Scikit-learn plugins

Automate full ML lifecycle: data preparation, model training, hyperparameter tuning, experiment tracking, and production deployment using multi-agent orchestration for MLOps workflows.

Instantly access 149 ready-to-use agent skills for scientific research, data analysis, machine learning, bioinformatics, and technical writing across domains. Execute experiments, analyze sequences, run simulations, generate reports, and automate lab workflows without writing boilerplate.

Run K-means, DBSCAN, and hierarchical clustering on datasets using scikit-learn, generating group identifications, metrics, visualizations, and documented code artifacts with validation and error handling.

Run hyperparameter grid, random, or Bayesian searches on ML models using scikit-learn or Optuna. Generates validated Python code, returns performance metrics, and saves tuning artifacts with documentation.

Profile datasets for quality issues, design A/B experiments, scaffold scikit-learn/XGBoost pipelines, and evaluate models with bias audits, all with documentation-ready model cards.