/ Каталог / Песочница / woodshed
● Сообщество gaearon ⚡ Сразу

woodshed

автор 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.

Зачем использовать

Ключевые функции

Живое демо

Как выглядит на практике

woodshed-skill.replay ▶ готово
0/0

Установка

Репозиторий автора · Официальная документация Claude Skills

Сценарии использования

Реальные сценарии: 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

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

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

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

Подводные камни
  • Overfitting to test cases — Hold out some tests; re-run after every iteration to catch regressions
Сочетать с: filesystem

Improve a skill that's been disappointing you

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

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

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

Итог: A skill you can trust.

Комбинации

Сочетайте с другими MCP — эффект 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.✓ Скопировано
woodshed-skill + filesystem

Persist iteration history across sessions

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

Инструменты

Что предоставляет этот MCP

ИнструментВходные данныеКогда вызыватьСтоимость
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

Стоимость и лимиты

Во что обходится

Квота API
None
Токенов на вызов
High during iteration (many test runs)
Деньги
Free (Claude API usage applies)
Совет
Keep test sets small — 5 tests beats 50 that never get reviewed.

Безопасность

Права, секреты, радиус поражения

Хранение учётных данных: None
Исходящий трафик: None from skill

Устранение неполадок

Частые ошибки и исправления

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

Альтернативы

woodshed в сравнении

АльтернативаКогда использоватьКомпромисс
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

Ещё

Ресурсы

📖 Читать официальный README на GitHub

🐙 Открытые задачи

🔍 Все 400+ MCP-серверов и Skills