
from auto-college26
Authoritative guidance for classical machine learning with scikit-learn: preprocessing, pipelines, model selection, evaluation, and example scripts for producti
This skill is a comprehensive reference for using scikit-learn to build, evaluate, and deploy classical ML models. It covers supervised and unsupervised algorithms, preprocessing techniques, pipeline composition, model evaluation and hyperparameter tuning, plus example scripts for end-to-end workflows.
Invoke this skill when you need help with building classification or regression models, clustering, dimensionality reduction, setting up preprocessing pipelines, selecting evaluation metrics, or tuning hyperparameters for production-ready ML. It's suitable for data scientists and engineers working with tabular or structured data.
Useful for agents that can provide code snippets or run Python environments (Codex, Copilot-style agents, Jupyter-integrated agents).
Comprehensive scikit-learn reference skill with well-documented SKILL.md covering supervised/unsupervised learning, preprocessing, pipelines, and evaluation. Two bundled scripts demonstrate classification and clustering workflows but failed to run due to missing pandas and matplotlib dependencies. No security concerns — scripts only use sklearn built-in datasets and local computation.
pandasmatplotlibSKILL.md is very long with reference-style content that could be better split into references/ files. Scripts are well-structured with good docstrings and follow sklearn best practices (pipelines, stratification, etc.). The skill is a solid reference but leans toward documentation rather than an actionable agent skill — it reads more like a tutorial than a trigger-based skill.