SOLFIND
Web Lens
Portal home

Agent Skills Overview - Agent Skills

https://agentskills.io/home • 265 KB fetched
Open original page


Agent Skills Overview - Agent Skills Documentation Index Fetch the complete documentation index at: /llms.txt Use this file to discover all available pages before exploring further. Skip to main content Agent Skills now has an official Discord server . See the announcement for details. Agent Skills home page Agent Skills Search... ⌘ K Ask Assistant ⌘ I * agentskills/agentskills * agentskills/agentskills Search... Navigation Agent Skills Overview * Overview * Specification * Client Showcase For skill creators * Quickstart * Best practices * Optimizing descriptions * Evaluating skills * Using scripts For client implementors * Adding skills support On this page * What are Agent Skills? * Why Agent Skills? * How do Agent Skills work? * Where can I use Agent Skills? * Open development * Get started with Agent Skills Agent Skills Overview Copy page Copy page A standardized way to give AI agents new capabilities and expertise. Copy page Copy page ​ 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: * Discovery : At startup, agents load only the name and description of each available skill, just enough to know when it might be relevant. * Activation : When a task matches a skill’s description, the agent reads the full SKILL.md instructions into context. * 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! ​ 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. Come join the discussion on GitHub or Discord ! ​ Get started with Agent Skills Quickstart Create your first Agent Skill and see it in action. Specification The complete format specification for Agent Skills. Specification Assistant Responses are generated using AI and may contain mistakes.

Links found on this page

  1. /llms.txt [direct]
  2. Skip to main content [direct]
  3. Discord server [direct]
  4. announcement [direct]
  5. Agent Skills home page Agent Skills [direct]
  6. agentskills/agentskills [direct]
  7. Specification [direct]
  8. Client Showcase [direct]
  9. Quickstart [direct]
  10. Best practices [direct]
  11. Optimizing descriptions [direct]
  12. Evaluating skills [direct]
  13. Using scripts [direct]
  14. Adding skills support [direct]
  15. Anthropic [direct]