A team of AI agents can now review your code for you. Each agent has a specialty like security, performance, or style. They work together to find problems and suggest fixes.
This system goes beyond simple tools. It checks for hidden issues like security holes and slow code. Developers get clear feedback right away.
Teams can catch bugs early and keep code quality high. The agents handle the hard work so you can focus on building.
Global
mkdir -p ~/.claude/skills/agent-code-review-swarmProject
mkdir -p .claude/skills/agent-code-review-swarmSource Repository
Web Design Guidelinesvercel-labs/agent-skills
Review your UI code for compliance with web interface guidelines
Improve Codebase Architecturemattpocock/skills
Scan your codebase for architecture improvements with visual reports and pick one to refactor
Zoom Outmattpocock/skills
Get a big picture view of your code with a simple map of modules and callers
Caveman Reviewjuliusbrussee/caveman
Ultra-compressed one-line code review comments that cut noise
Requesting Code Reviewobra/superpowers
Catch code issues early with focused automated reviews before every merge
Receiving Code Reviewobra/superpowers
Think first, then code. Verify feedback before making changes. Stay objective
Auditpbakaus/impeccable
Audit your code for accessibility performance theming and anti-patterns
Request Refactor Planmattpocock/skills
Plan safe code refactors with tiny commits and clear GitHub issues