Review a code change independently for correctness, regression risk, maintainability, compatibility, tests, and unsafe assumptions.
Scanned 9/11/2026
Install to Claude Code
npx -y skills add Dadmin88/hermes-profile-packs --skill code-review --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Code Review?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/dadmin88-code-review)More formats (shields.io, HTML) on the badges page.
---
name: code-review
description: Review a code change independently for correctness, regression risk, maintainability, compatibility, tests, and unsafe assumptions.
---
# Code Review
Use when implementation exists and needs independent technical review.
## Procedure
1. Read the stated goal and acceptance criteria before inspecting the diff.
2. Understand the changed behavior, boundaries, and affected callers or data paths.
3. Look for correctness bugs, missing edge cases, state inconsistencies, error-handling gaps, compatibility breaks, unsafe concurrency, and hidden assumptions.
4. Evaluate whether tests exercise the changed behavior and meaningful failure modes.
5. Separate blocking findings from suggestions. Give each finding a precise location, consequence, and rationale.
6. Verify suspicious claims by reading adjacent code or running targeted checks when practical.
7. Re-review fixes to blocking findings.
## Quality gate
A review should maximize signal. Do not bury important defects in style commentary or demand rewrites without a concrete engineering reason.Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.