woodshed (Claude Skill) — 설치 & 라이브 데모

왜 쓰나요

핵심 기능

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

라이브 데모

실제 사용 모습

woodshed-skill.replay ▶ 준비됨

0/0

설치

작성자 저장소 · Claude Skills 공식 문서

사용 사례

실전 활용법: 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

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

흐름

Scaffold

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

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

Generate 5 diverse test inputs.✓ 복사됨

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

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

→ Outputs presented with rating slots
Iterate based on ratings

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

→ Proposed diff with rationale per change

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

함정

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

함께 쓰기: filesystem

Improve a skill that's been disappointing you

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

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

흐름

Characterize the failures

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

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

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

→ Specific diffs

결과: A skill you can trust.

조합

다른 MCP와 조합해 10배 효율

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.✓ 복사됨

woodshed-skill + filesystem

Persist iteration history across sessions

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

도구

이 MCP가 노출하는 것

도구	입력	언제 호출
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

비용 및 제한

운영 비용

API 쿼터: None
호출당 토큰: High during iteration (many test runs)
금액: Free (Claude API usage applies)
팁: Keep test sets small — 5 tests beats 50 that never get reviewed.

보안

권한, 시크릿, 파급범위

자격 증명 저장: None

데이터 외부 송신: None from skill

문제 해결

자주 발생하는 오류와 해결

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

대안

woodshed 다른 것과 비교

대안	언제 쓰나	단점/장점
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

woodshed