A comprehensive collection of expert AI Agent Skills for Google Gemini, featuring a powerful CLI to convert and optimize Claude Code agents for the Gemini ecosystem.
## Gemini Agent Skill A comprehensive collection of expert AI Agent Skills for Google Gemini. ## Gemini to Gemini Converter CLI A CLI tool to convert Anthropic Claude "Code" configurations (Plugins, Agents, Skills) into Google Gemini Agent Skills. This tool uses **gemini-2.0-flash-exp** (via the API) to intelligently parse, refine, and restructure your existing agent definitions into the format required by the Gemini Agent Playground. ## Why this Tool? Claude Code has offered powerful agents and plugins for a while, but until now, there was no easy way to access these capabilities within the Gemini ecosystem. This repository solves that problem by converting existing configurations so you can use them with Gemini immediately. This is made possible by the new **Gemini Agent Skill** feature, which empowers Gemini to handle complex tasks just like other advanced AI coding tools. You can read the [official documentation here](https://geminicli.com/docs/cli/skills/). ## Credits This project builds upon the amazing work done by the [VoltAgent](https://github.com/VoltAgent/awesome-claude-code-subagents) team. They created the original collection of Claude Code subagents, and we want to give them full credit for these definitions. My goal is to take these proven agent patterns and optimize them for even greater efficiency on Gemini. ## What's Next? I am dedicated to optimizing these agents to be fully native and highly efficient within the Gemini ecosystem. Currently, I am developing an advanced configuration system that utilizes [Project Mitra](https://github.com/saeed-vayghan/mitra). This will unlock deeper customization and more structured control over your Gemini Agent Skills. ## Using Gemini Agent Skills Once you have generated your skills, you can interact with them directly in the Gemini CLI. **How to use:** ```bash # Install [email protected] npm install -g @google/[email protected] # Confirm version gemini --version
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.