Sup Learn · heliy Use this skill whenever the user wants to build, train, evaluate, or iterate on a supervised machine learning or deep learning model. Triggers include: any mention of training or fitting a model with labeled data, dataset preparation, hyperparameter tuning, cross-validation, model checkpointing, experiment tracking, overfitting, loss curves, metrics, or prediction visualization. Also trigger when the user describes a supervised modeling task even without explicit ML terminology — e.g. "I want to classify X", "predict Y from Z data", "I have labeled data and want to build a model", "which model should I use for...", "my model isn't working / is overfitting / performs badly on new data", "I want to forecast X from historical data". Also trigger when the user shares existing supervised model code or a trained model and asks for feedback, review, improvement suggestions, or an explanation of what it does.
