/ Annuaire / Playground / woodshed
● Communauté gaearon ⚡ Instantané

woodshed

par 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.

Pourquoi l'utiliser

Fonctionnalités clés

Démo en direct

Aperçu en pratique

woodshed-skill.replay ▶ prêt
0/0

Installation

Dépôt de l’auteur · Documentation officielle des Skills Claude

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.

Déroulement
  1. 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
  2. Create test cases
    Generate 5 diverse test inputs.✓ Copié
    → tests/ folder with 5 sample git log fixtures
  3. Run and rate
    Run the skill on each. Show me the output; I'll rate.✓ Copié
    → Outputs presented with rating slots
  4. 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
  1. 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
  2. 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

OutilEntréesQuand appelerCoût
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

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

AlternativeQuand l'utiliserCompromis
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

Plus

Ressources

📖 Lire le README officiel sur GitHub

🐙 Voir les issues ouvertes

🔍 Parcourir les 400+ serveurs MCP et Skills