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

# Agent Skills

> Pre-built workflow skills that teach AI agents how to use Databar

The MCP server ships with **Agent Skills** — pre-built workflow instructions that teach AI agents how to combine Databar tools for common tasks.

Skills follow the open [SKILL.md](https://agentskills.io/) standard and work across **27+ agents** including Claude, Cursor, Codex, Gemini CLI, OpenClaw, Windsurf, and GitHub Copilot.

<Info>
  Skills work with the [hosted MCP server](https://mcp.databar.ai/mcp) (recommended). They also work with a **local** server via npm or a source build; the **npm package may lag behind hosted**, so prefer the remote URL when your client supports it.
</Info>

## Available skills

<CardGroup cols={2}>
  <Card title="Single Enrichment" icon="magnifying-glass" href="/mcp-skill-enrichment">
    Look up a person, company, email, or phone number using the best matching enrichment.
  </Card>

  <Card title="Table-Driven Enrichment" icon="table" href="/mcp-skill-table">
    Create a table, insert rows, attach an enrichment, run it, and get a shareable link.
  </Card>

  <Card title="Waterfall Enrichment" icon="bolt" href="/mcp-skill-waterfall">
    Try multiple data providers in sequence to maximize success rate.
  </Card>

  <Card title="Bulk Enrichment" icon="layer-group" href="/mcp-skill-bulk">
    Enrich a list of up to 100 records in a single operation with inline results.
  </Card>
</CardGroup>

## How skills work

Without skills, you have to guide the AI step-by-step: "search for an enrichment, then get details, then run it..." With skills, you just say **"find the email for John Smith at Google"** and the agent knows the full workflow automatically.

Skills use a three-phase loading model to stay efficient:

| Phase          | What loads                              | Token cost               |
| -------------- | --------------------------------------- | ------------------------ |
| **Discovery**  | Name and description only               | \~100 tokens per skill   |
| **Activation** | Full instructions when the task matches | Under 5,000 tokens       |
| **Execution**  | Agent follows the workflow              | Zero additional overhead |

<Info>
  Skills are loaded on demand — they don't consume context until the agent decides they're relevant to your request.
</Info>

## Installing skills

Skills are included in the `skills/` folder of the [GitHub repo](https://github.com/databar-ai/databar-mcp-server). To use them:

<Tabs>
  <Tab title="Claude Code / Claude.ai">
    Copy the skill folders into your Claude skills directory:

    ```bash theme={null}
    git clone https://github.com/databar-ai/databar-mcp-server.git
    cp -r databar-mcp-server/skills/* ~/.claude/skills/
    ```

    Claude will automatically discover and activate the skills when relevant.
  </Tab>

  <Tab title="Cursor / Codex / Other agents">
    Copy the skill folders into your project's `.claude/skills/` directory (most agents that support SKILL.md use this path):

    ```bash theme={null}
    git clone https://github.com/databar-ai/databar-mcp-server.git
    mkdir -p .claude/skills
    cp -r databar-mcp-server/skills/* .claude/skills/
    ```
  </Tab>

  <Tab title="OpenClaw">
    Copy to your OpenClaw skills directory:

    ```bash theme={null}
    git clone https://github.com/databar-ai/databar-mcp-server.git
    cp -r databar-mcp-server/skills/* ~/.openclaw/skills/
    ```
  </Tab>
</Tabs>