AI tools can write code fast but sometimes add unnecessary extras. Comments that do not fit, extra checks, or style issues can clutter your work. This skill helps you clean up that AI slop from your current branch. It compares your code to the main branch and removes what does not belong. You get a clean codebase that looks like a human wrote it.
After you write code with AI, run this skill. It finds extra comments, defensive try/catch blocks, and type casts that are not normal for your project. It also fixes any style that does not match the rest of the file. The result is a report that tells you what changed in one to three sentences. This keeps your code consistent and easy to review.
Anyone who uses AI code generation will benefit. Developers can spend less time manually cleaning up. Teams get cleaner pull requests and fewer arguments about style. This skill makes AI code feel more natural and professional.
Global
mkdir -p ~/.claude/skills/deslopProject
mkdir -p .claude/skills/deslopSource Repository
Improve Codebase Architecturemattpocock/skills
Scan your codebase for architecture improvements with visual reports and pick one to refactor
Web Design Guidelinesvercel-labs/agent-skills
Review your UI code for compliance with web interface guidelines
Caveman Reviewjuliusbrussee/caveman
Ultra-compressed one-line code review comments that cut noise
Zoom Outmattpocock/skills
Get a big picture view of your code with a simple map of modules and callers
Codebase Designmattpocock/skills
Create deep modules with tiny interfaces and lots of hidden logic for testability
Requesting Code Reviewobra/superpowers
Catch code issues early with focused automated reviews before every merge
Request Refactor Planmattpocock/skills
Plan safe code refactors with tiny commits and clear GitHub issues
Receiving Code Reviewobra/superpowers
Think first, then code. Verify feedback before making changes. Stay objective