Clarify requirements before implementing. Do not use automatically, only when invoked explicitly.
中文简介正在准备中。当前显示原文说明。
Use when building a managed team skills library for a real stack. Map work to shelves, browse before curating, write meaningful `whyHere` notes, and create a starter pack once the first pass is solid.
中文简介正在准备中。当前显示原文说明。
实测评分 未实测
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Build a managed skills library that another teammate or agent can actually browse, trust, and install.
Do not hand-edit skills.json, README.md, or WORK_AREAS.md when the CLI already has the mutation you need.
Start with a managed workspace.
npx ai-agent-skills init-library <name>
cd <name>
Ask at most 3 short questions before acting:
Use these 5 work areas as the shelf system:
frontend: web UI, browser work, design systems, visual polishbackend: APIs, data, security, infrastructure, runtime systemsmobile: iOS, Android, React Native, Expo, device testing, app deliveryworkflow: docs, testing, release work, files, research, planningagent-engineering: prompts, evals, tools, orchestration, agent runtime designMap the user's stack to shelves before adding anything.
React Native + Node backend maps to mobile + backend.workflow only when testing, release, docs, or research are real parts of the job.agent-engineering only when the team is doing AI features, prompts, evals, or tooling.Browse before curating.
npx ai-agent-skills list --area <work-area>
npx ai-agent-skills search <query>
npx ai-agent-skills collections
If the user named multiple primary shelves, inspect each one before choosing skills.
Keep the first pass small: around 3 to 8 skills.
add first for bundled picks and simple GitHub imports.catalog when you want an upstream entry without copying files into skills/.vendor only for true house copies the team wants to edit or own locally.Every mutation must include explicit curator metadata like --area, --branch, and --why.
Good branch names:
React Native / UIReact Native / QANode / APIsNode / DataDocs / ReleaseBad branch names:
stuffmiscnoteswhyHerewhyHere is curator judgment, not filler.
Good:
Covers React Native testing so the mobile shelf has a real device-validation option.
Bad:
I want this on my shelf.
Use --featured sparingly.
After the library has about 5 to 8 solid picks, create a starter-pack collection.
--collection starter-pack while adding new skills.npx ai-agent-skills curate <skill> --collection starter-pack for existing entries.Before finishing:
npx ai-agent-skills list --area <work-area>
npx ai-agent-skills collections
npx ai-agent-skills build-docs
list --area for each primary shelf you touched.starter-pack, confirm the install command looks right.Return:
starter-pack contains, if you created one还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Clarify requirements before implementing. Do not use automatically, only when invoked explicitly.
中文简介正在准备中。当前显示原文说明。
Use when checking the overall health of a skills library. Run doctor, validate, check for stale skills, and verify generated docs are in sync.
中文简介正在准备中。当前显示原文说明。
Backend API design, database architecture, microservices patterns, and test-driven development. Use for designing APIs, database schemas, or backend system architecture.
中文简介正在准备中。当前显示原文说明。
Transforms vague prompts into optimized Claude Code prompts. Adds verification, specific context, constraints, and proper phasing. Invoke with /best-practices.
中文简介正在准备中。当前显示原文说明。
Use when exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing. Always use --fields to limit output size and --dry-run before committing to an install.
中文简介正在准备中。当前显示原文说明。
Use when regenerating README.md and WORK_AREAS.md in a managed library workspace. Always dry-run first to preview changes.
中文简介正在准备中。当前显示原文说明。