Agent skills
Agent skills are folders of instructions, scripts and reference files, each described by a SKILL.md file, that an AI agent can discover and load only when a task needs them.
Also called: SKILL.md, Claude skills
By Divya Sharma · Checked Nov 15, 2026 · How we review
An agent's system prompt cannot hold every procedure a team uses. Skills package that know-how into folders the agent reads on demand: how to fill in a company form, run a release, or follow a house style.
How it works
Each skill is a directory with a SKILL.md file. The file starts with YAML front matter that gives the skill a name and a description, followed by instructions in Markdown. It can point to other files and scripts in the folder.
Loading is staged, which Anthropic calls progressive disclosure. At startup the agent sees only the name and description of each installed skill. When a task matches, it reads the full SKILL.md. If that file points to more material, it reads that only when needed. Many skills can be installed without filling the context window.
Anthropic has published Agent Skills as an open standard, so the same folder can work across different agents.
Skills versus MCP servers
An MCP server gives an agent new tools, often connecting to an outside service. A skill mostly gives it instructions and local scripts. The two combine well: a skill can explain how to use a server's tools for a particular job. Skills are also close to slash commands, which a user triggers by name.
See the skills directory and Anthropic's skills repository for examples.
Related terms
- MCP server
- An MCP server is a program that exposes tools, data resources or prompt templates to AI applications through the Model Context Protocol, so any MCP-compatible client can use them without custom integration code.
- Coding agent
- A coding agent is an AI agent that works on software directly: it reads a codebase, edits files, runs commands and tests, and repeats until a change works, rather than only suggesting code for a person to paste.
- System prompt
- A system prompt is the block of instructions an application sends to a language model before the user's messages. It sets the model's role, rules, tone and output format for the whole conversation.
- Slash command
- A slash command is an instruction typed with a leading slash, such as /compact or /review, that tells an AI tool to run a built-in action or a saved prompt instead of treating the text as an ordinary message.
- Agent instructions file (AGENTS.md)
- An agent instructions file is a Markdown file in a code repository, such as AGENTS.md or CLAUDE.md, that a coding agent reads at the start of a session to learn the project's commands, conventions and rules.