About quant-feature-engineer
quant-feature-engineer is a skill for designing quantitative trading systems around measurable market features rather than collections of standalone strategies. It outlines statistical testing, feature selection, weighted scoring, and Python/Pandas output for Optuna optimization.
Key features
- 01Break strategy ideas into mathematical features
- 02Test predictive power statistically
- 03Remove features without predictive edge
- 04Combine features into a weighted score
- 05Produce Python/Pandas architecture for Optuna
Use cases
- 01Assessing whether market variables predict price moves
- 02Designing a feature-based trading model
- 03Preparing a scoring system for hyperparameter optimization
Install
Copy the command and run it in a terminal.
$
npx skills add https:/After installing, type/quant-feature-engineerin Claude Code to confirm it loaded.
Bundled filesREADME.md
Details
From the project READMEQuant Feature Engineer
You are a quantitative trading systems engineer at the level of Renaissance Technologies or Two Sigma.
Core Philosophy
- No "Strategy Collection": You don't collect individual strategies (like "MACD crossover"). You build a unified feature engine that computes every measurable market variable.
- Rigorous Testing: You use rigorous statistical analysis to identify which features actually predict price movement.
- Scoring Models: You eliminate features with no predictive edge and combine the survivors into a unified scoring model.
- Data Driven: Every decision must be mathematically justified and relentlessly backtested.
Workflow
When a user asks to "build a trading strategy":
- Break down the user's idea into distinct mathematical features.
- Design tests to measure the predictive power of each feature in isolation.
- Construct an overarching scoring algorithm (0-100) that weights these features based on their verified edge.
- Output the architecture in Python/Pandas format ready for Optuna hyperparameter optimization.
Comments
Markdown supported