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 — Installer & Démo en direct

Pourquoi l'utiliser

Fonctionnalités clés

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

Démo en direct

Aperçu en pratique

skills-skill-8.replay ▶ prêt

0/0

Installation

Dépôt de l’auteur · Documentation officielle des Skills Claude

Cas d'usage

Usages concrets : 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

Quand l'utiliser : You have a draft SKILL.md and want it audited before sharing.

Déroulement

Scaffold with init-project

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

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

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

→ Clearer, more executable wording
Stress-test

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

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

write-skill-readme for this skill.✓ Copié

→ README following convention

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

Pièges

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

Combiner avec : skillcheck-free-skill

Compare two implementation approaches with parallel-vibe

👤 Engineers stuck between two architectures ⏱ ~90 min advanced

Quand l'utiliser : You can't decide between approach A and approach B and want to try both.

Déroulement

Describe both approaches

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

→ Two independent workspaces with separate code and test results
Compare

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

→ Honest tradeoff analysis grounded in both codebases

Résultat : A data-backed decision between two architectures.

Combinaisons

Associez-le à d'autres MCPs pour un effet X10

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.✓ Copié

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.✓ Copié

Outils

Ce que ce MCP expose

Outil	Entrées	Quand appeler	Coût
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

Coût et limites

Coût d'exécution

Quota d'API: None
Tokens par appel: parallel-vibe can be expensive — runs multiple solution attempts
Monétaire: Free — skills are local files
Astuce: Use parallel-vibe sparingly; it multiplies your token spend by N branches.

Sécurité

Permissions, secrets, portée

Stockage des identifiants : No credentials — pure prompts. git-* skills use your local git config.

Sortie de données : None from skills themselves; git-* may push to remotes you configure.

Dépannage

Erreurs courantes et correctifs

Wrong trigger keywords — git-commit doesn't activate

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

Alternatives

skills vs autres

Alternative	Quand l'utiliser	Compromis
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

Plus

Ressources

📖 Lire le README officiel sur GitHub

🐙 Voir les issues ouvertes

🔍 Parcourir les 400+ serveurs MCP et Skills