/ml--dataset-prep

/ml--dataset-prep is a Claude Code skill in the AI & Agents section. Turns a raw dataset into a clean, well-split, leakage-free base for modeling: profiling, cleaning, train/validation/test splits and balance checks.

Author's description

Prepare a dataset for ML — cleaning, splits, leakage checks, balance, versioning

How to ask for it

/ml--dataset-prep prepare my customer dataset for training
/ml--dataset-prep check for data leakage between train and test
/ml--dataset-prep balance the classes in this imbalanced dataset

Install

curl -fsSL https://raw.githubusercontent.com/sgomez-dev/claude-skills/main/install.sh | bash

After installing with the script, type /ml--dataset-prep. Using Cursor, Windsurf or Codex? Platform guides

Demo coming soon

/ml--feature-engineeringFeature engineering for ML
Designs features for a tabular ML problem inside a leakage-safe pipeline: encodings, scaling, interactions and date-based features.
Built here
/ml--mlops-pipelineMLOps setup
Gives an ML project reproducible training, experiment tracking, a model registry and CI, sized to the team instead of a full platform.
Built here
/ml--model-deploymentDeploying an ML model
Takes a trained model to production: batch or online serving pattern, prediction API, packaging, monitoring, drift detection and rollback plan.
Built here
/ml--model-evaluationML model evaluation
Evaluates a model beyond one headline number: metrics matched to error costs, calibration, per-slice performance and error-by-error analysis.
Built here
/ml--model-trainingTraining an ML model
Trains a model methodically: a trivial baseline first, then the simplest model that could work, with cross-validation and tuning.
Built here
/ml--recommender-systemRecommender system
Builds a recommender that beats a popularity baseline: picks the approach, handles cold start and evaluates it offline.
Built here

How to ask for it

Install

More from this section