跳到正文
FunCoding

搜索

搜索文档、Skill 和 MCP

curate-a-team-library

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.

AI 与智能体1.1kskills/curate-a-team-library/SKILL.md

安装

把这段话发给 Claude Code、Codex 或 Cursor。智能体会先检查安全性,你确认后才安装。

读取 https://funcoding.ai/skills/moizibnyousaf/ai-agent-skills/curate-a-team-library/install.md ,按里面的步骤帮我安装这个 Skill。

SKILL.md

Curate A Team Library

Goal

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.

First Move

Start with a managed workspace.

npx ai-agent-skills init-library <name>
cd <name>

Ask at most 3 short questions before acting:

  • what kinds of work the library needs to support
  • whether the first pass should stay small and opinionated or aim broader
  • whether the output should stay local or end as a shareable GitHub repo

Shelf System

Use these 5 work areas as the shelf system:

  • frontend: web UI, browser work, design systems, visual polish
  • backend: APIs, data, security, infrastructure, runtime systems
  • mobile: iOS, Android, React Native, Expo, device testing, app delivery
  • workflow: docs, testing, release work, files, research, planning
  • agent-engineering: prompts, evals, tools, orchestration, agent runtime design

Map the user's stack to shelves before adding anything.

  • Example: React Native + Node backend maps to mobile + backend.
  • Add workflow only when testing, release, docs, or research are real parts of the job.
  • Add agent-engineering only when the team is doing AI features, prompts, evals, or tooling.
  • Make sure the first pass covers every primary shelf the user explicitly named.

Discovery Loop

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.

Mutation Rules

Keep the first pass small: around 3 to 8 skills.

  • Use add first for bundled picks and simple GitHub imports.
  • Use catalog when you want an upstream entry without copying files into skills/.
  • Use 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 / UI
  • React Native / QA
  • Node / APIs
  • Node / Data
  • Docs / Release

Bad branch names:

  • stuff
  • misc
  • notes

Writing Good whyHere

whyHere is curator judgment, not filler.

  • Mention the stack or workflow it supports.
  • Mention the gap it fills in this library.
  • Be honest about why it belongs here.

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.

  • keep it to about 2 to 3 featured skills per shelf
  • reserve it for skills you would tell a new teammate to install first

Collections

After the library has about 5 to 8 solid picks, create a starter-pack collection.

  • Use --collection starter-pack while adding new skills.
  • Or use npx ai-agent-skills curate <skill> --collection starter-pack for existing entries.
  • Keep the collection small and onboarding-friendly.

Sanity Check

Before finishing:

npx ai-agent-skills list --area <work-area>
npx ai-agent-skills collections
npx ai-agent-skills build-docs
  • Run list --area for each primary shelf you touched.
  • If you created starter-pack, confirm the install command looks right.
  • Make sure the final shelf mix still matches the user's actual stack.

Finish

Return:

  • what you added
  • which shelves you used and why
  • which skills are featured
  • what starter-pack contains, if you created one
  • whether the library is local-only or ready to share

相似的 Skill

brand-guidelines
anthropics/skills180k

brand-guidelines

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

AI 与智能体

internal-comms
anthropics/skills180k

internal-comms

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).

AI 与智能体

template-skill
anthropics/skills180k

template-skill

Replace with description of the skill and when Claude should use it.

AI 与智能体

mcp-builder
anthropics/skills180k

mcp-builder

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

AI 与智能体

algorithmic-art
anthropics/skills180k

algorithmic-art

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

AI 与智能体

academy-guide
anthropics/skills180k

academy-guide

Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.

AI 与智能体