Skill Cabinet: CLI Tool for Auditing Local AI Skills

X postBen WilliamsTool

Ben Williams has released Skill Cabinet, a CLI utility designed to scan multiple local directories, review installed AI skills, and clean them up.

Key points

  1. Can be run directly via 'npx skill-cabinet'.
  2. Scans the local filesystem across various locations where skills are installed.
  3. Provides an interface to inspect and clean up experimental or cluttered skill setups.
  4. Quickly received updates, including version 0.4.0 following community feedback.

Why it matters

When experimenting with various AI agent skills, local filesystems tend to accumulate stale configurations across different paths. Skill Cabinet simplifies regular maintenance without requiring manual inspection of hidden dotfiles.

Analysis

Skill Cabinet addresses a growing workflow friction point as local AI agent tooling expands. Providing a quick, centralised overview helps developers keep their development environment clean when evaluating third-party skills.

Original post

Ben Williams

@theplgeek · 31 August 2026

Folks, please enjoy Skill Cabinet. 🗄️ npx skill-cabinet If you're anything like me, at some point you're local skills situation has gotten somewhat messy. Even if you're organised and managing them through Git you'll probably still be installing stuff locally just to test out t.co/e58m8QkIwX

1.1k likes43 replies2k bookmarks78.4k views

View on X
More posts in the thread (9)
  1. @JadMadi Oh that's a great idea 💡
  2. @doodlestein Cheers Jeffrey, hope you're well dude
  3. @smtng_mendex hah nice!
  4. @shyamshanckin7 looks cool - pretty different use case though
  5. @JadMadi here you go t.co/2Fse75DEHe
  6. @scottfwalter Good shout - fixed in 0.4.0 npx skill-cabinet@latest
  7. @austinshandle Nice idea I’ll take a look tomorrow - movie night with the kids tonight. Cheers Austin
  8. @_robguss hope you find it useful!
  9. @0xTAW94 here ya go t.co/cmfBoF05i7
Selected replies (5)
  • @shyamshanckin7 @theplgeek Interesting! We’ve built something similar, but it’s extended to many practical scenarios of how skills will be used going forward in a systematic way. Check it out : t.co/8tPPGvvHIX
  • @JadMadi @theplgeek Nice! I loved it. It was much needed, to be honest, and came right on time. If you accept issues on X, I'd love to see it distinguish between original files and symlinks.
  • @doodlestein @theplgeek Looks cool, I’ll check it out!
  • @krysamon @shyamshanckin7 @theplgeek Awesome! I really needed to manage my skills visually.
  • @shezmalik @theplgeek been avoiding eye contact with ~/.claude/skills

Links and tools from this entry

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Similar in content, found by the AI search.

  • Repository:vercel-labs/skills

    vercel-labs/skills: Universal CLI for AI Agent Skills

    skills is an open-source CLI by Vercel Labs designed to discover, install, and execute modular capabilities across coding agents including Claude Code, Cursor, OpenCode, and Codex.

    31.8kstarsTypeScript

    AI & LLMs· Tool

  • Repository:mattpocock/skills

    mattpocock/skills: Modular Agent Skills for Real Software Engineering

    Matt Pocock shares a curated collection of agent skills taken directly from his own development setup. The project positions itself against rigid frameworks like GSD, BMAD, and Spec-Kit, as well as uncontrolled 'vibe coding'. Instead, it provides small, composable, and adaptable skills compatible with Claude Code, Codex, and other coding agents.

    247.2kstarsShell

    AI & LLMs· Tool

  • Repository:Bennyoooo/Airbot

    Airbot: Self-Evolving Skills for Coding Agents

    Airbot (distributed via the skillmaxxing CLI) hooks into coding agents such as Claude Code and Codex to automatically capture reusable workflows and repo nuances as evolving skills without manual intervention.

    22starsTypeScript

    AI & LLMs· Tool

  • Link:Brian Lovin

    deslop: AI Code Cleanup Skill

    “deslop” is an agent skill created by Brian Lovin designed to remove AI-generated code slop from Git branches. It inspects branch diffs against the main branch to eliminate unnatural comments, redundant error handling, and improper type casts.

    AI & LLMs· Tool

Let's talk about your project

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.