Market Ingest

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.

skills.sh installs: 726
GitHub stars: 81.4K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add ruvnet/ruflo --skill market-ingest --agent claude-code

Installs into .claude/skills of the current project.

Files

Market Ingest

Fetch market data for a symbol, normalize to OHLCV vectors, and store them by symbol and date. Ingest is read-only analysis: nothing here places or sizes an order.

When to use

When you need to ingest raw market data (price and volume) for a symbol and prepare it for pattern detection and similarity search. This is the first step before running pattern detection or comparison.