🎯Skills14
A collection of ML experimentation skills for Python built around skrub, scikit-learn, and skore, covering the full PyData ecosystem pipeline from data sourcing to model evaluation.
A skill for ML experimentation in Python organized around the PyData ecosystem, providing guidance on skrub, scikit-learn, and skore for data processing, model training, and experiment tracking.
A collection of 55+ ML experimentation skills for Python organized around skrub, scikit-learn, and skore within the PyData ecosystem. Skills cross-reference each other for iteration loops, sourcing strategies, test routing, and symbol lookups.
A collection of ML experimentation skills for Python organized around skrub, scikit-learn, and skore. Covers the full ML pipeline lifecycle including data sourcing, feature engineering, model evaluation, and iteration loops for 55+ AI coding agents.
A collection of 55+ ML experimentation skills for Python, organized around skrub, scikit-learn, and skore within the PyData ecosystem. Supports multiple coding agents including Claude Code, Codex, and Cursor, with cross-referencing between skills for iteration loops, sourcing strategies, and smoke tests.
Part of a collection of ML experimentation skills for Python built around skrub, scikit-learn, and skore, supporting the full ML pipeline lifecycle within the PyData ecosystem.
A skill bundle for ML experimentation in Python, built around skrub, scikit-learn, and skore, covering pipeline construction, evaluation, testing, and iterative experiment workflows in the PyData ecosystem.
Part of the Probabl AI skills collection for ML experimentation in Python, organized around skrub, scikit-learn, and skore within the PyData ecosystem, with support for 55+ coding agents including Claude Code and Codex.
A collection of ML experimentation skills for Python built around skrub, scikit-learn, and skore, covering the PyData ecosystem with cross-referencing workflows for pipeline building and testing.
Part of Probabl's ML experimentation skills organized around skrub, scikit-learn, and skore, this skill provides smoke testing patterns for machine learning pipelines in the PyData ecosystem with support for 55+ coding agents.
A collection of 55+ ML experimentation skills for Python organized around skrub, scikit-learn, and skore, supporting the broader PyData ecosystem. Skills cross-reference each other and support multiple agents including Claude Code, Codex, Cursor, Gemini CLI, and Mistral Vibe.
Sources the next ML experiment by walking report.diagnosis() on the previous skore report and converting every actionable finding into a Backlog row. Part of an ML experimentation skill collection for Python using skrub, scikit-learn, and skore.
Skill
Skill