Every time you edit a file, this skill checks your code for quality issues. It runs auto-formatting and linting silently in the background. Most problems get fixed automatically by Claude-powered subprocesses. You only see a message if something is still broken. This helps developers keep their code clean without extra work.
The skill protects your linter settings from being changed by the AI. It also blocks old package managers and forces you to use modern tools. This prevents the agent from skipping quality checks.
It works with Python, TypeScript, Shell, YAML, JSON, TOML, Markdown, and Dockerfile. Anyone who uses Claude Code for coding will benefit from fewer formatting issues and better code quality.
Global
mkdir -p ~/.claude/skills/plankton-code-qualityProject
mkdir -p .claude/skills/plankton-code-qualitySource 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