Open Source · GitHub Data Agent Skills Libraries
Loading data…
⚠  

Open Source · Agent Skills · Updated daily via GitHub Actions

Agent Skills Libraries —
official, community, and searchable

A curated index of agent skills libraries and collections — folders of instructions and scripts that agents such as Claude Code and Codex load on demand — with live GitHub stats. Building an agent instead? See the frameworks index.

of
Definitions

What is an agent skill?

An agent skill is a folder containing a SKILL.md file — instructions, with a name and a short description at the top — plus any scripts and reference files the instructions need. The agent sees only the names and descriptions up front and loads a skill’s full contents when the task calls for it, which keeps context small while making a large library available.

A skills library is a collection of these folders: an official set from a vendor, a large community catalog, a focused set for one domain, or a curated list pointing elsewhere. The format is documented as an open specification and is read by more than one agent, so a good skill is portable. The flip side is that a skill can bundle executable scripts, so installing one is closer to installing software than to copying a prompt.

Taxonomy

Categories in this index

Every entry above is tagged by kind. Use the Topic filter to isolate any of these — or read on for what each one means.

Spec

The specification and documentation for the skill format itself — what a valid skill looks like.

Official

Published by the vendor or team behind the product or agent, so it tracks that product and is accountable for it.

Collection

Large community libraries of many skills, often installable as plugins or bundles. Breadth varies; so does quality.

Directory

Curated “awesome” lists that point to skills elsewhere. Good for discovery; the skills themselves live in other repositories.

Domain

Focused libraries for one field — science, design, security, marketing, note-taking — with skills that share a point of view.

Tooling

Installers, converters, scanners and optimizers around skills, rather than skills themselves.

Security

Skills for security work, or tools that scan skills for risky content. Use security skills only on systems you are authorized to test.

Plugins

Bundles that package skills together with commands, sub-agents or hooks so they install as one unit.

Methodology

Libraries that encode a whole working method — planning, testing, review — rather than a single capability.

Terminology

Skill vs MCP server vs harness

They solve different problems and are often used together.

Skill

Instructions and scripts loaded into the agent’s context on demand. A skill teaches the agent how to do something — a procedure, a house style, a workflow.

MCP server

A live connection to a tool or data source. An MCP server gives the agent access to something — a database, a browser, an API.

Harness

The control layer that decides what the agent may actually do with either — permissions, budgets, approvals and verification.

Evaluation

How to choose a skills library

Six checks worth making before you install skills into an agent that can run commands on your machine.

1

Which agents it supports

Some libraries target Claude Code, others Codex, GitHub Copilot or OpenClaw. The format is shared, but packaging and install steps differ, so check the README for your agent.

2

What the skills can run

A skill may include scripts that execute on your machine. Read them before installing, prefer official or widely reviewed libraries, and consider running a scanner from the tooling group.

3

Curated or catalog

A small vetted library and a catalog of thousands serve different needs. Bigger is not better: a skill you never trigger is just clutter.

4

Trigger quality

A skill loads only when its description matches the task. Overlapping or vague descriptions across many skills make an agent pick the wrong one or none at all.

5

License

MIT and Apache-2.0 are unrestricted for commercial use. Some collections mix content under different terms, so check before redistributing.

6

Maintenance signal

The Updated column shows the last push. Skills reference tools and APIs that change, so an untouched library goes stale quickly.

FAQ

Questions, answered

What is an agent skill?

A folder with a SKILL.md file — a name, a description and instructions — plus optional scripts and reference files. An agent loads the full skill only when the task matches its description.

What is the difference between a skill and an MCP server?

A skill teaches the agent a procedure and is loaded into its context on demand. An MCP server gives the agent live access to a tool or data source. Skills add know-how; MCP servers add reach.

Are skills safe to install?

Treat them like any code you run. A skill can include scripts, and its instructions steer what the agent does. Prefer official or widely reviewed libraries, read a skill before installing it, and scan third-party ones.

Do skills only work in Claude?

The format is documented as an open specification, and several agents load the same SKILL.md structure. This index includes collections aimed at Claude Code, Codex, GitHub Copilot and OpenClaw — check each library’s README for exactly what it supports.

How do I install a skill?

It depends on the agent and the library. Some libraries ship as plugins, some as folders you copy into your agent’s skills directory, and there are installer tools listed under tooling. The library’s README is authoritative.

How are libraries chosen for this list?

By hand: substantial collections and official libraries, plus the specification and tooling around them. Single-purpose one-off skills are out of scope. Each entry is verified against the live GitHub API when the list is reviewed.

How current is this list?

Stars, forks and topics are refreshed daily via GitHub Actions — the freshness indicator in the nav bar shows the age of the current data pull. The list itself is reviewed by hand periodically.