mdASSUME INTERRUPTION: If it's not in memory, it didn't happen.
Agent frontmatter enhancements — disallowedTools, mcpServers scoping, fork_eligible field
Context management — pre-compact persistence, threshold alignment, microcompact/circuit breaker detection
Hook enhancements — updatedInput for bash safety prefixes, suppressOutput for verbose blocks, denial-based routing feedback
基于 SOC 职业分类