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.