k-skill-cleaner

nomadamas/k-skill

Interview users and audit skill usage to identify and recommend unused K-skills for removal.

What is k-skill-cleaner?

k-skill-cleaner helps you maintain a clean coding-agent skill environment by interviewing you about your workflow and analyzing trigger counts across installed K-skills. Use it to discover which skills you're not using and get removal recommendations to reduce clutter.

Interviews you about your coding workflow and skill usage patterns
Inspects trigger counts for all installed K-skills
Identifies unused or rarely-triggered skills
Recommends skills as candidates for removal
Helps keep your skill environment lean and focused

How to install k-skill-cleaner

npx skills add https://github.com/nomadamas/k-skill --skill k-skill-cleaner

Prerequisites

Node.js 18 or later
An existing K-skill installation with multiple skills installed
Access to skill trigger count data from your coding agent

Claude Code

Cursor

Windsurf

Cline

How to use k-skill-cleaner

1.Run `npx -y @nomadamas/k-skill@0 instruct k-skill-cleaner` to fetch full runtime-specific instructions
2.Answer the interview questions about your coding workflow and skill usage
3.Allow the skill to inspect trigger counts for your installed K-skills
4.Review the recommendations for unused or low-trigger skills
5.Decide which skills to remove based on the analysis

Use cases

Good for

Cleaning up your K-skill collection after installing many experimental skills
Identifying which installed skills you actually use versus which are dormant
Optimizing your coding-agent setup by removing low-value skills
Auditing skill usage before sharing your environment with teammates
Reducing cognitive load by removing skills you've outgrown

Who it's for

Developers managing multiple K-skill installations
Teams standardizing their coding-agent skill sets
Users looking to optimize their agent environment
Anyone with accumulated unused skills seeking cleanup guidance

k-skill-cleaner FAQ

What data does k-skill-cleaner inspect?

It analyzes trigger counts (how often each skill was invoked) for your installed K-skills and combines that with your interview responses about actual usage patterns.

Will this delete my skills automatically?

No. k-skill-cleaner only recommends removal; you must explicitly approve deletion of any skill.

How do I get the latest instructions?

Run `npx -y @nomadamas/k-skill@0 instruct k-skill-cleaner` each time—it detects your runtime and prints only applicable instructions.

Can I update all my skills at once?

Yes, use `npx -y @nomadamas/k-skill@0 update` to keep the CLI and all installed skills current.

What if I disagree with the removal recommendations?

The recommendations are advisory only. You control which skills stay or go based on your own workflow needs.

Full instructions (SKILL.md)

Source of truth, from nomadamas/k-skill.

name: k-skill-cleaner description: Interview the user and inspect coding-agent skill trigger counts to recommend unused K-skills for removal.

k-skill-cleaner

Get the full instructions (required first step)

Run this and follow its output as the primary instructions for this skill:

npx -y @nomadamas/k-skill@0 instruct k-skill-cleaner

The CLI detects the current runtime (Dolshoi vault/CloakBrowser vs generic) and prints only the applicable instructions, always up to date. Helper files bundled with the CLI are listed by:

npx -y @nomadamas/k-skill@0 files k-skill-cleaner

Keep the CLI and every coding-agent skill install current (including Vercel Agent Skills) with:

npx -y @nomadamas/k-skill@0 update

If npx is unavailable, install Node.js 18+ or follow https://github.com/NomaDamas/k-skill#readme, or read the source instructions at https://github.com/NomaDamas/k-skill/blob/main/k-skill-cleaner/instruction.md.

Hard rules even without the CLI

Never execute payment, message/email delivery, final submission, cancellation, or public posting without the user's explicit approval immediately beforehand.
Never ask for, print, or store plaintext credentials in chat, files, or shell arguments.
Never bypass legal, physical-presence, CAPTCHA, identity-proofing, or electronic-signature boundaries.