# What is an agent skill?

An agent skill is a folder that teaches an AI agent how to do one kind of task. It holds a SKILL.md file (a name, a description of when to use it, and instructions) and can include scripts, templates and reference files. The agent loads it only when a task matches the description.

## What is in a skill

Every skill has a `SKILL.md` file. It starts with a short header, then the instructions:

```markdown
---
name: release-notes
description: Write release notes from merged pull requests. Use when the user asks for release notes or a changelog.
---

# Release notes

1. List the pull requests merged since the last tag.
2. Group them into Added, Changed and Fixed.
...
```

In Anthropic's format the `name` is lower-case letters, numbers and hyphens, up to 64 characters, and the `description` (up to 1,024 characters) must say both what the skill does and when to use it. A skill folder can also hold more Markdown files, scripts the agent can run, and templates.

## Loaded only when needed

Skills are cheap to install because the agent reads them in stages:

1. At start-up it reads only each skill's name and description.
2. When your request matches a description, it reads that skill's instructions.
3. It opens extra files or runs scripts only if the instructions point to them, and only a script's output enters the conversation.

*Diagram: How a skill loads.* At start-up the agent reads only each skill’s name and description. When a task matches, it reads the SKILL.md instructions. Extra files and scripts load only if the instructions point to them.

## Skills and MCP

They solve different problems and work well together. An [MCP server](https://ai-powered.com/academy/glossary/mcp) gives an agent access: new tools and data, such as your issue tracker. A skill gives it know-how: the steps your team follows, the format you want, which tools to use for a job.

## Where skills work

As of 19 November 2026, Anthropic documents skills in the Claude apps (uploaded as a zip on paid plans with code execution on), in Claude Code (folders in `~/.claude/skills/` or a project's `.claude/skills/`) and in the Claude API. Skills added in one of these places don't appear in the others. Other agents read the same folder format; the [agent skills](https://ai-powered.com/skills) section of the directory shows which ones each skill lists.

## Safety

A skill is instructions plus code, so treat installing one like installing software. Anthropic advises using skills only from sources you trust and reading every file first, looking for network calls or file access that don't match what the skill says it does.

## Sources

Official documentation, checked on 19 November 2026:

- [Agent Skills overview (Claude docs)](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/overview)

## Related terms

- [AI agent](https://ai-powered.com/academy/glossary/ai-agent): An AI agent is a system in which a language model decides, step by step, which tools to use and what to do next to finish a task, checking the result of each step before the next. A fixed script decides nothing; an agent directs its own process.
- [MCP](https://ai-powered.com/academy/glossary/mcp): MCP (Model Context Protocol) is an open standard for connecting AI applications to outside tools and data. An AI app connects to small programs called MCP servers, asks each one what it offers, and calls those tools when a task needs them.
- [Tool call](https://ai-powered.com/academy/glossary/tool-call): A tool call is a structured request from an AI model to run one of the functions it was given, with arguments that match the function's input schema. The app runs the function, sends the result back to the model, and the model uses it to answer or to decide its next step.
