Skip to content
/code-reviewerStable

Reviews code for bugs, logic errors, security vulnerabilities, and adherence to project conventions.

QualitySecurity· 1 min read

Quick import: Download the .md file and save it to .claude/commands/ (Claude Code), .cursorrules (Cursor), or paste as a system prompt in ChatGPT, Gemini, or any LLM API.

#What it does

The /code-reviewer skill performs a comprehensive code review on your recent changes. It checks for bugs, logic errors, security vulnerabilities, code quality issues, and adherence to project conventions.

#How to use

bash
/code-reviewer

The skill automatically detects your unstaged changes (via git diff) and reviews them. You can also point it at specific files.

#What it checks

  • Bugs & Logic Errors — Off-by-one errors, null pointer risks, race conditions, incorrect boolean logic
  • Security Vulnerabilities — Injection risks, hardcoded secrets, insecure crypto, XSS/CSRF
  • Code Quality — Dead code, unnecessary complexity, naming issues, missing error handling
  • Project Conventions — Adherence to CLAUDE.md rules, consistent patterns, proper typing

#Configuration

The skill reads your project's CLAUDE.md and .claude/ configuration to understand your conventions. No additional setup required.

#Example output

## Code Review: 3 files changed

### src/api/users.ts
- [HIGH] Line 42: SQL injection risk — user input concatenated into query string
- [MEDIUM] Line 78: Missing error handling on database call

### src/components/Form.tsx
- [LOW] Line 15: Unused import `useState`
Orel Ohayon·
View all skills