feature-engineering

Name: feature-engineering
Availability: InStock
Author: agiprolabs

Generate predictive features from time-series market data for trading models.

266|54|Updated Mar 11, 2026

Search Tags:#machine learning #feature engineering #time series #data processing #quantitative finance #trading

Ready to run

npx skills add https://github.com/agiprolabs/claude-trading-skills --skill feature-engineering-agiprolabs

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: feature-engineering
Source: https://github.com/agiprolabs/claude-trading-skills/tree/main/skills/feature-engineering
Command: npx skills add https://github.com/agiprolabs/claude-trading-skills --skill feature-engineering-agiprolabs

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pandas, numpy, scipy, httpx, statsmodels, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the complex and time-consuming process of creating high-quality features from raw market data, essential for building accurate machine learning trading models.

Core Features & Use Cases

Comprehensive Feature Generation: Computes over 25 features across price, volume, technical indicators, and time-based patterns.
Stationarity Testing: Automatically tests features for stationarity using the ADF test, flagging non-stationary features that can harm model performance.
Use Case: Generate a robust set of features from historical OHLCV data for a Solana token, ready to be fed into a predictive model for signal classification or price forecasting.

Quick Start

Use the feature-engineering skill to build features from the provided OHLCV data.

Frequently Asked Questions about feature-engineering

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I generate machine learning features from OHLCV market data?▼

Generate predictive features from OHLCV market data by computing over 25 price, volume, technical, and time-based features. This prepares raw time-series data for machine learning trading models.

Why does stationarity testing matter when building time-series features for quantitative trading?▼

Stationarity testing identifies non-stationary features that can harm predictive model performance. The process uses the ADF test from statsmodels to flag these features, ensuring only stable data is used.

Does this feature engineering workflow require pandas and statsmodels?▼

Yes, the feature engineering workflow requires pandas, numpy, and scipy, while statsmodels is used optionally for performing ADF stationarity tests to validate feature quality.

What's the best way to automate time-series feature generation for trading models?▼

Automate time-series feature generation by applying scripts that calculate technical indicators and perform stationarity checks automatically, producing a quality report for your predictive trading models.