Skip to content
Back to search

agentskills

Specification and documentation for Agent Skills

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/agentskills-agentskills/badge.svg)](/listings/agentskills-agentskills)

HTML

<a href="/listings/agentskills-agentskills"><img src="/api/listings/agentskills-agentskills/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 59 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Agent Skills
  2. [![Discord](https://img.shields.io/badge/Discord-Join-5865F2?logo=discord&logoColor=white)](https://discord.gg/MKPE9g8aUy)
  3. A standardized way to give AI agents new capabilities and expertise.
  4. ## What are Agent Skills?
  5. Agent Skills are a lightweight, open format for extending AI agent capabilities with specialized knowledge and workflows.
  6. 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.
  7. ```
  8. my-skill/
  9. ├── SKILL.md # Required: metadata + instructions
  10. ├── scripts/ # Optional: executable code
  11. ├── references/ # Optional: documentation
  12. ├── assets/ # Optional: templates, resources
  13. └── ... # Any additional files or directories
  14. ```
  15. ## Why Agent Skills?
  16. 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:
  17. - **Domain expertise**: Capture specialized knowledge — from legal review processes to data analysis pipelines to presentation formatting — as reusable instructions and resources.
  18. - **Repeatable workflows**: Turn multi-step tasks into consistent, auditable procedures.
  19. - **Cross-product reuse**: Build a skill once and use it across any skills-compatible agent.
  20. ## How do Agent Skills work?
  21. Agents load skills through **progressive disclosure**, in three stages:
  22. 1. **Discovery**: At startup, agents load only the name and description of each available skill, just enough to know when it might be relevant.
  23. 2. **Activation**: When a task matches a skill's description, the agent reads the full `SKILL.md` instructions into context.
  24. 3. **Execution**: The agent follows the instructions, optionally executing bundled code or loading referenced files as needed.
  25. Full instructions load only when a task calls for them, so agents can keep many skills on hand with only a small context footprint.
  26. ## Where can I use Agent Skills?
  27. Agent Skills are supported by a large number of AI tools and agentic clients — see the [Client Showcase](https://agentskills.io/clients) to explore some of them!
  28. ## Getting started
  29. - **[Documentation](https://agentskills.io)** — Guides and tutorials
  30. - **[Specification](https://agentskills.io/specification)** — Format details
  31. - **[Example Skills](https://github.com/anthropics/skills)** — See what's possible
  32. - **[Discord](https://discord.gg/MKPE9g8aUy)** — Share what you're building!
  33. ## Open development
  34. The Agent Skills format was originally developed by [Anthropic](https://www.anthropic.com/), 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`](CONTRIBUTING.md) for how to get involved.
  35. ## License
  36. Code in this repository is licensed under [Apache 2.0](LICENSE). Documentation is licensed under [CC-BY-4.0](https://creativecommons.org/licenses/by/4.0/). See individual directories for details.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.