/ Directorio / Playground / woodshed
● Comunidad gaearon ⚡ Instantáneo

woodshed

por gaearon · gaearon/woodshed

Create, run, rate, and iterate your Claude Skills — Dan Abramov's skill-workshop skill, a meta-loop for getting skills actually good.

A meta-skill for authoring other skills. Scaffolds a new skill, runs it on test cases, asks you to rate the output, and uses the feedback to iterate on the skill's prompts. Based on Dan Abramov's 'woodshedding' methodology — deliberate practice applied to skill authoring.

Por qué usarlo

Características clave

Demo en vivo

Cómo se ve en la práctica

woodshed-skill.replay ▶ listo
0/0

Instalar

Elige tu cliente

~/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
    }
  }
}

Abre Claude Desktop → Settings → Developer → Edit Config. Reinicia después de guardar.

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

Cursor usa el mismo esquema mcpServers que Claude Desktop. La configuración del proyecto prevalece sobre la global.

VS Code → Cline → MCP Servers → Edit
{
  "mcpServers": {
    "woodshed-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/gaearon/woodshed",
        "~/.claude/skills/woodshed"
      ],
      "_inferred": true
    }
  }
}

Haz clic en el icono MCP Servers de la barra lateral de Cline y luego en "Edit Configuration".

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

Mismo formato que Claude Desktop. Reinicia Windsurf para aplicar.

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

Continue usa un array de objetos de servidor en lugar de un mapa.

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

Añádelo a context_servers. Zed recarga en caliente al guardar.

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

Un solo comando. Verifica con claude mcp list. Quita con claude mcp remove.

Casos de uso

Usos del mundo real: 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

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

Requisitos previos
  • Skill installed — git clone https://github.com/gaearon/woodshed ~/.claude/skills/woodshed
Flujo
  1. Scaffold
    Use woodshed. Create a new skill called 'changelog-writer' that turns git logs into user-facing changelogs.✓ Copiado
    → skills/changelog-writer/ created with SKILL.md
  2. Create test cases
    Generate 5 diverse test inputs.✓ Copiado
    → tests/ folder with 5 sample git log fixtures
  3. Run and rate
    Run the skill on each. Show me the output; I'll rate.✓ Copiado
    → Outputs presented with rating slots
  4. Iterate based on ratings
    Based on my ratings, suggest prompt changes to SKILL.md. Don't apply yet.✓ Copiado
    → Proposed diff with rationale per change

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

Errores comunes
  • Overfitting to test cases — Hold out some tests; re-run after every iteration to catch regressions
Combinar con: filesystem

Improve a skill that's been disappointing you

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

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

Flujo
  1. Characterize the failures
    Use woodshed. Here's a skill I installed. Here are 3 sessions where it underperformed. Diagnose.✓ Copiado
    → Pattern in failures — instruction gap, example gap, framing issue
  2. Propose fixes
    Propose minimal SKILL.md edits to address those patterns.✓ Copiado
    → Specific diffs

Resultado: A skill you can trust.

Combinaciones

Combínalo con otros MCPs para multiplicar por 10

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.✓ Copiado
woodshed-skill + filesystem

Persist iteration history across sessions

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

Herramientas

Lo que expone este MCP

HerramientaEntradasCuándo llamarCoste
scaffold_skill skill name, goal New skill 0
run_tests skill + test set Evaluating 0
capture_rating rating + notes After each test 0
iterate_prompt skill + ratings After a rating round 0

Coste y límites

Lo que cuesta ejecutarlo

Cuota de API
None
Tokens por llamada
High during iteration (many test runs)
Monetario
Free (Claude API usage applies)
Consejo
Keep test sets small — 5 tests beats 50 that never get reviewed.

Seguridad

Permisos, secretos, alcance

Almacenamiento de credenciales: None
Salida de datos: None from skill

Resolución de problemas

Errores comunes y soluciones

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

Alternativas

woodshed vs otros

AlternativaCuándo usarlaContrapartida
Hand-tuning SKILL.md without loopSimple skills with obvious promptsSlower convergence; easier to miss regressions
claude-skills-vault-skillYou want ready-made skills, not authoring toolsDifferent goal

Más

Recursos

📖 Lee el README oficial en GitHub

🐙 Ver issues abiertas

🔍 Ver todos los 400+ servidores MCP y Skills