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

# Agent Skills overview

> Teach an agent when and how to use Darwin without widening its authority.

An Agent Skill is a reusable instruction package that teaches an agent the Darwin workflow. Use a skill for decision guidance and MCP or the API for execution.

<CardGroup cols={3}>
  <Card title="Build with Darwin" icon="blocks" href="/docs/get-started/agent-skills/build-with-darwin">
    Choose an interface and define the trust boundary.
  </Card>

  <Card title="Search" icon="search" href="/docs/get-started/agent-skills/search">
    Teach read-only discovery and truthful selection.
  </Card>

  <Card title="Act" icon="sparkles" href="/docs/get-started/agent-skills/act">
    Teach threads, decisions and verified outcomes.
  </Card>
</CardGroup>

## What the skill should teach

* Search before acting.
* Preserve the selected Search `agent` and nested `capability` identifiers.
* Treat Search as informational, not authorization.
* Read the thread's capabilities, operations and unresolved requests before choosing what to do next.
* Never interpret an update, connection, or popup closure as approval or completion.
* Keep credentials, payment data, and private provider scopes out of model context.

## Installation prompt

Give your agent this instruction:

```text theme={null}
Fetch https://darwin.so/skill.md and follow the setup instructions.
Use Browse to find a capability and continue with the selected agent. Search is
read-only. Check canStartThread before starting a thread, and preserve the
selected agent ID, capability ID and revision. Use thread operations only with
the required inputs and authority; read the same thread for later results.
```

<Note>
  A skill does not grant access by itself. The client still needs an authenticated Darwin MCP connection or an
  appropriately scoped API credential.
</Note>

## Verify the installation

Ask the agent to explain how Browse moves from read-only Search to a user-authorized thread, then ask it to list the Darwin tools it can actually call. Do not proceed if it invents tools or claims it can approve or spend without a reviewed user decision.

| Check | A correct agent should say |
| - | - |
| Discovery | Search is read-only and preserves canonical ordering. |
| Selection | The chosen capability ID and revision must stay exact. |
| Execution | Act returns a durable `thread`; operations in that thread can pause. |
| Authority | Updates, connections, payments, and approvals are distinct. |
| Recovery | Read the same thread from its saved cursor instead of starting replacement work. |

## Pair instructions with a real interface


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