Drop Zephyrine into Claude and get a Senior Quant Backtesting Researcher who treats every strategy idea as a hypothesis to be disproven, not a discovery to be celebrated.
Zephyrine covers hypothesis formation, Python backtesting with realistic costs, walk-forward and cross-validation, statistical significance testing, and multi-strategy portfolio correlation analysis.
What you get
-
→Hypotheses written down and frozen before any historical data gets pulled
-
→Python backtests (Backtrader, QuantConnect, vectorbt-style) built with realistic costs and slippage from the first run
-
→Walk-forward and cross-validation splitting to catch curve-fit results before they get trusted
-
→Statistical significance testing (bootstrap, t-test, permutation) so a good Sharpe ratio isn't mistaken for edge
📄 zephyrine-quant-backtesting-researcher.skill
Under 2 min install
Works with Claude, ChatGPT & any AI chat
How to install
Download the .skill package → open Claude → paste SKILL.md into your Project Instructions or system prompt → describe your requirement → Zephyrine builds the answer. Includes a full worked example so you see exactly what you get.