agentskills

From public sources

Agent Skills is an open specification for packaging instructions, scripts and resources into portable SKILL.md folders that AI agents load on demand.

AI skillCategory: AI Skills · Skill collections · Software engineeringOpen sourcedata checked Oct 15, 2026

Overview

AI agents often lack the procedural knowledge and team-specific context needed to complete real tasks reliably. Agent Skills solves this with a lightweight, open format: a skill is a folder built around a SKILL.md file that holds metadata and step-by-step instructions, optionally bundled with scripts, reference documents and templates. Agents use progressive disclosure. At startup they read only each skill's name and description, then load the full instructions when a task matches, and run bundled code or referenced files as needed. This keeps many skills available without filling the context window. The format suits developers, teams and organizations that want to capture repeatable workflows as version-controlled, reusable assets usable across any compatible agent. It is released under Apache 2.0 for code and CC-BY-4.0 for documentation.
  • agent-skills

Installation

Commands are shown, never run by the marketplace. Check them against the official documentation.

Compatibility

Unknown means no evidence was found — not that the product is incompatible.
PlatformStatusArchitectureEvidenceConfidence
Claude CodeUnknown———
Claude (web & desktop)Unknown———
OpenAI CodexUnknown———
ChatGPTUnknown———
CursorUnknown———
GitHub CopilotUnknown———
Gemini CLIUnknown———

Releases

checked Oct 29, 2026
No releases found on the source.

Quality profile

algorithm quality-v1.0 · assessed Oct 15, 2026
Quality Score73
Risk Score0
Confidence 1.00
Quality Score and Risk Score are different measures. A high score does not guarantee safety.

Score components

Maintenance · 2016
last activity 67 days ago
Documentation · 1515
README 3315 chars, description present
Ready to use · 150
install instructions: no; releases: no
Metadata · 1010
4/4 of description, homepage, license, topics
Releases · 102
0 release(s)
Category confidence · 1010
classifier confidence 1
Adoption · 1010
26181 stars (log-dampened, 10k = max)
License clarity · 55
SPDX Apache-2.0
Community · 55
issues enabled, 1974 forks

License

Apache-2.0
Known licensefrom the repository host

This is the catalog policy status, not legal advice.

Sources

github.com/agentskills/agentskillsPrimary★ 26,181 starslast activity Aug 9, 2026Primary repository · Confidence 1.00

Reviews

Sign in to write a review

No reviews yet.

Alternatives

README

From agentskills/agentskills · license Apache-2.0 · fetched Oct 29, 2026

Agent Skills

[Discord]

A standardized way to give AI agents new capabilities and expertise.

What are Agent Skills?

Agent Skills are a lightweight, open format for extending AI agent capabilities with specialized knowledge and workflows.

At its core, a skill is a folder containing a SKILL.md file. This file includes metadata (name and description, at minimum) and instructions that tell an agent how to perform a specific task. Skills can also bundle scripts, reference materials, templates, and other resources.

my-skill/
├── SKILL.md          # Required: metadata + instructions
├── scripts/          # Optional: executable code
├── references/       # Optional: documentation
├── assets/           # Optional: templates, resources
└── ...               # Any additional files or directories

Why Agent Skills?

Agents are increasingly capable, but often don't have the context they need to do real work reliably. Skills solve this by packaging procedural knowledge and company-, team-, and user-specific context into portable, version-controlled folders that agents load on demand. This gives agents:

  • Domain expertise: Capture specialized knowledge — from legal review processes to data analysis pipelines to presentation formatting — as reusable instructions and resources.
  • Repeatable workflows: Turn multi-step tasks into consistent, auditable procedures.
  • Cross-product reuse: Build a skill once and use it across any skills-compatible agent.

How do Agent Skills work?

Agents load skills through progressive disclosure, in three stages:

  1. Discovery: At startup, agents load only the name and description of each available skill, just enough to know when it might be relevant.

  2. Activation: When a task matches a skill's description, the agent reads the full SKILL.md instructions into context.

  3. Execution: The agent follows the instructions, optionally executing bundled code or loading referenced files as needed.

Full instructions load only when a task calls for them, so agents can keep many skills on hand with only a small context footprint.

Where can I use Agent Skills?

Agent Skills are supported by a large number of AI tools and agentic clients — see the Client Showcase to explore some of them!

Getting started

Open development

The Agent Skills format was originally developed by Anthropic, released as an open standard, and has been adopted by a growing number of agent products. The standard is open to contributions from the broader ecosystem — see CONTRIBUTING.md for how to get involved.

License

Code in this repository is licensed under Apache 2.0. Documentation is licensed under CC-BY-4.0. See individual directories for details.

Open the repository ↗