← ClaudeAtlas

prediction-market-monitorlisted

Pull Kalshi prediction market prices for Fed decisions, CPI, GDP, NFP, and other macro / market events. Report implied probability per outcome, aggregate cross-strike distribution when the series is a laddered strike set (like KXFED-27APR-T4.25, T4.00, T3.75...), expected value, modal outcome, and open interest. Prediction markets now clear enough volume post-2024 to reflect a real market-implied policy path, often diverging from surveyed economist consensus. Uses Kalshi's public read-only API; no authentication required.
rgourley/quant-garage · ★ 6 · Data & Documents · score 66
Install: claude install-skill rgourley/quant-garage
# prediction-market-monitor You pass a Kalshi series or shortcut. The skill pulls open markets, groups by event, and reports implied probabilities. When the event is a laddered strike-type (Fed funds level, CPI reading), it derives the cross-strike probability distribution from adjacent-threshold differences and reports the modal outcome and expected value. Motivated by 2025-26 growth of prediction markets as leading indicators post-2024 election validation. Kalshi Fed-decision contracts now trade meaningful volume; contract prices often reflect policy expectations before consensus surveys catch up. ## When to invoke - "What's the Kalshi-implied Fed decision at the next meeting?" - Comparing market-implied CPI to Bloomberg / Reuters consensus - Cross-referencing macro-print bets against your positioning - The user says "Kalshi", "prediction market", "implied Fed", "fed funds futures alternative" ## What you need - Internet access (Kalshi's public API; no Massive key needed) Optional: - `--series` (shortcut like `fed`, `cpi`, `nfp`, `gdp`, or a raw Kalshi series ticker like `KXFED`, `KXCPI`) - `--keyword` (client-side filter on title / ticker) - `--event-ticker` (pin a specific event, e.g. `KXFED-27APR`) - `--max-events` (default 5) ## What you get back **Layer 1: JSON**. Per event: `event_ticker`, `title`, `close_time`, `markets` (each with `implied_probability`, bid, ask, last, volume, open interest, floor_strike). When laddered: `implied_distribution.buckets`