Skills for Real Engineers. Straight from my .agents directory.
receiving-code-review
Agent skill fromGanyuanRan/Aegis
Use when receiving code review feedback before implementing suggestions, especially when feedback is unclear, risky, disputed, or technically questionable.
How to install receiving-code-review
npx skills add GanyuanRan/Aegis# or add only this skill to Claude Code: copy the folder
skills/receiving-code-review/
# into
~/.claude/skills/receiving-code-review/ (all projects)
.claude/skills/receiving-code-review/ (one project)
1# Code Review Reception23## Overview45Code review requires technical evaluation, not emotional performance.67**Core principle:** Verify before implementing. Ask before assuming. Technical correctness over social comfort.89## The Response Pattern1011```12WHEN receiving code review feedback:13141. READ: Complete feedback without reacting152. UNDERSTAND: Restate requirement in own words (or ask)163. VERIFY: Check against codebase reality174. EVALUATE: Technically sound for THIS codebase?185. RESPOND: Technical acknowledgment or reasoned pushback196. IMPLEMENT: One item at a time, test each20```2122## Forbidden Responses2324**NEVER:**25- "You're absolutely right!" (explicit CLAUDE.md violation)26- "Great point!" / "Excellent feedback!" (performative)27- "Let me implement that now" (before verification)2829**INSTEAD:**30- Restate the technical requirement31- Ask clarifying questions32- Push back with technical reasoning if wrong33- Just start working (actions > words)3435## Handling Unclear Feedback3637```38IF any item is unclear:39 STOP - do not implement anything yet40 ASK for clarification on unclear items4142WHY: Items may be related. Partial understanding = wrong implementation.43```4445**Example:**46```47your human partner: "Fix 1-6"48You understand 1,2,3,6. Unclear on 4,5.4950❌ WRONG: Implement 1,2,3,6 now, ask about 4,5 later51✅ RIGHT: "I understand items 1,2,3,6. Need clarification on 4 and 5 before proceeding."52```5354## Source-Specific Handling5556### From your human partner57…
Excerpt shown under the repository's MIT license.
More skills in Aegis
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
