Skill Claude CodeCodex
Keep local AI agent environments clean, explainable, and recoverable. Use for repo artifact governance, workspace cache audits, WSL2/Docker hygiene, package and model cache mapping, C-drive growth diagnosis, and safe cleanup boundaries. Prevent throwaway Markdown files, audit local development environment sprawl, and…
Command Claude Code
These are documentation triggers for hosts that map natural language or slash commands to skills. They do not install a runtime server.
Command Claude Code needs its repo
List suspicious root agent process files and placement directories.
Command Claude Code needs its repo
Classify a proposed path into tidy-skill Classes A–E before writing a file.
Command Claude Code needs its repo
One-shot read-only doctor for skill package presence and repo hygiene.
Command Claude Code needs its repo
Score the current repository hygiene 0–100.
Command Claude Code
Run a full read-only local hygiene pass on the current repository.
Cursor rule Cursor
洁癖.skill - prevent agents from littering the project root with temporary Markdown files.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: