How to use
- Copy the installation command and review the source package before installing it in your own agent environment.
- Check the source document for required tools, credentials and supported hosts.
- Describe your input and desired deliverable; review the output against the source material.
npx skills add https://github.com/crawlora-org/crawlora-skills --skill prediction-markets-researchBefore you start
- Installation does not include a model subscription, API allowance or permission to access your files.
- Repository stars and installation counts describe activity, not an independent quality or security test.
Rendered from the source repository. Headings, examples, code, tables, links, and referenced images are preserved.
Prediction markets research
Pull live and historical odds, order books, and forecast questions from Polymarket, Kalshi, and Metaculus as normalized JSON — no scraping market-maker sites or parsing raw order-book blobs.
When to use this skill
- "What does the market think will happen with <event>?" / "current odds for …"
- "Show me the order book / spread / price history for this market."
- "What are the top trending prediction markets right now?"
- "What's the community forecast (Metaculus) for <question>?"
- Election, macro, sports, or crypto-outcome forecasting research.
Setup (one-time)
- Get a free Crawlora API key (2,000 credits/mo, no card) at https://crawlora.net.
- Set
CRAWLORA_API_KEYin the environment before running the helper. - The helper reads
CRAWLORA_API_KEYfrom the environment and sends requests tohttps://api.crawlora.net/api/v1. Missing/invalid key →401.
How it works
- Polymarket —
/polymarket/searchor/polymarket/eventsto find an
event; /polymarket/event/{slug} for detail (nested markets); /polymarket/market/{id} for one market; then token-level pricing via /polymarket/token/{token_id}/price|midpoint|orderbook|spread|price-history (or the batched POST /polymarket/tokens/prices etc. for up to 25 at once). /polymarket/leaderboard and /polymarket/dashboards/macro cover traders and macro events.
- Kalshi —
/kalshi/events//kalshi/marketsto browse;/kalshi/event/{event_ticker}
or /kalshi/market/{ticker} for detail; /kalshi/market/{ticker}/history for candlesticks, /kalshi/market/{ticker}/orderbook for depth, /kalshi/trades for recent fills. /kalshi/historical/* covers settled (closed) markets.
- Metaculus —
/metaculus/questionsto browse;/metaculus/question/{id}
for detail; /metaculus/question/{id}/forecasts for the current community aggregate, /forecast-history for how it moved over time.
Full endpoint list, methods, and params: `reference/endpoints.md`.
Calling the API
# Polymarket:
scripts/crawlora.sh /polymarket/search q="fed rate cut" | jq '.'
scripts/crawlora.sh /polymarket/event/will-the-fed-cut-rates | jq '.'
# Kalshi:
scripts/crawlora.sh /kalshi/markets | jq '.data'
scripts/crawlora.sh /kalshi/market/INXD-24DEC31-T5000/history | jq '.'
# Metaculus:
scripts/crawlora.sh /metaculus/questions | jq '.data'
scripts/crawlora.sh /metaculus/question/12345/forecasts | jq '.'Use scripts/crawlora.sh for all requests; it keeps the API key out of command-line arguments.
Endpoint reference
See `reference/endpoints.md` for every Polymarket, Kalshi, and Metaculus endpoint this skill uses.
Examples
- Cross-platform odds check:
/polymarket/searchand/kalshi/markets
for the same real-world event, compare implied probabilities.
- Market momentum:
/kalshi/market/{ticker}/historyor
/polymarket/token/{token_id}/price-history plotted over time to see how sentiment shifted.
- Forecast vs. market:
/metaculus/question/{id}/forecasts(community
aggregate) alongside the matching Polymarket/Kalshi market price.
Notes & limits
- Credits / pay-on-success: billed only on
2xx; free tier 2,000 credits/mo.
Key at https://crawlora.net.
- Public, credential-free data only — no trading, no order placement;
read-only market data. This is not financial advice.
- Security: key lives in
CRAWLORA_API_KEYonly — never hardcode, query-param, or commit it. - Batch endpoints (
/polymarket/tokens/*) accept up to 25 ids per call —
chunk larger lists.



