Feature Engineering

Helps Claude understand and apply feature engineering techniques when you're prepping data for machine learning. You get guidance on encoding categorical variables, normalizing different scales, handling skewed distributions, and creating domain-specific features based on your business context. It's from aj-geddes's useful-ai-prompts repo, which has 245 GitHub stars and passes all three security audits. Most useful when you're past the raw data stage and need to actually improve model performance through better feature work. The skill covers when to use different techniques rather than just listing transformations, which makes it more practical than a simple reference.

GitHub stars: 317
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add aj-geddes/useful-ai-prompts --skill 'Feature Engineering' --agent claude-code

Installs into .claude/skills of the current project.

Files

Feature Engineering

Overview

Feature engineering creates and transforms features to improve model performance, interpretability, and generalization through domain knowledge and mathematical transformations.

When to Use

When you need to improve model performance beyond using raw features
When dealing with categorical variables that need encoding for ML algorithms
When features have different scales and require normalization
When creating domain-specific features based on business knowledge
When handling skewed distributions or non-linear relationships
When preparing data for different types of ML algorithms with specific requirements