Monitor Kalshi

Monitor Kalshi prediction markets and rank 24h trading changes into alerts.

6|2|Updated May 21, 2026
One-click install
npx skills add https://github.com/anajuliabit/aeon --skill monitor-kalshi
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Monitor Kalshi
Source: https://github.com/anajuliabit/aeon/tree/main/skills/monitor-kalshi
Command: npx skills add https://github.com/anajuliabit/aeon --skill monitor-kalshi

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill turns noisy Kalshi price tables into a decision-focused digest by identifying which prediction markets moved enough, with enough liquidity, to matter over the last 24 hours.

Core Features & Use Cases

  • Watchlist-driven monitoring: Watches a configured list of Kalshi event tickers (or a single ad-hoc ticker) and analyzes only open markets.
  • 24h move + liquidity scoring: Computes intraday change from candlesticks, ranks markets by a move score weighted by activity, and estimates conviction using orderbook spread and depth.
  • Noise suppression and alerts: Suppresses small/low-volume moves, highlights large non-thin-book swings as alerts, and demotes continued-from-yesterday repeats.

Quick Start

Configure your watchlist in skills/monitor-kalshi/watchlist.md (one event ticker per line) and run the skill to receive a ranked report for the last 24h with alerts for the biggest non-thin-book movers.

Frequently Asked Questions about Monitor Kalshi

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

FAQPage Schema
How do I monitor Kalshi prediction markets for meaningful 24h price moves?

To monitor Kalshi prediction markets, you can configure a watchlist of event tickers to fetch candlestick deltas and orderbook depth from the Kalshi public trade API, producing a ranked, low-noise digest of 24h trading changes and alerts for significant movers.

What is the best way to filter low-liquidity noise from Kalshi market monitoring?

Filtering low-liquidity noise from Kalshi market monitoring involves applying suppression and threshold rules to candlestick deltas and orderbook spread data, which demotes small-volume moves and highlights only large, non-thin-book swings as alerts.

Can I generate research alerts for Kalshi markets based on orderbook depth and implied probability?

Yes, you can generate research alerts for Kalshi markets by estimating conviction using orderbook spread and depth metrics, which calculates an activity-weighted move score to flag large non-thin-book swings and continued movers within an event watchlist.

How does a candlestick delta calculation work for Kalshi market surveillance?

Candlestick delta calculation for Kalshi market surveillance computes the intraday change in implied probability by fetching 24h trading data from the public trade API, ranking markets by a move score weighted by activity and liquidity signals.

How do I set up a watchlist for scheduled Kalshi market surveillance and morning briefs?

Set up a watchlist for scheduled Kalshi market surveillance by adding one event ticker per line in the configuration file, then run the skill to analyze open markets and receive a ranked report with alerts for the biggest 24h movers.

Why are some continued Kalshi market movers demoted in my monitoring alerts?

Continued Kalshi market movers are demoted in monitoring alerts because the noise suppression rules identify and lower the priority of repeats from yesterday, ensuring the digest focuses on new, high-conviction swings rather than ongoing trends.