Gemma 4 Agent Skills
# Gemma Skills for AI Edge Gallery This repository contains useful skills for Gemma 4 in Google AI Edge Gallery. The goal is simple: give on-device mobile LLMs practical capabilities through reusable skill packages that are easy to install, test, and extend. ## What This Project Provides - Curated skills for real-world use cases such as legal guidance, coaching, recommendations, and web-grounded search - Support for both skill types used by AI Edge Gallery: - Text-based skills (SKILL.md only) - JavaScript skills (SKILL.md plus scripts/index.html running in a sandboxed hidden webview) - A structure that is easy to contribute to and review ## Disclaimer These skills are provided for demonstration and educational purposes only. They are intended to showcase implementation patterns and practical possibilities for Gemma 4 in Google AI Edge Gallery. Actual behavior, quality, and outputs may differ based on model version, platform implementation, device environment, and runtime configuration. Do not treat these skills as guarantees of identical behavior across systems. **Always validate and test thoroughly in your own environment before relying on any skill for critical, safety-sensitive, legal, financial, medical, or production use.** ## Skill Format Each skill lives in its own folder and follows one of these patterns: 1. Text-based skill - SKILL.md 2. JavaScript skill - SKILL.md - scripts/index.html - Optional assets/ for webviews and UI files ## Available Skills The complete and up-to-date list is maintained in [CATALOG.md](CATALOG.md). | Skill | Folder | Type | Requires Secret | Description | | --- | --- | --- | --- | --- | | Fire Service Advisor | [skills/fire-service-advisor](skills/fire-service-advisor) | Text | No | Emergency triage, tactical decision support, and incident command guidance for fire-related incidents. | | Gemini Search | [skills/gemini-search](skills/gemini-search) | JavaScript | Yes | Live web search via Gemini grounding wi
Google's AI-powered research notebook that ingests your documents and becomes an expert on your content. Generates audio overviews, study guides, FAQs, and interactive discussions from uploaded sources.
Google DeepMind's experimental AI agent that can navigate websites, fill forms, and complete multi-step browser tasks autonomously. Uses Gemini's multimodal understanding to interact with web interfaces.
Google DeepMind's universal AI assistant prototype that can see, hear, and respond in real-time through your device camera and microphone. Demonstrates the future of multimodal AI interaction.
Google Cloud's enterprise platform for building, deploying, and managing AI agents powered by Gemini. Supports multi-agent orchestration, tool integration, and enterprise governance.
Gemini's agentic research capability that autonomously browses the web, synthesizes information from dozens of sources, and produces comprehensive research reports on any topic.
Interactive coding and content creation agent that generates, previews, and iterates on code, documents, and interactive applications in a side panel. Supports HTML/CSS/JS, Python, and more.