woodshed MCP — Anwendungsfälle, Installieren & Live-Demo

Warum nutzen

Hauptfunktionen

Scaffolds new skills with clean SKILL.md + structure
Runs test cases against the skill
Captures ratings and qualitative notes
Iterates on the skill's prompts based on feedback
Track record of which changes helped

Live-Demo

In der Praxis

woodshed-skill.replay ▶ bereit

0/0

Installieren

Wählen Sie Ihren Client

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "woodshed-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/gaearon/woodshed",
        "~/.claude/skills/woodshed"
      ],
      "_inferred": true
    }
  }
}

Öffne Claude Desktop → Settings → Developer → Edit Config. Nach dem Speichern neu starten.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "woodshed-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/gaearon/woodshed",
        "~/.claude/skills/woodshed"
      ],
      "_inferred": true
    }
  }
}

Cursor nutzt das gleiche mcpServers-Schema wie Claude Desktop. Projektkonfiguration schlägt die globale.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "woodshed-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/gaearon/woodshed",
        "~/.claude/skills/woodshed"
      ],
      "_inferred": true
    }
  }
}

Klicken Sie auf das MCP-Servers-Symbol in der Cline-Seitenleiste, dann "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "woodshed-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/gaearon/woodshed",
        "~/.claude/skills/woodshed"
      ],
      "_inferred": true
    }
  }
}

Gleiche Struktur wie Claude Desktop. Windsurf neu starten zum Übernehmen.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "woodshed-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/gaearon/woodshed",
        "~/.claude/skills/woodshed"
      ]
    }
  ]
}

Continue nutzt ein Array von Serverobjekten statt einer Map.

~/.config/zed/settings.json

{
  "context_servers": {
    "woodshed-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/gaearon/woodshed",
          "~/.claude/skills/woodshed"
        ]
      }
    }
  }
}

In context_servers hinzufügen. Zed lädt beim Speichern neu.

claude mcp add woodshed-skill -- git clone https://github.com/gaearon/woodshed ~/.claude/skills/woodshed

Einzeiler. Prüfen mit claude mcp list. Entfernen mit claude mcp remove.

Anwendungsfälle

Praxisnahe Nutzung: woodshed

Author a new skill and iterate it to 'actually works'

👤 Skill authors who've noticed their first drafts don't survive real use ⏱ ~120 min advanced

Wann einsetzen: You have an idea for a skill but every time you write one, it degrades after 3 uses.

Voraussetzungen

Skill installed — git clone https://github.com/gaearon/woodshed ~/.claude/skills/woodshed

Ablauf

Scaffold

Use woodshed. Create a new skill called 'changelog-writer' that turns git logs into user-facing changelogs.✓ Kopiert

→ skills/changelog-writer/ created with SKILL.md
Create test cases

Generate 5 diverse test inputs.✓ Kopiert

→ tests/ folder with 5 sample git log fixtures
Run and rate

Run the skill on each. Show me the output; I'll rate.✓ Kopiert

→ Outputs presented with rating slots
Iterate based on ratings

Based on my ratings, suggest prompt changes to SKILL.md. Don't apply yet.✓ Kopiert

→ Proposed diff with rationale per change

Ergebnis: A skill that works on your real use cases, not just the demo.

Fallstricke

Overfitting to test cases — Hold out some tests; re-run after every iteration to catch regressions

Kombinieren mit: filesystem

Improve a skill that's been disappointing you

👤 Anyone with a skill installed they're unhappy with ⏱ ~60 min intermediate

Wann einsetzen: You have a skill that half-works and you can't tell why.

Ablauf

Characterize the failures

Use woodshed. Here's a skill I installed. Here are 3 sessions where it underperformed. Diagnose.✓ Kopiert

→ Pattern in failures — instruction gap, example gap, framing issue
Propose fixes

Propose minimal SKILL.md edits to address those patterns.✓ Kopiert

→ Specific diffs

Ergebnis: A skill you can trust.

Kombinationen

Mit anderen MCPs für 10-fache Wirkung

woodshed-skill + skill-fetch-skill

Find skills with skill-fetch, improve them with woodshed

Find a changelog-writer skill; install; run woodshed on it to tune for my repo.✓ Kopiert

woodshed-skill + filesystem

Persist iteration history across sessions

Keep woodshed logs in skills/<name>/.woodshed/ for traceability.✓ Kopiert

Werkzeuge

Was dieses MCP bereitstellt

Werkzeug	Eingaben	Wann aufrufen
scaffold_skill	skill name, goal	New skill
run_tests	skill + test set	Evaluating
capture_rating	rating + notes	After each test
iterate_prompt	skill + ratings	After a rating round

Kosten & Limits

Was der Betrieb kostet

API-Kontingent: None
Tokens pro Aufruf: High during iteration (many test runs)
Kosten in €: Free (Claude API usage applies)
Tipp: Keep test sets small — 5 tests beats 50 that never get reviewed.

Sicherheit

Rechte, Secrets, Reichweite

Credential-Speicherung: None

Datenabfluss: None from skill

Fehlerbehebung

Häufige Fehler und Lösungen

Iteration keeps changing but doesn't improve

Your test set is too narrow; add diverse cases

Skill works in woodshed but not in real use

Production prompts differ from test fixtures; add real-session logs to the test set

Alternativen

woodshed vs. andere

Alternative	Wann stattdessen	Kompromiss
Hand-tuning SKILL.md without loop	Simple skills with obvious prompts	Slower convergence; easier to miss regressions
claude-skills-vault-skill	You want ready-made skills, not authoring tools	Different goal

Mehr

Ressourcen

📖 Offizielle README auf GitHub lesen

🐙 Offene Issues ansehen

🔍 Alle 400+ MCP-Server und Skills durchsuchen