moonpay-scout

Finds mispricings and arbitrage opportunities across Polymarket and Kalshi prediction markets.

110|29|Updated Mar 11, 2026
One-click install
npx skills add https://github.com/moonpay/skills --skill moonpay-scout
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: moonpay-scout
Source: https://github.com/moonpay/skills/tree/main/skills/moonpay-scout
Command: npx skills add https://github.com/moonpay/skills --skill moonpay-scout

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Prediction markets often price events inconsistently across platforms, creating actionable arbitrage and alpha opportunities for informed traders.

Core Features & Use Cases

  • Cross-platform scouting: Scan Polymarket and Kalshi for the same underlying event.
  • Deterministic arb math: Compute edge after platform fees and liquidity constraints.
  • Alpha thesis: Identify informational gaps to explain mispricings and potential trades.

Quick Start

Ask the agent to scout a topic across Polymarket and Kalshi to identify arbitrage and alpha opportunities.

Frequently Asked Questions about moonpay-scout

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I find arbitrage opportunities across Polymarket and Kalshi?

Cross-platform arbitrage in prediction markets occurs when the same event is priced inconsistently across platforms. You can capitalize on this by scanning Polymarket and Kalshi to identify mispricings, then evaluating the edge and alpha trades after accounting for fees and liquidity constraints.

Can I calculate prediction market edge after fees and liquidity constraints?

Yes, you can calculate prediction market edge after fees and liquidity constraints. The tool enforces deterministic math for arbitrage evaluation, ensuring accurate profitability rankings for cross-platform trades on Polymarket and Kalshi.

What is the best way to identify alpha trades in prediction markets?

The best way to identify alpha trades in prediction markets is to scan for informational gaps explaining mispricings across platforms. The tool evaluates these alpha theses alongside deterministic arbitrage math, ranking opportunities by profitability.

Does this tool work with both Polymarket and Kalshi market data?

Yes, this tool works with both Polymarket and Kalshi market data. It requires access to market data, fee structures, and liquidity metrics from both platforms to scout cross-platform mispricings and evaluate arbitrage opportunities.

When should I not use cross-platform arbitrage scouting for prediction markets?

You should avoid cross-platform arbitrage scouting when real-time market data, fee structures, or liquidity metrics are unavailable. Accurate deterministic math for arb evaluation depends entirely on access to these inputs from both Polymarket and Kalshi.