Back to list
asadullah48

receiving-code-review

by asadullah48

Unified Claude.ai Skills Marketplace - 39+ production-ready skills for development workflows, hackathon projects, and AI automation

0🍴 1📅 Jan 24, 2026

SKILL.md


name: receiving-code-review description: Use when receiving code review feedback - requires technical evaluation before implementing suggestions, with verification and reasoned pushback when appropriate

Receiving Code Review

Overview

Code review requires technical evaluation, not emotional performance.

Core principle: Verify before implementing. Ask before assuming. Technical correctness over social comfort.

The Response Pattern

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

Forbidden Responses

NEVER:

  • "You're absolutely right!"
  • "Great point!" / "Excellent feedback!"
  • "Let me implement that now"
  • Any gratitude expressions

INSTEAD:

  • Restate the technical requirement
  • Ask clarifying questions
  • Push back with technical reasoning if wrong
  • Just start working

Handling Unclear Feedback

IF any item is unclear:
  STOP - do not implement anything yet
  ASK for clarification on unclear items

Example:

Human: "Fix items 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."

Source-Specific Handling

From your human partner

  • Trusted - implement after understanding
  • Still ask if scope unclear
  • No performative agreement
  • Skip to action or technical acknowledgment

From External Reviewers

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

YAGNI Check

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

Implementation Order

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

When To Push Back

Push back when:

  • Suggestion breaks existing functionality
  • Reviewer lacks full context
  • Violates YAGNI (unused feature)
  • Technically incorrect for this stack
  • Legacy/compatibility reasons exist
  • Conflicts with architectural decisions

How to push back:

  • Use technical reasoning, not defensiveness
  • Ask specific questions
  • Reference working tests/code

Acknowledging Correct Feedback

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]

No thanks - Actions speak. Just fix it.

Common Mistakes

MistakeFix
Performative agreementState requirement or just act
Blind implementationVerify against codebase first
Batch without testingOne at a time, test each
Assuming reviewer is rightCheck if breaks things

Score

Total Score

70/100

Based on repository quality metrics

SKILL.md

SKILL.mdファイルが含まれている

+20
LICENSE

ライセンスが設定されている

+10
説明文

100文字以上の説明がある

+10
人気

GitHub Stars 100以上

0/15
最近の活動

3ヶ月以内に更新がある

0/10
フォーク

10回以上フォークされている

0/5
Issue管理

オープンIssueが50未満

+5
言語

プログラミング言語が設定されている

+5
タグ

1つ以上のタグが設定されている

0/5

Reviews

💬

Reviews coming soon