Skip to main content
Rekko is available as a SKILL.md in the OpenClaw 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:
SkillRoleWhat it does
RekkoThe BrainDeep causal research, probability estimates, trading signals
PolyClawThe Hands (Polymarket)Executes trades on Polymarket via CTF minting + CLOB
Kalshi TraderThe 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

npx skills add rekko
This adds the SKILL.md to your agent’s skill set. Requires REKKO_API_KEY in your environment.

​
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

MCP Tools Reference

Full list of available tools and parameters.

API Reference

Direct API access for custom integrations.