AI SummaryThis skill packages everything needed to build a panel that reads prediction-market probabilities from Polymarket + Kalshi (both public, read-only, no account) and presents them as a macro sentiment thermometer grouped by module.
Install
Copy this and paste it into Claude Code, Cursor, or any AI assistant:
I want to install the "globalpercent" skill in my project. Please run this command in my terminal: # Install skill into your project mkdir -p .claude/skills/globalpercent && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/globalpercent/SKILL.md "https://raw.githubusercontent.com/simonlin1212/globalpercent/main/SKILL.md" Then restart Claude Code (or reload the window in Cursor) so the skill is picked up.
Description
GlobalPercent — build a global-macro-probability panel for an investment research system. Merges public probability data from prediction markets (Polymarket + Kalshi), classifies every market into macro modules (monetary policy / macro economy / AI / etc.), and shows the whole market's expected-probability state at a glance as a sentiment/risk overlay (not a trading signal). Use when building a macro-probability or "event probability" dashboard, or wiring Polymarket/Kalshi APIs. Includes verified API details, the full architecture, hard-won gotchas, and adaptable reference code (Python backend + React panel).
GlobalPercent — a global-macro-probability panel for your research system
This skill packages everything needed to build a panel that reads **prediction-market probabilities from Polymarket + Kalshi** (both public, read-only, no account) and presents them as a macro sentiment thermometer grouped by module. It is NOT a single API call. The value is in the system: classification, dedup, multi-source merge, snapshot caching, async refresh, translation, and a dozen non-obvious gotchas that each cost real debugging time. All of that is captured here so you don't rediscover it.
The one idea
A prediction market's price IS a probability. A contract trading at $0.62 means the market collectively bets 62% the event happens. Reading those numbers is free, needs no wallet or account — only trading does. So you can pull a global, money-backed sentiment read on Fed decisions, geopolitics, AI milestones, etc. for zero cost. Use it as a thermometer, not a trading tool. 70–84% of prediction-market traders lose money; the edge belongs to HFT market-makers, not "AI that predicts well." Frame the panel as "what is the market's mood?", never as a buy/sell signal.
When to use this skill
• Building an "event probability" / "sentiment" / "macro mood" dashboard panel • Integrating Polymarket or Kalshi probability data into any app • Anyone asks for prediction-market odds, election/Fed/geopolitics probabilities as data
What you're building (architecture in one breath)
` Polymarket Gamma API ─┐ ├─► per-source fetchers shape every market into ONE common schema Kalshi events API ────┘ (question, prob_yes, change_24h, volume_24h, source, …) │ shared taxonomy classifies each into a module (货币政策/宏观/地缘/政治/股指大宗/AI + reference group) │ aggregator: merge → group by module → cap floods → translate titles → pin a disk SNAPSHOT │ /pulse/overview (instant from snapshot; refresh = async rebuild) │ React panel: module sections + source badges + trend chart `
Discussion
Health Signals
My Fox Den
Community Rating
Sign in to rate this booster