About skillproof
skillproof is an MCP server for finding and checking Claude Code skills before installation. It reports test results against a no-skill baseline, including cases that did not pass.
Key features
- 01Ranked skill search with verdicts
- 02Checks a skill by name or repository
- 03Real-task comparison with baseline
- 04Reports setup requirements and test notes
- 05Live catalog cached for 15 minutes
Use cases
- 01Find a tested skill for a task
- 02Evaluate a recommended skill before installing
- 03Review why a skill failed its test
MCP support
Exposes `find_skill` and `check_skill` tools to MCP clients, returning skill matches or a verdict with scores and test notes.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
2Saved tool list · updated 3w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| limit | number | No | Max results (default 5) |
| query | string | Yes | The job to do, e.g. "convert markdown to Confluence" or "spark tuning" |
| category | enum | No | Optional filterdocuments | coding | design | marketing | sales | data | productivity | writing | seo | crypto | testing | efficiency |
| include_failures | boolean | No | Include skills that failed our test (default true — knowing what NOT to install is the point) |
Details
From the project READMESkillProof MCP
Ask whether a Claude Code skill actually works — before you install it.
GitHub has tens of thousands of SKILL.md files. Almost none have been run by anyone but their author.
SkillProof installs them from their repo, triggers them, and runs them on a real
task against a no-skill baseline. This MCP server puts those verdicts in your agent's hands.
> is there a tested skill for converting markdown to Confluence?
## Confluence — DIDN'T PASS — scored below the no-skill baseline
What our test found: Ran the bundled convert_markdown_to_wiki.py on a real sample doc: it silently
turns **bold** text into wiki _italic_ (a genuine regex bug), and leaves standard GitHub-style tables
completely unconverted, despite SKILL.md listing "tables" among the elements it handles.
That is the whole point. A directory that only lists winners tells you nothing.
Tools
| Tool | What it answers |
|---|---|
find_skill | "Is there a tested skill for X?" — ranked matches with verdict, score, test notes, install command |
check_skill | "Someone recommended X — is it any good?" — the verdict for one skill by name, slug, or repo |
Every answer carries one of three verdicts:
- pass — installed, triggered, and beat the no-skill baseline on a real task.
- setup — works, but needs a manual step first (the notes say which).
- didn't pass — scored below the no-skill baseline: it either couldn't run, or left you worse off than not installing it.
If nothing has been tested for your job, the server says so instead of guessing. "Not tested" is a real answer.
Install
Claude Code:
claude mcp add skillproof -- npx -y skillproof-mcp
Or add it to your MCP config by hand:
{
"mcpServers": {
"skillproof": {
"command": "npx",
"args": ["-y", "skillproof-mcp"]
}
}
}
Works in any MCP client (Claude Code, Claude Desktop, Cursor, Windsurf, Zed). Node 18+. No API key, no account.
Where the data comes from
The server reads the live catalog at skillproof.dev/api/skills.json
and caches it for 15 minutes. Nothing is bundled, so verdicts are never stale. The scoring rubric —
install /5, triggering /5, output-vs-baseline /10, docs /5 — is published at
skillproof.dev/methodology.
Catalog data is CC BY 4.0: use it, cite skillproof.dev.
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.