/ Diretório / Playground / woodshed
● Comunidade gaearon ⚡ Instantâneo

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 que usar

Principais recursos

Demo ao vivo

Como fica na prática

woodshed-skill.replay ▶ pronto
0/0

Instalar

Escolha seu 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
    }
  }
}

Abra Claude Desktop → Settings → Developer → Edit Config. Reinicie após salvar.

~/.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 o mesmo esquema mcpServers que o Claude Desktop. Config de projeto vence a global.

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

Clique no ícone MCP Servers na barra lateral do Cline, depois "Edit Configuration".

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

Mesmo formato do Claude Desktop. Reinicie o Windsurf para aplicar.

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

O Continue usa um array de objetos de servidor em vez de um map.

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

Adicione em context_servers. Zed recarrega automaticamente ao salvar.

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

Uma linha só. Verifique com claude mcp list. Remova com claude mcp remove.

Casos de uso

Usos do 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

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

Pré-requisitos
  • Skill installed — git clone https://github.com/gaearon/woodshed ~/.claude/skills/woodshed
Fluxo
  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.

Armadilhas
  • Overfitting to test cases — Hold out some tests; re-run after every iteration to catch regressions
Combine com: filesystem

Improve a skill that's been disappointing you

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

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

Fluxo
  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.

Combinações

Combine com outros MCPs para 10× de alavancagem

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

Ferramentas

O que este MCP expõe

FerramentaEntradasQuando chamarCusto
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

Custo e limites

O que custa rodar

Cota de API
None
Tokens por chamada
High during iteration (many test runs)
Monetário
Free (Claude API usage applies)
Dica
Keep test sets small — 5 tests beats 50 that never get reviewed.

Segurança

Permissões, segredos, alcance

Armazenamento de credenciais: None
Saída de dados: None from skill

Solução de problemas

Erros comuns e correções

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. outros

AlternativaQuando usarTroca
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

Mais

Recursos

📖 Leia o README oficial no GitHub

🐙 Ver issues abertas

🔍 Ver todos os 400+ servidores MCP e Skills