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

# Agent Templates

> Start from a pre-built agent: fork a template into your GitHub during onboarding, or install one locally with the Claude Code plugin

Templates are pre-built agents with their instructions, context files and helper scripts. Use one as a starting point and customize it for your team.

There are two ways to use a template:

| Where | How | Result |
| - | - | - |
| DataGen Cloud onboarding | **Start from a Template** → **Use Template** | The template's repository is forked into your GitHub account and connected as a repository agent |
| Claude Code | `/datagen:fetch-agent` | The template's files are installed into your local project |

***

## Fork a template during onboarding

New DataGen Cloud accounts see two options when they start: **Deploy from GitHub** and **Start from a Template**.

<Steps>
  <Step title="Connect GitHub">
    Forking needs the DataGen GitHub App installed on your account, because the template is forked into your GitHub. If it is not installed yet, connect GitHub first.
  </Step>

  <Step title="Choose a template">
    Pick **Start from a Template**, then browse **Choose a Template**. Filter by category -- **Prospecting**, **CRM Hygiene**, **Lead Routing**, **Monitoring** or **Development**. Each card shows its difficulty and the MCP servers it needs.
  </Step>

  <Step title="Use it">
    Click **Use Template**. DataGen forks the template's repository into your GitHub account, connects the fork, and continues onboarding with connecting tools.
  </Step>
</Steps>

The fork is yours: change the agent by pushing to it, and set its runtime (vault, tool bundle, model, knowledge and data) on the agent page like any other repository agent. See [Connect a GitHub repository](/agents/build#connect-a-github-repository).

<Note>
  Template forking uses GitHub and is not available on self-hosted installations. There, upload the template's folder with **Upload** on the **Agents** page instead. See [Upload an agent](/agents/build#upload-an-agent).
</Note>

***

## Install a template with Claude Code

The DataGen plugin for Claude Code installs templates from the [DataGen agent templates repository](https://github.com/datagendev/datagen-agent-templates).

### Browse templates

```
/datagen:fetch-agent
```

Run it without arguments to see the catalog: each template's description, required tools and MCP connections.

### Install a template

```
/datagen:fetch-agent linkedin-engagement
```

<Steps>
  <Step title="Download files">
    Downloads the template's files:

    * `.claude/agents/<template-id>.md` -- the agent definition
    * `.datagen/<template-id>/` -- context, scripts, memory and working files
  </Step>

  <Step title="Check prerequisites">
    Lists the MCP connections, secrets and Python packages the template needs, and what is missing.
  </Step>

  <Step title="Install dependencies">
    Installs the Python packages listed in the template's manifest.
  </Step>

  <Step title="Post-install guide">
    Shows what the agent does, how to invoke it, and any remaining setup.
  </Step>
</Steps>

<Warning>
  After installing, run `claude -r` to reload Claude Code and pick up the new agent.
</Warning>

### After installing

* **Connect the MCP servers it needs.** Run `/datagen:add-mcps`, or add them to a vault in the web app. See [Tools](/agents/tools#add-an-mcp-server).
* **Add the secrets it needs** as credentials in a vault. See [Vault](/foundation/vault).
* **Run it** in Claude Code: `@<template-id> run the full pipeline`.

### Customize it

Installed templates are fully editable:

* **Context files** in `.datagen/<template-id>/context/` -- your domain knowledge
* **Scripts** in `.datagen/<template-id>/scripts/` -- data processing logic
* **Agent definition** in `.claude/agents/<template-id>.md` -- reasoning and workflow

<Tip>
  A locally installed template is a Claude Code sub-agent in your project. To run the same workflow as a DataGen agent, put its instructions in the agent's `CLAUDE.md` -- for example by asking the Agent Builder chat to adapt the template -- and publish it. See [Build an agent](/agents/build).
</Tip>

***

## Reusable skills

Skills are smaller, reusable capabilities that any agent can use. Install one locally with:

```
/datagen:fetch-skill
```

Skills install to `.claude/skills/<skill-name>/`. In DataGen, skills are uploaded to the workspace registry, reviewed, and then installed on agents. See [Skills](/context/skills).

## Next

<CardGroup cols={2}>
  <Card title="Build an agent" icon="hammer" href="/agents/build">
    Create and configure an agent in the Agent Builder
  </Card>

  <Card title="Apps" icon="table-columns" href="/apps/overview">
    Build notebooks and custom apps on the same data and context
  </Card>
</CardGroup>


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