machine-learning

Build production ML pipelines by automating end-to-end workflows from data ingestion to deployment. This skill provides structured templates, configuration schemas, and validation scripts to manage preprocessing, feature engineering, model training, and evaluation using scikit-learn and XGBoost.

Automate cross-validation and model selection by applying this skill's built-in experimentation workflows. It supports hyperparameter tuning, cross-validation, and versioning to ensure reliable model performance assessment before production deployment.

Yes, this machine-learning skill handles feature engineering and data preprocessing automatically. It automates scalable data preparation tasks as part of the end-to-end pipeline, reducing manual setup for data science projects.

Yes, you can use this for staging deployable ML artifacts after model evaluation. The skill supports exporting validated models and ensures production-readiness through reproducibility, versioning, and structured validation scripts.

Yes, you need PyYAML installed as a dependency to configure ML pipeline validation scripts. The skill relies on YAML configuration schemas to enforce reproducibility and structured pipeline definitions.

ML pipelines fail reproducibility checks when lacking structured configuration schemas and versioning. This skill resolves that by applying validation scripts and best-practice templates to enforce production-readiness across data preparation and model training.