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

# OpenClaw Skills

> Use Rekko as an intelligence skill in the OpenClaw agent ecosystem.

<Info>
  **Source code:** [github.com/Rekko-AI/rekko-skill](https://github.com/Rekko-AI/rekko-skill)
</Info>

Rekko is available as a **SKILL.md** in the [OpenClaw](https://openclaw.org) ecosystem — an open standard for composable AI agent skills.

## Rekko's role

In the OpenClaw ecosystem, three skills work together for autonomous prediction market trading:

| Skill             | Role                   | What it does                                                 |
| ----------------- | ---------------------- | ------------------------------------------------------------ |
| **Rekko**         | The Brain              | Deep causal research, probability estimates, trading signals |
| **PolyClaw**      | The Hands (Polymarket) | Executes trades on Polymarket via CTF minting + CLOB         |
| **Kalshi Trader** | The Hands (Kalshi)     | Executes trades on Kalshi                                    |

Rekko also ingests market data from **Robinhood** as a supported data source for research and analysis, though Robinhood does not have a separate execution skill.

Rekko provides the *why* behind market movements. Execution skills handle the *how*.

## Installation

```bash theme={null}
npx skills add Rekko-AI/rekko-skill
```

This adds the `SKILL.md` to your agent's skill set. Requires `REKKO_API_KEY` in your environment, or an EVM wallet with USDC on Base for x402 autopay.

## Python client

The repo includes `rekko_tools.py` — an async HTTP client with x402 payment support:

```python theme={null}
from rekko_tools import RekkoClient

async with RekkoClient() as client:
    markets = await client.list_markets(source="kalshi", limit=30)
    signal = await client.get_strategy("Will the Fed cut rates?")
```

See the [Python client reference](/integrations/openclaw/python-client) for full documentation.

## Example workflow

An agent with all three skills can autonomously:

1. **Screen** markets with Rekko (`list_markets`, `screen_markets`)
2. **Analyze** promising candidates (`get_strategy` — 30-90s blocking call)
3. **Decide** based on the signal (recommendation, edge, confidence)
4. **Execute** via PolyClaw (Polymarket) or Kalshi Trader (Kalshi)
5. **Track** the position (`place_shadow_trade`, `get_portfolio`)

## Thin client principle

The SKILL.md teaches agents how to *consume* Rekko intelligence — how to call tools, interpret responses, and chain with execution skills. All research methodology stays behind the API.

## Learn more

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/integrations/openclaw/quickstart">
    Get your first signal in 5 minutes.
  </Card>

  <Card title="Python Client" icon="python" href="/integrations/openclaw/python-client">
    RekkoClient reference with x402 autopay.
  </Card>

  <Card title="MCP Tools Reference" icon="wrench" href="/integrations/mcp/tools-reference">
    Full list of available tools and parameters.
  </Card>

  <Card title="API Reference" icon="code" href="/api-reference/introduction">
    Direct API access for custom integrations.
  </Card>
</CardGroup>