Energizados

Generates a complete experiment results report from training pipeline outputs. Includes a phase-by-phase comparison table, AUC evolution analysis, technical insights, prioritized next steps, and a business-friendly section with an operational impact simulator. Trigger: When the user says "generate results", "experiment results", "create experiment report", "results report", "experiment analysis", "generate _results.md".

Design and generate a complete set of ML training experiments for an Energizados project. Creates _experiments.md roadmap + all YAML config files following the phased experiment pattern (Baselines → Sampling → Feature Engineering → Encoding → Selection → Tuning → Calibration → Ensemble). Trigger: When the user says "new experiments", "create experiments", "nuevos experimentos", "crear experimentos", "experiment design", "experiment roadmap", "set up experiments".

Run a full Energizados training experiment (validate → ETL → train) and surface the key metrics from the JSON report. Use when you want to kick off a pipeline run and see results.

Scaffold a new ETL block for config/etl.yaml. Guides through name, mode (concat/merge/incremental), inputs, outputs, and dependencies. Produces valid YAML ready to paste.