{"enrichment":{"faq":[{"a":"ml-model-training covers training workflows across all three frameworks. For scikit-learn, use estimators like LogisticRegression or RandomForest with .fit(). PyTorch requires manual training loops with loss computation and backpropagation. TensorFlow offers high-level APIs via Keras. The skill emphasizes proper data splitting, feature scaling, and validation to ensure robust models across frameworks.","q":"How to train machine learning models with scikit-learn, PyTorch, or TensorFlow?"},{"a":"ml-model-training addresses overfitting through regularization (L1/L2), dropout layers, and early stopping. Monitor validation loss during training\u2014if it diverges from training loss, your model is overfitting. Reduce model complexity, increase training data, or apply data augmentation. Early stopping in PyTorch halts training when validation metrics plateau, preventing unnecessary epochs that worsen generalization.","q":"What causes overfitting in neural networks and how do I fix it?"},{"a":"ml-model-training teaches GridSearchCV and RandomizedSearchCV for systematic hyperparameter search in scikit-learn. Use k-fold cross-validation to assess stability across data splits. For PyTorch/TensorFlow, manually loop over parameter combinations or use Optuna. Cross-validation prevents overfitting to a single train-test split and provides confidence intervals on performance estimates.","q":"How do I perform hyperparameter tuning and cross-validation?"},{"a":"ml-model-training emphasizes splitting data before any preprocessing to avoid leakage. Fit scalers and encoders only on training data, then transform test data. Handle class imbalance via stratified splits, resampling, or class weights. Never use test information during feature engineering or hyperparameter tuning. Proper train-test-validation separation ensures honest performance estimates.","q":"How should I prepare data and prevent data leakage in ML?"},{"a":"ml-model-training covers appropriate metrics: accuracy for balanced data, F1-score or ROC-AUC for imbalanced classification, MAE/RMSE for regression. Use confusion matrices to diagnose false positives/negatives. Always evaluate on held-out test sets, not training data. Report metrics with confidence intervals from cross-validation to demonstrate reproducibility and statistical significance.","q":"What are the best practices for evaluating model performance?"},{"a":"ml-model-training addresses convergence by checking learning rate, batch size, and gradient flow. Underfitting occurs when both training and validation loss remain high\u2014increase model capacity, train longer, or reduce regularization. Use gradient clipping for exploding gradients. Monitor loss curves during training; sudden spikes suggest learning rate too high, while flat curves suggest too low.","q":"How do I debug convergence issues and underfitting in neural networks?"}],"shadow_tags":["supervised-learning","model-evaluation","data-leakage-prevention","regularization-techniques","imbalanced-datasets","training-pipeline","reproducibility-seeds","performance-metrics"],"summary_rewrite":"Build and evaluate machine learning models across scikit-learn, PyTorch, and TensorFlow with a structured workflow covering data preparation, feature engineering, model selection, and performance assessment. Learn to handle common pitfalls like data leakage, class imbalance, overfitting, and hyperparameter tuning mistakes through best practices and code examples."},"files":[{"bytes":6938,"path":"plugins/ml-model-training/skills/ml-model-training/SKILL.md","sha256":"4641463a8341bd5ee8aa06b1ee9d4d6153e52eee175b8cfcdc001a94ce054a0b","url":"https://skillfed.io/files/secondsky/claude-skills/ml-model-training/ba77be14/SKILL.md"}],"id":"secondsky/claude-skills/ml-model-training","links":{"html":"https://skillfed.io/secondsky/claude-skills/ml-model-training","md":"https://skillfed.io/secondsky/claude-skills/ml-model-training.md","repo":"https://github.com/secondsky/claude-skills"},"meta":{"agents_supported":[],"first_seen":"2026-07-28","forks":29,"language":"TypeScript","last_updated":"2026-07-25","license":"MIT","name":"ml-model-training","publisher":"secondsky","stars":196},"relations":{"similar":[{"id":"tondevrel/scientific-agent-skills/xgboost-lightgbm"},{"id":"pluginagentmarketplace/custom-plugin-data-engineer/machine-learning"},{"id":"tondevrel/scientific-agent-skills/scikit-learn"},{"id":"aj-geddes/useful-ai-prompts/ml-model-training"},{"id":"personamanagmentlayer/pcl/ml-expert"},{"id":"synthetic-sciences/openscience/mlflow"},{"id":"Orchestra-Research/AI-Research-SKILLs/mlflow"},{"id":"OpenLAIR/dr-claw/mlflow"},{"id":"jaechang-hits/SciAgent-Skills/scikit-learn-machine-learning"},{"id":"beita6969/ScienceClaw/scikit-learn-ml"}]},"slug":{"owner":"secondsky","repo":"claude-skills","skill":"ml-model-training"},"version":"ba77be14"}