Making a small improvement to your code can be fast and easy. This process helps you do that without any extra steps. It focuses on low risk changes that you can confirm with tests.
The AI chooses a classic refactoring technique like extract function or guard clauses. You give a single confirmation. Then the AI changes the code and runs your tests to prove it still works the same.
This process only applies to small changes inside one file or function. If the change is larger or changes what the code does, the AI will suggest a full refactoring instead.
Global
mkdir -p ~/.claude/skills/cs-refactor-ffProject
mkdir -p .claude/skills/cs-refactor-ffSource 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