Build automated machine learning pipelines with feature engineering, model selection, and hyperparameter tuning. Use when automating ML workflows from data preparation through model deployment. Trigger with phrases like "build automl pipeline", "automate ml workflow", or "create automated training pipeline".
6.4
Rating
0
Installs
Machine Learning
Category
Well-structured AutoML pipeline skill with clear prerequisites, multi-step workflow, and proper separation of concerns. The description effectively communicates when and how to invoke the skill. Strong task knowledge is indicated through comprehensive steps covering data validation, feature engineering, model selection, and deployment, with references to implementation details in external files. Structure is clean with a concise SKILL.md that indexes detailed content in references/ and scripts/. Novelty is moderate - while AutoML pipelines are valuable, many AutoML libraries already provide high-level automation, so the incremental value over calling Auto-sklearn/TPOT/PyCaret directly is somewhat limited. The skill is most useful for standardizing the end-to-end workflow with validation, deployment artifacts, and reporting rather than solving a problem a CLI agent couldn't tackle, though it does reduce token cost for repeated ML pipeline tasks.
jeremylongshore
Skill Author
Loading SKILL.md…
