Skills for Real Engineers. Straight from my .agents directory.
requesting-code-review
Agent skill fromGanyuanRan/Aegis
Use when requesting independent code review, after implementation slices, before merging high-risk work, or when verification exposes evidence, baseline, architecture, compatibility, or retirement uncertainty.
How to install requesting-code-review
npx skills add GanyuanRan/Aegis# or add only this skill to Claude Code: copy the folder
skills/requesting-code-review/
# into
~/.claude/skills/requesting-code-review/ (all projects)
.claude/skills/requesting-code-review/ (one project)
1# Requesting Code Review23Dispatch a reviewer subagent using the canonical `code-reviewer.md` template to4catch issues before they cascade. The reviewer gets precisely crafted context5for evaluation — never your session's history. This keeps the reviewer focused6on the work product, not your thought process, and preserves your own context7for continued work.89This skill is the canonical review-request workflow for method-pack implementation work. Use it to request review only after you have enough evidence, enough context, and a clear authority boundary for what the reviewer is being asked to assess.1011**Core principle:** Review early, review often.1213**Findings First:** Reviews lead with concrete findings before summary. Use14bugs first, risk first, tests first. Strengths and general assessment are still15useful, but they must not bury correctness, evidence, architecture, or16retirement problems.1718Review readiness is not merge approval. A review can reduce uncertainty and19recommend readiness, but it does not replace `verification-before-completion`20and does not grant completion authority.2122## When to Request Review2324**Mandatory:**25- After each task in subagent-driven development26- After completing major feature27- Before merge to main2829**Optional but valuable:**30- When stuck (fresh perspective)31- Before refactoring (baseline check)32- After fixing complex bug3334## Required Outputs3536Before you leave this workflow, you must be able to state:37381. **What exact scope is being reviewed**39…
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
