tidymodels
- 13 skills
- 0 followers
- 6 hours ago last updated
- ▌
- ▌ Add Model Engine · tidymodelsAdd tidypredict support for a new parsnip engine of an already-supported model type. Use when a user wants an existing tidymodels model type to work with an additional engine (e.g. "add the glm engine to linear_reg()", "support partykit in rand_forest()"). This is the lighter-weight of the two model-support skills. If the engine's fitted object is a class tidypredict does not yet parse, use the add-model-type skill first.
- ▌ Tidy Add Step Argument · tidymodelsGuide for adding a new argument to an existing recipes step or check. Use when a user asks to add an argument/parameter to a `step_*()` or `check_*()` function, covering the constructor, `prep()`, backwards compatibility with previously saved recipes, documentation, tests, and NEWS.
- ▌ Types Check · tidymodelsValidate function inputs in R using a standalone file of check_* functions. Use when writing exported R functions that need input validation, reviewing existing validation code, or when creating new input validation helpers.
- ▌ Create Skill · tidymodelsGuide for creating new Claude Code skills. Use when you need to create a new skill to package expertise or workflow into a reusable capability that Claude can automatically invoke.
- ▌ Detect Metrics · tidymodelsDetect and list all metric functions in the yardstick package. Use when a user asks to find, list, or identify all metrics in the package.
- ▌ Tidy Deprecate Function · tidymodelsGuide for deprecating R functions/arguments. Use when a user asks to deprecate a function or parameter, including adding lifecycle warnings, updating documentation, adding NEWS entries, and updating tests.
- ▌ Tidymodels · tidymodels bundleBuild machine learning models using tidymodels for tabular data using proper data spending, resampling, and validation practices. Covers train/test splitting, cross-validation, feature engineering, model tuning, and evaluation. Use when building predictive models, comparing algorithms, or when users mention machine learning, model training, or prediction tasks.
- ▌ Add Recipe Step · tidymodels bundleCreate a new preprocessing step for the recipes package following tidymodels conventions
- ▌ Add Parsnip Model · tidymodels bundleCreate entirely new model specifications for the parsnip package. Use when creating a fundamentally new model type (like linear_reg, boost_tree) with its constructors, registration, and engine implementations. For adding engines to existing models, use add-parsnip-engine instead.
- ▌ Add Parsnip Engine · tidymodels bundleAdd new computational engines to existing parsnip models. Use when connecting an existing parsnip model (linear_reg, boost_tree, etc.) to a new computational backend or R package.
- ▌ Add Dials Parameter · tidymodels bundleGuide for creating new dials parameters for hyperparameter tuning. Use when a developer needs to define custom tuning parameters for models, recipes, or workflows, including quantitative parameters (continuous/integer), qualitative parameters (categorical), parameters with transformations, and data-dependent parameters requiring finalization.
- ▌ Add Yardstick Metric · tidymodels bundleGuide for creating new yardstick metrics. Use when a developer needs to extend yardstick with a custom performance metric, including numeric, class, probability, ordered probability, survival (static, dynamic, integrated, linear predictor), and quantile metrics.