when-debugging-ml-training-use-ml-training-debugger

This skill provides a specialized workflow for developing, training, and deploying machine learning models, supporting architectures like CNNs and RNNs. Use it when you need to build a new model, require training, or are preparing for production deployment. It handles the full pipeline from development to generating deployment packages and evaluation reports.

This skill provides a structured workflow for developing, training, and deploying machine learning models, supporting architectures like CNNs and RNNs. Use it when you need to build a new model, retrain an existing one, or prepare a model for production deployment. It handles the full pipeline from training with frameworks like TensorFlow/PyTorch to generating deployment-ready packages and evaluation reports.

This skill helps debug and optimize machine learning training issues like loss divergence, overfitting, and slow convergence. It provides systematic diagnosis, identifies root causes, and delivers fixes with performance comparisons. Use it when facing training failures, poor validation performance, or needing optimization recommendations.

This skill provides a production-tested setup for Content Collections, a TypeScript-first tool that transforms Markdown/MDX files into type-safe data collections with Zod validation. Use it when building blogs, documentation sites, or content-heavy Vite + React applications to ensure type safety and automatic content validation. It covers everything from Vite plugin configuration and MDX compilation to deployment optimization and schema validation.