Skills Janitor
Plugin Verified Active7 skill hygiene tools: audit, health report, auto-fix, usage tracking, token cost analysis, GitHub search, and pre-install overlap check.
To help users maintain a clean, organized, and efficient ecosystem of AI coding skills by providing tools for auditing, quality checking, and cleanup.
Features
- Full skill inventory and audit
- Health reporting with linting and duplicate detection
- Automatic fixing of common skill issues
- Usage tracking to identify active and unused skills
- Context window token cost analysis per skill
- GitHub skill search and market comparison
- Pre-installation overlap check for new skills
Use Cases
- Use when you need to understand all installed AI skills and their status.
- Use when you want to identify and fix broken, duplicate, or low-quality skills.
- Use when you need to optimize token usage by removing unused skills.
- Use when evaluating a new skill before installation to check for conflicts.
Non-Goals
- Modifying skills from plugins or marketplace sources that might be overwritten.
- Deleting skills without explicit user confirmation or `--apply` flag.
- Automatically installing new skills or making widespread changes without review.
Installation
First, add the marketplace
/plugin marketplace add khendzel/skills-janitor/plugin install skills-janitor@skills-janitorContains 7 extensions
Skill (7)
Show all your installed skills
Automatically fix skill problems (safe preview first). Also use with --prune to find and remove broken symlinks, empty directories, and orphaned skills.
Check if a new skill overlaps with your existing ones before installing. Use when the user wants to evaluate a skill before adding it, check for duplicates pre-install, or verify a GitHub skill won't conflict.
Full health check of all your skills in one report. Use when the user wants to check for errors, find duplicates, detect broken skills, or get a complete overview of skill health.
Search GitHub for new skills to install. Also use with --compare to analyze a local skill against GitHub alternatives and marketplace competition.
Show how many context window tokens each skill consumes. Use when the user asks about token cost, context budget, skill size, or wants to know which skills waste the most context space.
Show which skills you use and which you never use
Quality Score
VerifiedSimilar Extensions
Modern Python
97Modern Python best practices. Use when creating new Python projects, and writing Python scripts, or migrating existing projects from legacy tools.
Dotforge Stack Python Fastapi
100Python 3.12+ with FastAPI, async/await, type hints, and Ruff linting rules for Claude Code.
Karpathy Coder
100Active coding discipline enforcer based on Karpathy's 4 principles: surface assumptions, keep it simple, make surgical changes, define verifiable goals. Ships 4 Python tools (complexity_checker, diff_surgeon, assumption_linter, goal_verifier), a review agent, /karpathy-check slash command, and a pre-commit hook. All tools stdlib-only.
Dotforge
100Node.js 20+ with Express/Fastify, TypeScript, and ESM module rules for Claude Code.
Si
100Self-Improving Agent: curate auto-memory, promote learnings to CLAUDE.md and rules, extract proven patterns into reusable skills. Provides /si:review, /si:promote, /si:extract, /si:status, and /si:remember slash commands.
Ruflo Security Audit
99Security review, dependency scanning, policy gates, and CVE monitoring