Code review
Use when reviewing a branch, PR, diff, or implementation quality. Covers correctness, regression risk, security, maintainability, missing tests, architecture compliance, dependency changes, concurrency, data safety, and review comment quality.From its SKILL.md
npx -y skills add PetrovC/ai-agent-kit --skill code-reviewAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.5 KB, as published. Nobody here has run it
Code Review Skill
Goal
Find real problems before they reach production. Not cosmetic issues.
A good review catches: incorrect behavior, regressions, security holes, missing tests, and architectural drift. It does not nitpick style unless style hides a real problem.
Quick reference
| Focus | Check |
|---|---|
| Scope | Small, reviewable PRs (one concern per PR, < 200 lines preferred) |
| Security | Sanitized inputs, parameterized SQL, authorized endpoints, no committed secrets |
| Correctness | Handle async errors, prevent race conditions, check null/undefined boundary cases |
| Testing | Verify changed code is covered by automated unit/integration tests |
Full guidance
Extended how-to, patterns, anti-patterns, and checklists: SKILL.deep.md