Receiving Code Review

This one's about not being a pushover when someone drops review feedback on your code. It walks you through actually verifying suggestions against your codebase before implementing them, especially from external reviewers who might not know the full context. The pattern is straightforward: read, understand, verify it won't break things, then respond with technical reasoning or just fix it. What I like is the YAGNI check for when reviewers suggest "implementing properly" on features nobody even calls. It also bans performative responses like "Great point!" in favor of either asking clarifying questions or just showing the fix in code. Useful if you tend to auto-accept feedback without thinking it through first.

GitHub stars: 492
last updated: Jun 11, 2026

View on GitHub

Install

$ npx -y skills add ganyuanran/aegis --skill receiving-code-review --agent claude-code

Installs into .claude/skills of the current project.

Files

Code Review Reception

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

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

Forbidden Responses

NEVER:

"You're absolutely right!" (explicit CLAUDE.md violation)
"Great point!" / "Excellent feedback!" (performative)
"Let me implement that now" (before verification)

INSTEAD:

Restate the technical requirement
Ask clarifying questions
Push back with technical reasoning if wrong
Just start working (actions > words)

Handling Unclear Feedback

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.

SKILL.md on GitHub