Give your agents the skills they need.

Skills don’t work if your setup rejects them. Skillproof finds what you need and fits it into your setup — seamlessly, with your permission.

Paste one short prompt into any agentic AI — it installs Skillproof and starts your first session.

✓ Every skill here was checked to make sure it isn’t malicious before it was listed.

What’s a skill?

Skill — a small folder of instructions your AI reads so it does one job well (write honest tests, design cleaner pages). Agent — the AI (Claude, ChatGPT, Cursor…) doing the work for you. MCP — a plug that lets other tools talk to it. Your setup — the config files those tools already read (CLAUDE.md, installed skills, rules).

claude — 96×28
What are you trying to improve? Pick up to five — or describe it in your own words below.
Try:
Improving
Catalog ★ = GitHub stars
Build tray 0
This stack improves

Add items to see what your stack covers.

Install plan
# add items to build your install plan

Questions people ask first

What is a skill, in plain words?

A small folder of instructions your AI reads so it does one job well — honest tests, cleaner design, tighter research. Skillproof finds the right one and fits it into what you already have.

Does it change my files?

Only with your yes. It shows you the whole plan first — every file it would touch — keeps a backup, and tells you how to undo.

Is it safe?

Every listed skill was checked for malicious code before it was listed, and re-checked whenever its code changes — anything flagged is pulled and never shown. The Skillproof skill also reads a skill’s source before it runs a command from it, and nothing is ever piped into a shell. Still read anything before you run it.

What does it cost?

Free and open source. No account.

Which tools does it work with?

Any AI chat via the prompt (Claude, ChatGPT, Grok…); Claude Code via the skill; Cursor, Claude Desktop and any MCP-capable agent via the server.