Output skill isn't being invoked by Claude

Check the SKILL.md frontmatter's description field — Claude's auto-invocation depends on it matching the user prompt.

Skill_Seekers — Installieren & Live-Demo

Warum nutzen

Hauptfunktionen

Three-phase pipeline: ingest → AI enhancement → export
Supports docs sites, GitHub repos, PDFs, videos, notebooks, wikis (18 source types)
Conflict detection — flags when docs disagree with the actual source code
Exports to 12 LLM platforms and 8 RAG frameworks from one source
Checkpoint/resume and async scraping for large sources

Live-Demo

In der Praxis

skill-seekers-skill.replay ▶ bereit

0/0

Installation

Repository des Autors · Offizielle Dokumentation zu Claude Skills

Anwendungsfälle

Praxisnahe Nutzung: Skill_Seekers

Turn a library's documentation site into a Claude skill in 10 minutes

👤 Developers who rely on a library Claude doesn't know well ⏱ ~15 min intermediate

Wann einsetzen: Claude keeps inventing function signatures for your favorite library because its training data is stale.

Voraussetzungen

URL of the library's docs site — The canonical ReadTheDocs, Docusaurus, or mintlify URL

Ablauf

Review the generated SKILL.md

Show me the frontmatter and the first 50 lines of the generated SKILL.md.✓ Kopiert

→ Valid YAML frontmatter, clear sections
Test with a real prompt

Now use the new example skill to do <representative task>.✓ Kopiert

→ Claude uses real API names, not hallucinated ones

Ergebnis: A new skill in your ~/.claude/skills/ folder that Claude picks up automatically.

Fallstricke

Docs-vs-code drift sneaks into the output — Let the conflict detector flag mismatches; skim the conflicts.md report it produces

Kombinieren mit: firecrawl · filesystem

Generate a skill directly from a GitHub repo's code and README

👤 Anyone onboarding Claude onto an internal or obscure OSS codebase ⏱ ~20 min intermediate

Wann einsetzen: No hosted docs exist — the README and the source are the only truth.

Ablauf

Run on the repo URL

Run skill-seekers on github.com/acme/internal-sdk, include code examples from tests/.✓ Kopiert

→ Extracts public API surface + example usage
Iterate on the skill

The first draft misses the auth flow — add a section on token setup.✓ Kopiert

→ SKILL.md expanded with that section

Ergebnis: A targeted skill Claude can invoke when working in that codebase.

Fallstricke

Repo is huge and scraping stalls — Use excludePaths to skip vendored directories and test fixtures

Kombinieren mit: github

Kombinationen

Mit anderen MCPs für 10-fache Wirkung

skill-seekers-skill + firecrawl

Firecrawl does the heavy JS-rendered scraping; Skill Seekers does the structuring

Use firecrawl to crawl the docs site, then skill-seekers to turn the output into a SKILL.md.✓ Kopiert

skill-seekers-skill + github

Pull repo contents via GitHub MCP, enhance into a skill

Fetch the acme/sdk repo's README, examples/, and types, then build a skill from them.✓ Kopiert

Werkzeuge

Was dieses MCP bereitstellt

Werkzeug	Eingaben	Wann aufrufen	Kosten
Ingest	source URL / repo / PDF path	First phase — gather source material	Free (plus any scraper API if used)
Enhance	ingested content, target platform	Second phase — AI-write the skill	LLM tokens for enhancement
Conflict-detect	docs + code sources	Whenever you ingest both docs and source	0
Export	target platform (Claude, Cursor, LangChain, etc.)	Third phase — package for destination	0

Kosten & Limits

Was der Betrieb kostet

API-Kontingent: None for the skill itself; depends on which scraper you pair with
Tokens pro Aufruf: Generation phase can use 10-50k tokens for a large library
Kosten in €: Free — the skill itself. Pairing scrapers (Firecrawl) may cost credits.
Tipp: Cache ingested content; re-run enhance/export without re-scraping.

Sicherheit

Rechte, Secrets, Reichweite

Credential-Speicherung: No credentials in the skill. Paired scrapers may need their own API keys.

Datenabfluss: Only to the sources you point it at

Respect robots.txt and ToS of the sites you scrape.

Fehlerbehebung

Häufige Fehler und Lösungen

Generated SKILL.md has placeholder sections

Source was too thin — re-run with more inputs (add the GitHub repo alongside the docs site).

Checkpoint resume starts over

Make sure you're running from the same working directory where the .skillseekers/ cache was created.

Prüfen: ls .skillseekers/

Alternativen

Skill_Seekers vs. andere

Alternative	Wann stattdessen	Kompromiss
skillforge	You want an interactive skill router that also creates skills on demand	Lighter generator; Skill Seekers is more thorough on heavy doc sources
Manual SKILL.md writing	The skill is small and you know the library cold	Faster for trivial skills; tedious at scale

Mehr

Ressourcen

📖 Offizielle README auf GitHub lesen

🐙 Offene Issues ansehen

🔍 Alle 400+ MCP-Server und Skills durchsuchen