Ai-Agent-Skills
my curated agent skills library
AI Agent Skills
My curated library of agent skills, plus the package to build your own.
The skills I actually keep around, organized the way I work.
8 house copies · 47 cataloged upstream
Picked, shelved, and maintained by hand.
Build your own library · For your agent
Library
ai-agent-skills does two things.
It ships my curated library, and it gives you the CLI and TUI to build and manage your own.
It works with any Agent Skills-compatible agent.
The bundled library is organized the way I work:
- Start with a shelf like
frontendorworkflow - Keep the set small enough to browse quickly
- Keep provenance visible
- Keep notes that explain why a skill is here
Use skills.sh for the broad ecosystem.
Use ai-agent-skills when you want a smaller library with shelves, provenance, and notes.
What's New in 4.0.0
- Managed library workspaces with
init-library add <source>for bringing bundled picks, upstream repo skills, or house copies into your own librarysync [name]as the main refresh command;updatestays as an alias- Dependency-aware installs with
requiresand--no-deps - Installed status in both the CLI and TUI
What It Is Now
I launched this on December 17, 2025, before skills.sh existed and before the ecosystem had a clear default universal installer.
Originally this repo was that installer. It still does that.
What started as an installer is now a place to build and manage your own library of skills.
How It Works
Each skill here is either a house copy or a cataloged upstream pick.
House copies
Local folders underskills/<name>/.
These install fast, work offline, and ship with the npm package.Cataloged upstream
Metadata inskills.jsonwith no local folder.
These stay upstream and install from the source repo when you ask for them.
Upstream work stays upstream. That keeps the library lean.
Use It With Your Agent
Any Agent Skills-compatible agent with shell access can run this CLI for you.
The CLI already supports that. Prompts help, but they are optional. When the agent passes explicit metadata like --area, --branch, and --why, it can set up and curate a library without editing files by hand.
The block below includes the repo links so the agent can fetch its own context.
Full handoff: FOR_YOUR_AGENT.md
Paste this into your agent
Build me a small skills library with `ai-agent-skills`.
Use this repo for reference if you need docs or examples:
https://github.com/MoizIbnYousaf/Ai-Agent-Skills
https://github.com/MoizIbnYousaf/Ai-Agent-Skills/blob/main/FOR_YOUR_AGENT.md
Use the CLI with `npx`. Do not ask me to open the repo or link you to anything else.
Do not hand-edit files if the command already exists.
1. Create a new folder called `my-skills-library` with `npx ai-agent-skills init-library my-skills-library`, unless I clearly ask for a different name.
2. Move into that workspace and keep working there.
3. Ask me only the minimum questions you need before acting:
- if you have a built-in question tool, use it
- which shelves or kinds of work matter most
- whether to start mostly from bundled picks or mix in upstream skills
- whether installs should default to project scope, global scope, or library setup only
4. Add a small starter set, around 3 to 8 skills.
5. Start with `add`. Use `catalog` when you need an upstream entry. Use `vendor` only for a real house copy.
6. Run `npx ai-agent-skills build-docs` at the end.
7. Tell me what you added, which shelves you used, and what you'd add next.
If you cannot run local commands here, tell me to use another Agent Skills-compatible agent with terminal access.
Quick Start
Use the bundled library
# Open the terminal browser
npx ai-agent-skills
# List the shelves
npx ai-agent-skills list
# Install a skill from the library
npx ai-agent-skills install frontend-design
# Install the Swift hub to the default global targets
npx ai-agent-skills swift
# Install an entire curated pack
npx ai-agent-skills install --collection swift-agent-skills -p
# Install to the project shelf
npx ai-agent-skills install pdf -p
# Install all skills from an upstream repo to the default global targets
npx ai-agent-skills anthropics/skills
# Browse a repo before adding or installing from it
npx ai-agent-skills install openai/skills --list
Default install targets:
- Global:
~/.claude/skills/ - Project:
.agents/skills/
Legacy agent-specific targets still work through --agent <name>.
Start your own library
# Create a managed workspace
npx ai-agent-skills init-library my-library
cd my-library
# Add a bundled pick, install it, refresh it, and rebuild the docs
npx ai-agent-skills add frontend-design --area frontend --branch Implementation --why "I want this on my shelf."
npx ai-agent-skills install frontend-design -p
npx ai-agent-skills sync frontend-design -p
npx ai-agent-skills add anthropics/skills --skill webapp-testing --area workflow --branch Testing --why "I use this when I want browser-level checks in the workspace."
npx ai-agent-skills build-docs
Workspace Mode
Workspace mode is part of the normal flow now.
Start with a managed workspace, add a few skills, then keep your shelves current with add, catalog, vendor, sync, and build-docs.
npx ai-agent-skills init-library my-library
cd my-library
npx ai-agent-skills add frontend-design --area frontend --branch Implementation --why "I want this on my shelf."
npx ai-agent-skills install frontend-design -p
npx ai-agent-skills add anthropics/skills --skill webapp-testing --area workflow --branch Testing --why "I use this when I want browser-level checks in the workspace."
npx ai-agent-skills sync frontend-design -p
npx ai-agent-skills build-docs
Workflow guides:
Browse
Most browsing starts in one of two places:
| View | Why it exists | Start here |
|---|---|---|
| Shelves | The main way to understand the library: start with the kind of work, then drill into the small set of picks on that shelf. | npx ai-agent-skills list |
| Sources | The provenance view: see which publishers feed which shelves and branches. | npx ai-agent-skills info frontend-design |
The other views are still useful, just more situational:
npx ai-agent-skills browsefor the TUInpx ai-agent-skills list --collection my-picksfor a cross-shelf starter stacknpx ai-agent-skills install --collection swift-agent-skills -pfor an installable curated packnpx ai-agent-skills curate reviewfor the curator cleanup queue
Shelves
The shelves are the main structure.
| Shelf | Skills | What it covers |
|---|---|---|
| Frontend | 10 | Interfaces, design systems, browser work, and product polish. |
| Backend | 5 | Systems, data, security, and runtime operations. |
| Mobile | 24 | Swift, SwiftUI, iOS, and Apple-platform development, with room for future React Native branches. |
| Workflow | 10 | Files, docs, planning, release work, and research-to-output flows. |
| Agent Engineering | 6 | MCP, skill-building, prompting discipline, and LLM application work. |
The full map lives in WORK_AREAS.md.
Collections
Collections are smaller sets. Useful, but secondary to the shelves.
| Collection | Why it exists | Start here |
|---|---|---|
my-picks |
A short starter stack. These are the skills I reach for first. | frontend-design, mcp-builder, pdf |
build-apps |
Frontend, UI, and design work for shipping polished apps. | frontend-design, frontend-skill, shadcn |
swift-agent-skills |
The main Swift and Apple-platform set in this library. Install it all at once or pick from it. | swiftui-pro, swiftui-ui-patterns, swiftui-design-principles |
build-systems |
Backend, architecture, MCP, and security work. | mcp-builder, backend-development, database-design |
test-and-debug |
QA, debugging, CI cleanup, and observability. | playwright, webapp-testing, gh-fix-ci |
docs-and-research |
Docs, files, research, and writing work. | pdf, doc-coauthoring, docx |
Curating the catalog
Use catalog when you want to add an upstream skill without vendoring it.
In a managed workspace, start with add.
Use catalog and vendor when you want more control.
npx ai-agent-skills catalog openai/skills --list
npx ai-agent-skills catalog openai/skills --skill linear --area workflow --branch Linear
npx ai-agent-skills catalog openai/skills --skill security-best-practices --area backend --branch Security
npx ai-agent-skills catalog conorluddy/ios-simulator-skill --skill ios-simulator-skill --area mobile --branch "Swift / Tools" --collection swift-agent-skills
npx ai-agent-skills catalog shadcn-ui/ui --skill shadcn --area frontend --branch Components
It does not create a local copy.
It adds metadata and placement in the active library:
- which shelf it belongs on
- what branch it lives under
- why it earned a place
- how it should install later
For existing picks, use curate for quick edits:
npx ai-agent-skills curate frontend-design --branch Implementation
npx ai-agent-skills curate ios-simulator-skill --collection swift-agent-skills
npx ai-agent-skills curate ios-simulator-skill --remove-from-collection swift-agent-skills
npx ai-agent-skills curate frontend-design --why "A stronger note that matches how I actually use it."
npx ai-agent-skills curate review
When I want a local copy, I use vendor:
npx ai-agent-skills vendor <repo-or-path> --skill <name> --area <shelf> --branch <branch> --why "Why this deserves a local copy."
npx ai-agent-skills vendor <repo-or-path> --skill <name> --area mobile --branch "Swift / Tools" --collection swift-agent-skills --why "Why this deserves a place in the Swift pack."
Source Repos
Current upstream mix:
| Source repo | Skills |
|---|---|
anthropics/skills |
11 |
openai/skills |
9 |
Dimillian/Skills |
4 |
wshobson/agents |
4 |
rgmez/apple-accessibility-skills |
3 |
ComposioHQ/awesome-claude-skills |
2 |
MoizIbnYousaf/Ai-Agent-Skills |
2 |
andrewgleave/skills |
1 |
arjitj2/swiftui-design-principles |
1 |
AvdLee/Core-Data-Agent-Skill |
1 |
AvdLee/Swift-Concurrency-Agent-Skill |
1 |
AvdLee/Swift-Testing-Agent-Skill |
1 |
bocato/swift-testing-agent-skill |
1 |
conorluddy/ios-simulator-skill |
1 |
dadederk/iOS-Accessibility-Agent-Skill |
1 |
efremidze/swift-architecture-skill |
1 |
emilkowalski/skill |
1 |
Erikote04/Swift-API-Design-Guidelines-Agent-Skill |
1 |
ivan-magda/swift-security-skill |
1 |
PasqualeVittoriosi/swift-accessibility-skill |
1 |
raphaelsalaja/userinterface-wiki |
1 |
shadcn-ui/ui |
1 |
twostraws/Swift-Concurrency-Agent-Skill |
1 |
twostraws/Swift-Testing-Agent-Skill |
1 |
twostraws/SwiftData-Agent-Skill |
1 |
twostraws/SwiftUI-Agent-Skill |
1 |
vanab/swiftdata-agent-skill |
1 |
The two biggest upstream publishers in this library are Anthropic and OpenAI.
I browse, pick, and shelve. I do not mirror everything they publish.
Commands
# Browse
npx ai-agent-skills
npx ai-agent-skills browse
npx ai-agent-skills list
npx ai-agent-skills list --work-area frontend
npx ai-agent-skills collections
npx ai-agent-skills search frontend
npx ai-agent-skills info frontend-design
npx ai-agent-skills preview pdf
# Install
npx ai-agent-skills install <skill-name>
npx ai-agent-skills swift
npx ai-agent-skills install <skill-name> -p
npx ai-agent-skills install --collection swift-agent-skills -p
npx ai-agent-skills <owner/repo>
npx ai-agent-skills install <owner/repo>
npx ai-agent-skills install <owner/repo>@<skill-name>
npx ai-agent-skills install <owner/repo> --skill <name>
npx ai-agent-skills install <owner/repo> --list
npx ai-agent-skills install ./local-path
npx ai-agent-skills install <skill-name> --dry-run
# Maintain
npx ai-agent-skills sync [name]
npx ai-agent-skills uninstall <name>
npx ai-agent-skills check
npx ai-agent-skills doctor
npx ai-agent-skills validate [path]
# Curate
npx ai-agent-skills catalog <owner/repo> --list
npx ai-agent-skills catalog <owner/repo> --skill <name> --area <shelf> --branch <branch> --why "<editorial note>"
npx ai-agent-skills curate <skill-name> --branch "<branch>"
npx ai-agent-skills curate review
npx ai-agent-skills vendor <repo-or-path> --skill <name> --area <shelf> --branch <branch> --why "<editorial note>"
Testing
npm test
Fast regression coverage for CLI behavior, schema rules, routing, and local install flows.npm run test:live
No-mock live verification. Clones the real upstream repos, captures rawSKILL.mdfrontmatter and file manifests, runs real install/sync/uninstall flows in isolated temp homes and projects, drives the TUI through a real PTY, and writes a report totmp/live-test-report.json.npm run test:live:quick
A smaller live matrix for faster iteration with the same no-mock pipeline.
Legacy Agent Support
Still supported through --agent <name>:
claudecursorcodexampvscodecopilotgeminigooseopencodelettakilocodeproject
What I Care About
- Small shelves
- Clear provenance
- Notes that explain why something stays
- Upstream repos staying upstream
- A library that looks cared for
Contributing
This is a curated library.
Read CURATION.md before opening a PR.
Related
Yorumlar (0)
Yorum birakmak icin giris yap.
Yorum birakSonuc bulunamadi