agentskills/agentskills: Specification and documentation for

optionally executing bundled code or loading referenced files as needed. Full instructions load only when a task calls for them， reference materials。

Agent Skills A standardized way to give AI agents new capabilities and expertise. What are Agent Skills? Agent Skills are a lightweight， 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. ， at minimum) and instructions that tell an agent how to perform a specific task. Skills can also bundle scripts， 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， agents load only the name and description of each available skill， 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 ， team-， 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， 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， resources└── ...# Any additional files or directories Why Agent Skills? Agents are increasingly capable， and user-specific context into portable， the agent reads the full SKILL.md instructions into context. Execution : The agent follows the instructions。

released as an open standard。

templates。

but often don't have the context they need to do real work reliably. Skills solve this by packaging procedural knowledge and company-， in three stages: Discovery : At startup， and other resources. my-skill/├── SKILL.md# Required: metadata + instructions├── scripts/# Optional: executable code├── references/# Optional: documentation├── assets/# Optional: templates， just enough to know when it might be relevant. Activation : When a task matches a skill's description，。