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
Source: PetrovC/ai-agent-kit — distributed by TomeVault.
1---2name: petrovc-ai-agent-kit-code-review3description: Code Review Skill4---56# Code Review Skill78## Goal9Find real problems before they reach production. Not cosmetic issues.1011A good review catches: incorrect behavior, regressions, security holes, missing tests,12and architectural drift. It does not nitpick style unless style hides a real problem.1314## Quick reference1516| Focus | Check |17|---|---|18| Scope | Small, reviewable PRs (one concern per PR, < 200 lines preferred) |19| Security | Sanitized inputs, parameterized SQL, authorized endpoints, no committed secrets |20| Correctness | Handle async errors, prevent race conditions, check null/undefined boundary cases |21| Testing | Verify changed code is covered by automated unit/integration tests |2223## Full guidance24Extended how-to, patterns, anti-patterns, and checklists: [`SKILL.deep.md`](SKILL.deep.md)2526---27> Source: [PetrovC/ai-agent-kit](https://github.com/PetrovC/ai-agent-kit) — distributed by [TomeVault](https://tomevault.io).28<!-- tomevault:4.0:skill_md:2026-06-16 -->
tomevault-io