Kalshi

This connects Claude to Kalshi's CFTC-regulated prediction markets for sports outcomes. You get access to event contracts, market prices (on a 0-100 probability scale, not odds), trade history, and candlestick data across major sports including EPL, NBA, NFL, and Champions League. It's built for checking implied probabilities and market sentiment, not actual scores or results. The API is public and requires no auth for reads. One thing to watch: the sport parameter is mandatory for single-game market searches or you'll get zero results, and "football" means NFL here, not soccer. Use the league-specific codes like epl or ucl for that.

skills.sh installs: 1.1K
GitHub stars: 268
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add machina-sports/sports-skills --skill kalshi --agent claude-code

Installs into .claude/skills of the current project.

Files

Kalshi — Prediction Markets

Before writing queries, consult references/api-reference.md for sport codes, series tickers, and command parameters.

Quick Start

Prefer the CLI — it avoids Python import path issues:

sports-skills kalshi search_markets --sport=nba
sports-skills kalshi get_todays_events --sport=nba
sports-skills kalshi get_sports_config
sports-skills kalshi get_markets --series_ticker=KXNBA --status=open

Python SDK (alternative):

from sports_skills import kalshi

kalshi.search_markets(sport='nba')
kalshi.search_markets(sport='nba', query='Lakers')
kalshi.get_todays_events(sport='nba')
kalshi.get_sports_config()
kalshi.get_markets(series_ticker="KXNBA", status="open")

CRITICAL: Before Any Query

CRITICAL: Before calling any market endpoint, verify:

The sport parameter is always passed to search_markets and get_todays_events for single-game markets.
Prices are on a 0-100 integer scale (20 = 20% implied probability) — do not treat as American odds.
status="open" is used when querying markets to exclude settled/closed markets.

SKILL.md on GitHub