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 — 安装 & 实时演示

为什么要用

核心特性

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

实时演示

实际使用效果

skills-skill-8.replay ▶ 就绪

0/0

安装

作者仓库 · Claude Skills 官方文档

使用场景

实战用法： 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

何时使用： You have a draft SKILL.md and want it audited before sharing.

步骤

Scaffold with init-project

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

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

Run better-prompt on my SKILL.md body.✓ 已复制

→ Clearer, more executable wording
Stress-test

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

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

write-skill-readme for this skill.✓ 已复制

→ README following convention

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

注意事项

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

搭配使用： skillcheck-free-skill

Compare two implementation approaches with parallel-vibe

👤 Engineers stuck between two architectures ⏱ ~90 min advanced

何时使用： You can't decide between approach A and approach B and want to try both.

步骤

Describe both approaches

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

→ Two independent workspaces with separate code and test results
Compare

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

→ Honest tradeoff analysis grounded in both codebases

结果： A data-backed decision between two architectures.

组合

与其他 MCP 搭配，撬动十倍杠杆

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.✓ 已复制

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.✓ 已复制

工具

此 MCP 暴露的能力

工具	输入参数	何时调用	成本
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

成本与限制

运行它的成本

API 配额: None
每次调用 Token 数: parallel-vibe can be expensive — runs multiple solution attempts
费用: Free — skills are local files
提示: Use parallel-vibe sparingly; it multiplies your token spend by N branches.

安全

权限、密钥、影响范围

凭据存储： No credentials — pure prompts. git-* skills use your local git config.

数据出站： None from skills themselves; git-* may push to remotes you configure.

故障排查

常见错误与修复

Wrong trigger keywords — git-commit doesn't activate

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

替代方案

skills 对比其他方案

替代方案	何时用它替代	权衡
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