google-gemma

Trigger this skill when building applications with Gemma or for general knowledge inquiries related to Gemma models (e.g. prompt structure, capabilities). Covers model selection, development workflows, and deployment best practices.

Trigger this skill when the user wants to train, fine-tune, or adapt Gemma models (e.g. SFT, DPO, RLHF, Reward Modeling) on local hardware. Covers TRL, Unsloth, dataset preparation, validation, and GGUF/LiteRT conversion.

Authoring, editing, and maintaining the Google DeepMind Gemma documentation website built with Zensical. Use when adding or updating documentation pages, modifying model/framework metadata, creating tutorials with executable notebooks, styling with design…