Code Review Agent Skill
Review code changes for bugs, security issues, performance problems, and style violations. Use when asked to review code, a PR, or recent changes.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/owainlewis/youtube-tutorials --skill code-reviewThe instruction itself
4 sections, as written by the authorCode Review
When reviewing code, follow this process:
Step 1: Understand the Change
Run git diff (or git diff --staged for staged changes) to see what changed.
Read the modified files in full to understand the surrounding context.
Step 2: Check for Issues
Review each changed file for:
Correctness
- Logic errors, off-by-one errors, race conditions
- Missing null/undefined checks at system boundaries
- Incorrect error handling (swallowed errors, wrong error types)
Security
- SQL injection, XSS, command injection
- Hardcoded secrets or credentials
- Overly permissive file/network access
Performance
- N+1 queries, unnecessary loops, large allocations
- Missing indexes for new database queries
- Blocking operations in async code
Maintainability
- Unclear naming, overly complex logic
- Dead code, unused imports
- Missing types in TypeScript
Step 3: Report
Format your review as:
- Summary: One sentence on what the change does
- Issues: Specific problems with file paths and line numbers
- Suggestions: Optional improvements (clearly marked as optional)
Be direct. Don't pad with praise. Focus on things that matter.
Other skills for the same job
different authors, same section of the catalogue
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.
How to use it
Take owainlewis/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.