Review code for quality, security, and best practices. Use when analyzing code, suggesting improvements, or conducting code reviews.
npx skills add https://github.com/coleam00/custom-agent-with-skills --skill code_review
Provides comprehensive code review capabilities covering quality, security, and best practices analysis.
When conducting a code review, follow these steps in order:
Read the code thoroughly and identify:
Evaluate the code against best practices. Load the best practices guide for comprehensive checks:
references/best_practices.md - Comprehensive coding standards and practicesKey areas to check:
Check for security vulnerabilities. Load the security checklist for detailed guidance:
references/security_checklist.md - Security review checklist based on OWASP guidelinesKey security areas:
Identify code smells and antipatterns. Load the antipatterns guide for reference:
references/common_antipatterns.md - Common antipatterns and how to fix themCommon issues to look for:
Compile findings into a structured report:
## Code Review Summary
**File/Module**: [name]
**Language**: [language]
**Overall Assessment**: [Excellent/Good/Needs Improvement/Critical Issues]
### Strengths
- [List positive aspects]
### Issues Found
#### Critical (Must Fix)
- [Security vulnerabilities, bugs]
#### Major (Should Fix)
- [Significant antipatterns, bad practices]
#### Minor (Consider Fixing)
- [Style issues, small improvements]
### Recommendations
1. [Specific actionable recommendations]
2. [...]
### Resources Referenced
- [List which reference files were consulted]
Reference these files for detailed guidance during reviews:
references/best_practices.md - Comprehensive coding best practices covering organization, naming, error handling, testing, and documentationreferences/security_checklist.md - Security review checklist covering OWASP Top 10, input validation, authentication, and common vulnerabilitiesreferences/common_antipatterns.md - Guide to detecting and fixing common antipatterns like god classes, spaghetti code, and resource leaksUser asks: "Can you review this function?"
Response approach:
references/best_practices.md if needed)User asks: "Check this code for security vulnerabilities"
Response approach:
references/security_checklist.md for comprehensive security checksUser asks: "I need a thorough code review of my authentication module"
Response approach:
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
Execute git commit with conventional commit message analysis, intelligent staging, and message generation. Use when user asks to commit changes, create a git commit, or mentions "/commit". Supports: (1) Auto-detecting type and scope from changes, (2) Generating conventional commit messages from diff, (3) Interactive commit with optional type/scope/description overrides, (4) Intelligent file staging for logical grouping
Comprehensive GitHub code review with AI-powered swarm coordination
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
Use this skill to review code. It supports both local changes (staged or working tree) and remote Pull Requests (by ID or URL). It focuses on correctness, maintainability, and adherence to project standards.
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.
Create high-quality git commits: review/stage intended changes, split into logical commits, and write clear commit messages (including Conventional Commits). Use when the user asks to commit, craft a commit message, stage changes, or split work into multiple commits.
Take coleam00/code_review from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.