Explore skills

Assess whether a training window can be extended by adding a new data source (e.g., CRM-only features to bypass behavioral data limitations). Use when: (1) the user asks "can we train on more data?", "how far back can we go?", "can we extend the training window?", or "our model only has N months of data", (2) a multi-output model has different effective training windows per output due to dynamic l

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