Skillproof

io.github.SkillproofdevPublished by GitHub account Skillproofdevv1.0.1Updated Nov 10, 2026

Check whether a Claude Code skill was tested and whether it works before installing it.

VerifiedSTDIODesktop onlyKnowledge & MemoryDeveloper Tools

Overview

AI-generated overview

Looks up whether a Claude Code skill has been tested and whether it works, so an assistant can vet skills before installing them.

What you can do
  • Search the tested-skill catalog by task description, getting ranked matches with verdict, score, test notes and install command
  • Check one specific skill by name, slug or repository and get its verdict
  • Report pass, setup or didn't-pass verdicts, including skills that scored below a no-skill baseline
  • Say plainly when nothing has been tested for a job instead of guessing
When to use it
Useful when you are about to install or recommend a Claude Code skill found on GitHub and want evidence that it was actually run on a real task. Also handy when someone recommends a skill and you want a quick quality check.
Requirements
Runs locally over stdio via npx (Node 18 or newer). No API key or account. Needs network access to fetch the live catalog from skillproof.dev, cached for 15 minutes.
Before you install
Verdicts come from a third-party catalog and its scoring rubric, so treat them as one opinion rather than a guarantee. The server fetches catalog data from skillproof.dev on use, which reveals that you are querying it. It only reads catalog data; it does not install or run skills itself.

Installation

In SourceWeft

  1. Open Skillproof in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

SkillProof 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 baselineWhat our test found: Ran the bundled convert_markdown_to_wiki.py on a real sample doc: it silentlyturns **bold** text into wiki _italic_ (a genuine regex bug), and leaves standard GitHub-style tablescompletely 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

ToolWhat 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:

bash
claude mcp add skillproof -- npx -y skillproof-mcp

Or add it to your MCP config by hand:

json
{  "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

Source: README.md at commit 69dff9e

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.0.1LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts