woodshed MCP — Cas d'usage, Installer & Démo en direct

Pourquoi l'utiliser

Fonctionnalités clés

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

Démo en direct

Aperçu en pratique

woodshed-skill.replay ▶ prêt

0/0

Installer

Choisissez votre 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
    }
  }
}

Ouvrez Claude Desktop → Settings → Developer → Edit Config. Redémarrez après avoir enregistré.

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor utilise le même schéma mcpServers que Claude Desktop. La config projet l'emporte sur la globale.

VS Code → Cline → MCP Servers → Edit

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

Cliquez sur l'icône MCP Servers dans la barre latérale Cline, puis "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

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

Même format que Claude Desktop. Redémarrez Windsurf pour appliquer.

~/.continue/config.json

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

Continue utilise un tableau d'objets serveur plutôt qu'une map.

~/.config/zed/settings.json

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

Ajoutez dans context_servers. Zed recharge à chaud à la sauvegarde.

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

Une seule ligne. Vérifiez avec claude mcp list. Supprimez avec claude mcp remove.

Cas d'usage

Usages concrets : 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

Quand l'utiliser : You have an idea for a skill but every time you write one, it degrades after 3 uses.

Prérequis

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

Déroulement

Scaffold

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

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

Generate 5 diverse test inputs.✓ Copié

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

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

→ Outputs presented with rating slots
Iterate based on ratings

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

→ Proposed diff with rationale per change

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

Pièges

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

Combiner avec : filesystem

Improve a skill that's been disappointing you

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

Quand l'utiliser : You have a skill that half-works and you can't tell why.

Déroulement

Characterize the failures

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

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

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

→ Specific diffs

Résultat : A skill you can trust.

Combinaisons

Associez-le à d'autres MCPs pour un effet X10

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.✓ Copié

woodshed-skill + filesystem

Persist iteration history across sessions

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

Outils

Ce que ce MCP expose

Outil	Entrées	Quand appeler
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

Coût et limites

Coût d'exécution

Quota d'API: None
Tokens par appel: High during iteration (many test runs)
Monétaire: Free (Claude API usage applies)
Astuce: Keep test sets small — 5 tests beats 50 that never get reviewed.

Sécurité

Permissions, secrets, portée

Stockage des identifiants : None

Sortie de données : None from skill

Dépannage

Erreurs courantes et correctifs

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

Alternatives

woodshed vs autres

Alternative	Quand l'utiliser	Compromis
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

Plus

Ressources

📖 Lire le README officiel sur GitHub

🐙 Voir les issues ouvertes

🔍 Parcourir les 400+ serveurs MCP et Skills