Does it provide performance metrics?

Yes, it generates comprehensive metrics including accuracy, precision, recall, Mean Squared Error (MSE), and R-squared values.

What frameworks does this skill support?

This skill primarily supports common machine learning frameworks like scikit-learn for automated model training and evaluation.

Can it handle both classification and regression?

Yes, the skill automatically analyzes your provided dataset to determine the appropriate model type based on your target variable.

How does it ensure model reliability?

The skill utilizes cross-validation techniques during the training phase to ensure the model generalizes well and minimizes overfitting.

Where is the trained model saved?

After the training process is complete, the skill saves a persisted model artifact to your local directory for future use or production deployment.

Machine Learning Model Trainer

Name: Machine Learning Model Trainer
Author: jeremylongshore

byjeremylongshore

•

884

データサイエンスとML

Trains, evaluates, and persists machine learning models using automated workflows for classification and regression tasks.

概要

This skill automates the end-to-end machine learning lifecycle within Claude Code, handling everything from initial dataset analysis to model persistence. It intelligently selects appropriate algorithms based on target variables, performs robust training with cross-validation, and generates comprehensive performance metrics like accuracy or Mean Squared Error. It is ideal for developers and data scientists who need to quickly prototype, evaluate, or optimize scikit-learn based models without writing manual boilerplate code.

主な機能

Automated model selection for classification and regression
Robust training using cross-validation techniques
884 GitHub stars
Model artifact persistence for future deployment
Detailed performance metrics generation including accuracy and R-squared
Integrated data analysis and target variable identification

ユースケース

Building regression models for price forecasting based on multi-feature datasets
Evaluating and optimizing model performance through automated hyperparameter analysis
Training customer churn prediction models using classification algorithms

概要

主な機能

Automated model selection for classification and regression
Robust training using cross-validation techniques
884 GitHub stars
Model artifact persistence for future deployment
Detailed performance metrics generation including accuracy and R-squared
Integrated data analysis and target variable identification

ユースケース

Building regression models for price forecasting based on multi-feature datasets
Evaluating and optimizing model performance through automated hyperparameter analysis
Training customer churn prediction models using classification algorithms