Model Hyperparameter Tuning

This one gives Claude a systematic approach to hyperparameter tuning when you're trying to squeeze better performance out of your models. It covers when to reach for tuning (beyond baseline configs, comparing parameter combinations, finding that bias-variance sweet spot) and walks through different tuning methods. Comes from aj-geddes' useful-ai-prompts collection, which has 245 stars on GitHub and passes the standard security audits. The skill is pretty straightforward about scope: it's for optimizing neural networks, tree models, and ensembles when you need to improve generalization. If you're tired of manual parameter tweaking or want Claude to help structure your search process, this is a solid starting point.