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

> ## Agent Instructions
> To act on Atlan objects, use the Atlan MCP server at https://api.atlan.com/mcp or the SDK. To install or publish skills from a terminal, use the `brain` CLI; `brain --map json` prints its command map. The `atlanai` CLI is deprecated. Run a read-only identity check before any write.
> The docs MCP server at /mcp searches these docs only. It cannot read or change Atlan objects.
> SDK packages: Python `atlanai` (PyPI) and TypeScript `@atlanai/sdk` (npm). Show Python first, then TypeScript.
> These docs cover Atlan Agent Registry, Atlan's hosted product. The open-source agent registry specification and its CLI (`brain`) are documented, released and maintained in their own repository; /open-source on this site links to it. Answer general specification or `brain` command questions from the project's own docs, and use these docs only for Atlan-specific setup such as the Atlan adapter, sign-in and workspaces.

# Platform

> Build agents and their context, share skills, track what agents do and cost, and measure their quality.

Platform covers the work you do with Agent Registry itself, in the order teams usually do it: build an agent and the context it uses, share the skills it relies on, track what it does, and measure how well it does it.

<CardGroup cols={2}>
  <Card title="Build context" icon="hammer" href="/registry/agents/index">
    Register agents, equip them with governed skills and tools, and connect the clients and frameworks they run in.
  </Card>

  <Card title="Find & share" icon="share-nodes" href="/registry/skills/index">
    Find, assess, publish, release, and improve reusable skills.
  </Card>

  <Card title="Track usage" icon="chart-line" href="/registry/traces/index">
    Send traces from your agents and coding sessions, attribute them to the right agent, and compare usage, cost, and errors.
  </Card>

  <Card title="Measure quality" icon="gauge" href="/evals/index">
    Test an agent against fixed cases before release, gate pull requests on the scores, and judge the sessions it produces in use.
  </Card>
</CardGroup>

## Common first tasks

<CardGroup cols={2}>
  <Card title="Bring agent into Atlan" icon="arrow-right-to-bracket" href="/registry/agents/how-tos/bring-agent">
    Register an agent from its repository with Atlan Desktop, add its skills and context, and send its first trace.
  </Card>

  <Card title="Choose skill publishing method" icon="upload" href="/registry/skills/how-tos/publish-and-version">
    Compare the ways to publish skills to a workspace, prepare the package, and verify the version in Atlan.
  </Card>

  <Card title="Send and verify traces" icon="paper-plane" href="/registry/traces/how-tos/send-and-verify">
    Choose how to send traces, send them as the right identity, and confirm they reached the intended workspace and agent.
  </Card>

  <Card title="Run your first eval" icon="flask" href="/evals/quickstart">
    Run a two-case eval from Python or TypeScript and confirm the experiment and its traces are stored in your workspace.
  </Card>
</CardGroup>

To find a specific page, use **Search the docs** at the top of any page.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.