Skill not invoked — Claude uses its own defaults instead of init-project

Name the specific skill ('use init-project to scaffold...').

SKILL.md frontmatter wrong in a sub-skill

Each sub-skill has its own SKILL.md — inspect the specific folder.

skills — 설치 & 라이브 데모

왜 쓰나요

핵심 기능

init-project scaffolds the directive files every serious AI project needs
auto-test-skill and auto-test-project run critical robustness tests on skill design
parallel-vibe runs alternative solutions in independent workspaces to compare
git-* skills automate conventional commits, PR review, and release notes
Targets Claude Code, Codex, and Cursor via the open Agent Skills standard

라이브 데모

실제 사용 모습

skills-skill-8.replay ▶ 준비됨

0/0

설치

작성자 저장소 · Claude Skills 공식 문서

사용 사례

실전 활용법: skills

Author a new Claude skill and test it before publishing

👤 Developers who've built one-shot skills and want them actually reliable ⏱ ~60 min intermediate

언제 쓸까: You have a draft SKILL.md and want it audited before sharing.

흐름

Scaffold with init-project

Use init-project to scaffold AGENTS.md and CLAUDE.md for my new skill project.✓ 복사됨

→ Directive files appear with sensible defaults
Polish the prompt with better-prompt

Run better-prompt on my SKILL.md body.✓ 복사됨

→ Clearer, more executable wording
Stress-test

Now auto-test-skill my SKILL.md — find weaknesses.✓ 복사됨

→ Failure modes named (vague triggers, missing examples, ambiguous steps)
Write the README

write-skill-readme for this skill.✓ 복사됨

→ README following convention

결과: A skill that passes its own tests before anyone else sees it.

함정

auto-test-skill flags everything and you fix nothing — Prioritize Critical + Warning; Suggestion-level is aspirational

함께 쓰기: skillcheck-free-skill

Compare two implementation approaches with parallel-vibe

👤 Engineers stuck between two architectures ⏱ ~90 min advanced

언제 쓸까: You can't decide between approach A and approach B and want to try both.

흐름

Describe both approaches

parallel-vibe: implement approach A (server-sent events) and approach B (polling) in separate workspaces. Same test suite.✓ 복사됨

→ Two independent workspaces with separate code and test results
Compare

Now compare — which is simpler to maintain and which is faster under load?✓ 복사됨

→ Honest tradeoff analysis grounded in both codebases

결과: A data-backed decision between two architectures.

조합

다른 MCP와 조합해 10배 효율

skills-skill-8 + skillcheck-free-skill

Cross-validate: auto-test-skill finds design weaknesses, SkillCheck validates spec compliance

Run auto-test-skill, then SkillCheck, then fix whatever either flags.✓ 복사됨

skills-skill-8 + github

git-pr-review + git-publish-release against real PRs and releases

Use git-pr-review on PR #47 then draft the release notes via git-publish-release.✓ 복사됨

도구

이 MCP가 노출하는 것

도구	입력	언제 호출	비용
init-project	project intent	First commit in a new project	0
better-prompt	draft prompt/instructions	Before shipping any prompt-heavy artifact	0
auto-test-skill	SKILL.md path	Before publishing a skill	0
parallel-vibe	N approaches + test criteria	When you genuinely can't pick an approach on paper	0 + LLM tokens for each branch
git-commit	diff intent	End of a unit of work	0
git-pr-review	PR number or diff	Reviewing a PR you're assigned	0

비용 및 제한

운영 비용

API 쿼터: None
호출당 토큰: parallel-vibe can be expensive — runs multiple solution attempts
금액: Free — skills are local files
팁: Use parallel-vibe sparingly; it multiplies your token spend by N branches.

보안

권한, 시크릿, 파급범위

자격 증명 저장: No credentials — pure prompts. git-* skills use your local git config.

데이터 외부 송신: None from skills themselves; git-* may push to remotes you configure.

문제 해결

자주 발생하는 오류와 해결

Wrong trigger keywords — git-commit doesn't activate

Say 'use git-commit' explicitly; 'commit' alone is too generic.

대안

skills 다른 것과 비교

대안	언제 쓰나	단점/장점
skillcheck-free-skill	You want spec validation rather than robustness testing	Narrower scope, higher specificity to the agentskills spec
skills-skill-9 (tenequm)	You want broader product-building skills, not just skill authoring	Less meta — more domain skills

skills