The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill recommends installing standard, well-known libraries from the Python ecosystem, including scikit-learn, pandas, numpy, matplotlib, and seaborn, using the uv package manager.
[COMMAND_EXECUTION]: The skill provides instructional shell commands for package installation and for running the included Python scripts (scripts/classification_pipeline.py and scripts/clustering_analysis.py) to demonstrate machine learning workflows.
[DATA_EXPOSURE]: The reference documentation (references/model_evaluation.md and references/quick_reference.md) mentions the use of joblib and pickle for model persistence. While these utilities can be insecure if used on untrusted files, their inclusion here is strictly for documenting standard machine learning practices.
[DATA_EXPOSURE]: The example scripts and workflows demonstrate loading data from local CSV files using pandas.read_csv, which is the primary intended use case for a data science skill.

scikit-learn