ML Model Training

Data Preparation: Cleaning, encoding, normalization
Feature Engineering: Creating meaningful features
Model Selection: Choosing appropriate algorithms
Hyperparameter Tuning: Optimizing model settings
Validation: Cross-validation and evaluation metrics
Deployment: Preparing models for production

This is a straightforward reference guide that walks through the standard ML training pipeline, from data prep through deployment. It covers the usual suspects: feature engineering, hyperparameter tuning, cross-validation, plus a quick reference of common algorithms across regression, classification, clustering, and neural networks. It's more of a checklist than a deep dive, so expect high-level phases rather than implementation details. Useful if you want Claude to structure a training workflow or need a reminder of what steps you're missing, but you'll still need to know your scikit-learn or PyTorch to actually build anything. Think of it as scaffolding for ML conversations rather than a tutorial.

GitHub stars: 317
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add aj-geddes/useful-ai-prompts --skill 'ML Model Training' --agent claude-code

Installs into .claude/skills of the current project.

Files

ML Model Training

Training machine learning models involves selecting appropriate algorithms, preparing data, and optimizing model parameters to achieve strong predictive performance.