AI options flow signals as vectorbt features — open source Claude Code investment skills

[tellmefrankie]

Hey vectorbt community,

Fast backtesting and signal analysis — sharing an open source project that generates options flow signals that could feed vectorbt strategies.

AI Investment Skills:

• Options flow scanner — sector ETF P/C anomaly detection with volume quality filtering
• Price monitor — stop-loss/take-profit with Telegram alerts
• Daily AI briefing

vectorbt integration angle:
The scanner generates timestamped P/C anomaly signals. Feeding these into vectorbt as a signal series would let you backtest: "does elevated filtered P/C precede sector drawdowns?" The filtering (removing lottery ticket volume) is what makes the signal worth backtesting — raw P/C is too noisy.

Example signal:
XLI P/C hit 5.32 (normal: 0.5–1.2). After filtering 98% lottery ticket volume on CEG: adjusted P/C = "extremely bearish." Raw = "neutral." That divergence is the signal worth testing.

Open source:
→ https://github.com/tellmefrankie/ai-investment-skills

Anyone here backtesting options flow signals with vectorbt?