Gemma, a family of open models, are lightweight, remarkably capable, and have a wonderful "tunability" that makes them perfect for personal projects and enterprise-grade applications alike. But as the ecosystem grew, I found myself asking the same questions over and over:
To solve this, we put together a living repository called (which we're releasing!). It's a curated, structured collection of developer
gemma-skills
Let's take a walk through what's inside!
gemma-dev
At the center of the repository is our first major skill: gemma-dev. It's a skill file (
SKILL.md
) that serves as a blueprint. It's designed for agents to find what are the latest capabilities, model sizes, good practices, and resources to build with Gemma.The Gemma ecosystem moves fast, with new models, libraries, and best practices emerging constantly. For developers using foundational LLMs like Gemini, keeping assistant workflows perfectly synced with these rapid releases is a common challenge. Because foundational models are trained on vast, fixed datasets, they don't automatically inherit the day-one nuances of a rapidly evolving framework. This can manifest in a few typical development scenarios:
The gemma-skills repository bridges this gap. By providing "live" best practices and structured skill documents directly into your development workflow, we ensure your AI assistant has immediate access to the most current, efficient, and reliable implementation patterns available today.
These skills are designed to be entirely harness-agnostic. They integrates into any developer workflow or agentic tool, from Gemini to Claude. To get started quickly, whether you're leveraging these as clean templates or equipping an AI assistant, the Antigravity CLI (agy
) is available as a straightforward way to interact with the repository.
agy
in your terminal. From there, you can query the agent in plain English regarding the Gemma ecosystem. Since agy
leverages the gemma-dev
skill, you'll receive the most precise and up-to-date technical guidance available. Example Prompt:
Build a smart home simulator using Gradio and Gemma, use direct voice input to Gemma to minimize the latency for controlling the home.
Keep in mind that while the demo is functional, running a full-precision model via transformers can feel a little sluggish. For a better experience and optimal performance, I typically suggest serving a quantized version through a backend like Ollama or LM Studio, as shown in this next example.
Example Prompt:
Build a terminal app that translates a user's natural language input into an ascii art animation, using Gemma and LM Studio backend.
I invite you to dive deeper into the vast world of Gemma and its surrounding ecosystem. You'll surely discover it's an incredibly rewarding journey.
*Thank you for reading. If you build something cool with *
gemma-skills
, let me know! Happy building!