Tooluck logoTooluck
SKILL.md

curate-a-team-library

Agent skill fromMoizIbnYousaf/ai-agent-skills

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.

How to install curate-a-team-library

install curate-a-team-library
# install the ai-agent-skills pack with the skills CLI
npx skills add MoizIbnYousaf/ai-agent-skills

# or add only this skill to Claude Code: copy the folder

skills/curate-a-team-library/

# into

~/.claude/skills/curate-a-team-library/ (all projects)

.claude/skills/curate-a-team-library/ (one project)

skills/curate-a-team-library/SKILL.md

MITFull file
1# Curate A Team Library
2
3## Goal
4
5Build a managed skills library that another teammate or agent can actually browse, trust, and install.
6
7Do not hand-edit `skills.json`, `README.md`, or `WORK_AREAS.md` when the CLI already has the mutation you need.
8
9## First Move
10
11Start with a managed workspace.
12
13```bash
14npx ai-agent-skills init-library <name>
15cd <name>
16```
17
18Ask at most 3 short questions before acting:
19
20- what kinds of work the library needs to support
21- whether the first pass should stay small and opinionated or aim broader
22- whether the output should stay local or end as a shareable GitHub repo
23
24## Shelf System
25
26Use these 5 work areas as the shelf system:
27
28- `frontend`: web UI, browser work, design systems, visual polish
29- `backend`: APIs, data, security, infrastructure, runtime systems
30- `mobile`: iOS, Android, React Native, Expo, device testing, app delivery
31- `workflow`: docs, testing, release work, files, research, planning
32- `agent-engineering`: prompts, evals, tools, orchestration, agent runtime design
33
34Map the user's stack to shelves before adding anything.
35
36- Example: `React Native + Node backend` maps to `mobile` + `backend`.
37- Add `workflow` only when testing, release, docs, or research are real parts of the job.
38- Add `agent-engineering` only when the team is doing AI features, prompts, evals, or tooling.
39- Make sure the first pass covers every primary shelf the user explicitly named.
40
41## Discovery Loop
42
43Browse before curating.
44
45```bash
46…

Excerpt shown under the repository's MIT license.

More skills in ai-agent-skills

Keep exploring

Similar skill repositories

thedotmack /

claude-mem
116k

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

CCCXGHGM+135 skills

Newsletter

Join the Community

Subscribe to our newsletter for the latest news and updates