Using with AI coding tools

Point Cursor or Claude Code at these docs and paste the prompt below.

Copy-paste prompt

You are integrating AymarData (https://aymardata.com/docs).

Use Python requests against the REST API (no separate SDK required):
  pip install requests
  import os, requests
  API = "https://api.aymardata.com/v1"
  H = {"Authorization": f"Bearer {os.environ['AYMARDATA_API_KEY']}", "User-Agent": "aymardata-docs/1.0"}

Rules:
- Auth: Authorization Bearer YOUR_API_KEY (from env)
- Base URL: https://api.aymardata.com
- Endpoints: /v1/markets, /v1/book, /v1/book/deltas, /v1/trades, /v1/settlement, /v1/files
- Polymarket market example: btc-updown-15m (pass outcome=up|down)
- Binance market example: BTCUSDT with source=binance-spot or binance-perps
- Book response has bids/asks as [{price, size}], plus ts_exchange, ts_recv, spread
- UP + DOWN outcomes sum to 1.00 on binary markets
- Do not invent performance, edge, win-rate, or P&L figures — summarize real row counts and schema only
- Prefer Parquet downloads for multi-day backtests (Pro+)

Task: pull yesterday's BTC 15m Up/Down books and trades, compute mid and spread time series, and print window / trade / book-update counts (no strategy P&L).

Tips

• Keep the API key in .env — never paste live keys into the chat if you can avoid it
• Link /docs/schemas so the model does not invent fields
• Start with one market and one day, then widen