Pulls market data for a symbol, normalizes OHLCV candles into relative values (price changes as percentages, volume as z-scores), then indexes them as 64-dimension vectors with HNSW for fast similarity search. You'd use this before running pattern detection or comparing price action across different symbols and timeframes. The normalization step is what makes this more than a simple data fetch: it converts absolute prices into relative movements so a 2% swing in a penny stock looks the same as a 2% swing in a blue chip. Stores everything in the memory_store namespace and builds the vector index in one pass. If you're doing technical analysis or building a pattern recognition pipeline, this is your entry point.
npx skills add https://github.com/ruvnet/ruflo --skill market-ingest