> ## Documentation Index
> Fetch the complete documentation index at: https://learn.getodin.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Agent Skills Overview

> A standardized way to give AI agents new capabilities and expertise.

## 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 dataset containing a `SKILL` 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.

## 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:

<CardGroup cols={3}>
  <Card title="Domain Expertise" icon="brain">
    Capture specialized knowledge — from legal review processes to data analysis pipelines to presentation formatting — as reusable instructions and resources.
  </Card>

  <Card title="Repeatable Workflows" icon="arrow-rotate-right">
    Turn multi-step tasks into consistent, auditable procedures.
  </Card>

  <Card title="Cross-Product Reuse" icon="share-nodes">
    Build a skill once and use it across any skills-compatible agent.
  </Card>
</CardGroup>

## How do Agent Skills work?

Agents load skills through **progressive disclosure**, in three stages:

<Steps>
  <Step title="Discovery">
    At startup, agents load only the `name` and `description` of each available skill — just enough to know when it might be relevant.
  </Step>

  <Step title="Activation">
    When a task matches a skill's description, the agent reads the full `SKILL` instructions into context.
  </Step>

  <Step title="Execution">
    The agent follows the instructions, optionally executing bundled code or loading referenced files as needed.
  </Step>
</Steps>

Skills also have four key behavioral properties:

<CardGroup cols={2}>
  <Card title="Trigger-based" icon="bolt">
    Skills activate when user messages match defined keywords or regex patterns.
  </Card>

  <Card title="Always-on" icon="signal">
    Some skills inject instructions into every conversation turn, regardless of the trigger.
  </Card>

  <Card title="Composable" icon="layer-group">
    Multiple skills can activate simultaneously to handle complex, multi-domain tasks.
  </Card>

  <Card title="Library" icon="books">
    Install pre-built skills from the library or create your own custom skills.
  </Card>
</CardGroup>

<Note>
  Full instructions load only when a task calls for them, so agents can keep many skills on hand with only a small context footprint.
</Note>

## Add Agent Skills to Your Agents!

<CardGroup cols={2}>
  <Card title="Getting Started" icon="rocket" href="agent-skills-getting-started">
    Install the Skills Manager Toolkit and create your first custom skill.
  </Card>

  <Card title="Skills Library" icon="books" href="agent-skills-library">
    Browse all pre-built skills available out of the box, organized by category.
  </Card>
</CardGroup>