prediction-arbitrage-scout

Name: prediction-arbitrage-scout
Availability: InStock
Author: velcrafting

Compare Polymarket and Kalshi YES/NO prices to rank arbitrage opportunities.

1|Updated Jan 13, 2026

Search Tags:#data-analysis #market-data #kalshi #polymarket #fuzzy-matching #arbitrage

Ready to run

npx skills add https://github.com/velcrafting/codex-skills --skill prediction-arbitrage-scout

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: prediction-arbitrage-scout
Source: https://github.com/velcrafting/codex-skills/tree/main/skills/prediction-arb
Command: npx skills add https://github.com/velcrafting/codex-skills --skill prediction-arbitrage-scout

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, pandas, and includes scripts (resource) components.

What problem does it solve?

Scout cross-platform price discrepancies between Polymarket and Kalshi to surface candidate events for review.

Core Features & Use Cases

Event matching: fuzzy matching of market names to align related events across platforms.
Arbitrage discovery: compute theoretical costs and profits after fees to rank opportunities.
Reporting: generate CSV and Markdown reports for audits and prioritization.

Quick Start

Run the full discovery pipeline to fetch data, detect arbitrage candidates, and generate the review report.

Frequently Asked Questions about prediction-arbitrage-scout

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

FAQPage Schema

How do I find arbitrage opportunities between Polymarket and Kalshi?▼

Cross-market price discrepancies occur when YES/NO prices for aligned events differ across platforms. This Skill identifies those gaps by fetching public endpoint data, applying fuzzy matching to event names, and computing theoretical costs after fees to rank profitable opportunities.

How do I compare prediction market prices using Python and pandas?▼

You can compare prediction market prices by fetching data from public endpoints using the requests library and processing it with pandas. The workflow normalizes prices, matches events across platforms, and generates audit-ready Markdown and CSV outputs for review.

Do I need API keys to fetch Polymarket and Kalshi market data for analysis?▼

No, you do not need API keys to fetch market data for analysis. The pipeline retrieves YES/NO prices from publicly available endpoints on both platforms, requiring only Python 3.x with standard libraries like requests and pandas to execute the discovery workflow.

What is the best way to normalize and match event names across different prediction platforms?▼

The best way to normalize and match event names is using fuzzy matching algorithms to align similar market titles across platforms. This ensures accurate comparison of YES/NO prices and reliable calculation of arbitrage opportunities before generating final reports.

What limitations exist when calculating theoretical profits from prediction market price gaps?▼

Limitations include dependency on public endpoint availability and potential mismatches from fuzzy matching imperfect event names. Theoretical profit calculations rely on current fee structures, meaning real-time execution may face slippage or liquidity constraints not captured in the generated CSV report.