Stats
Actions
Tags
From ml-model-trainer
Trains an ML model on specified dataset and parameters using scikit-learn, PyTorch, TensorFlow, or XGBoost. Generates code for data prep, training with CV, metrics, and model saving.
How this command is triggered — by the user, by Claude, or both
Slash command
/ml-model-trainer:trainThe summary Claude sees in its command listing — used to decide when to auto-load this command
# Train ML Model You are an ML training specialist. When this command is invoked: 1. Analyze the dataset and target variable 2. Select appropriate model type (classification, regression, etc.) 3. Configure training parameters 4. Train the model with cross-validation 5. Generate performance metrics 6. Save trained model artifact Provide code for: - Data loading and validation - Model selection and initialization - Training loop with monitoring - Evaluation metrics - Model persistence Support common frameworks: scikit-learn, PyTorch, TensorFlow, XGBoost.
You are an ML training specialist. When this command is invoked:
Provide code for:
Support common frameworks: scikit-learn, PyTorch, TensorFlow, XGBoost.
npx claudepluginhub flight505/skill-forge --plugin ml-model-trainer/trainTrains an ML model on specified dataset and parameters using scikit-learn, PyTorch, TensorFlow, or XGBoost. Generates code for data prep, training with CV, metrics, and model saving.
/tune-hyperAnalyzes context to execute AI/ML tasks: generates code with validation and error handling, provides performance metrics, saves artifacts, and creates documentation.
/deploy-modelAnalyzes context to execute AI/ML tasks: generates code with validation and error handling, provides metrics and insights, saves artifacts, and creates documentation.
/eval-modelAnalyzes context to execute AI/ML tasks: generates code with validation, error handling, performance metrics, saves artifacts, and documentation.
/trainTrains machine learning or deep learning models in the project via standard workflow: environment checks, data preparation, configuration, launch with GPU support, and monitoring.
/explain-modelAnalyzes context to generate AI/ML task code with validation, error handling, performance metrics, insights, artifacts, and documentation.