A Claude Code skill providing comprehensive guidance for Google Gemini AI API integration in TypeScript/JavaScript and Python.
claude skill install google-gemini.skillclaude skill install https://github.com/ItachiDevv/google-gemini-skillCopy the google-gemini folder to your Claude skills directory:
- Windows:
%USERPROFILE%\.claude\skills\ - macOS/Linux:
~/.claude/skills/
This skill triggers when working with:
- Gemini 3 models (
gemini-3-pro-preview,gemini-3-flash-preview,gemini-3-pro-image-preview) - Structured JSON outputs with schema validation
- Function calling and tool use
- Multimodal content (images, video, PDF)
- Thinking modes and configuration
- Streaming responses
- Image generation and editing
| Feature | Description |
|---|---|
| Quick Start | Basic generation in TypeScript and Python |
| Models | Model selection guide with pricing |
| Structured Output | JSON schema validation with Zod integration |
| Thinking Levels | Control reasoning depth (low/medium/high/minimal) |
| Multimodal | Images, PDFs, video with resolution control |
| Function Calling | Tool declarations and response handling |
| Thought Signatures | Cross-turn reasoning context |
| Built-in Tools | Google Search, URL Context, Code Execution |
| Image Generation | 4K generation with grounding support |
| Streaming | Real-time response streaming |
| Migration | Gemini 2.5 to 3 migration guide |
google-gemini/
├── SKILL.md # Main skill file
└── references/
├── gemini3-full-docs.md # Complete API documentation
└── migration-guide.md # Migration from Gemini 2.5
Once installed, the skill automatically activates when you ask Claude Code to:
- "Create a Gemini API integration"
- "Add structured JSON output to my Gemini call"
- "Implement function calling with Gemini"
- "Migrate from Gemini 2.5 to 3"
- "Add image analysis using Gemini"
MIT
Issues and PRs welcome!