What is the benefit of using Gemini with Claude Code?

Gemini provides a massive 1-million-token context window and native multimodal analysis, allowing you to process entire codebases and images that exceed standard Claude limits.

Can I generate images with this skill?

Yes, the integrated Nano Banana extension allows for image generation, editing, icon creation, and photo restoration directly within your terminal workflow.

Does this require a separate API key?

Yes, you will need a Google Gemini API key from Google AI Studio configured in your environment variables as GOOGLE_API_KEY.

Which Gemini models are supported?

The skill supports Gemini 2.5 Flash for speed, 2.5 Pro for complex tasks, 2.5 Flash-lite for efficiency, and 3.0 Deep Think for advanced reasoning.

How do I trigger the Gemini skill?

You can activate it by mentioning 'Gemini', requesting image analysis, or asking for tasks involving very large documents or codebase-wide reviews.

Google Gemini AI & Multimodal Tools

Name: Google Gemini AI & Multimodal Tools
Author: dev-jelly

bydev-jelly

Data Science & ML

Integrates Google Gemini's multimodal analysis, massive context processing, and image generation capabilities directly into Claude Code.

About

This skill empowers Claude Code with Google's most advanced Gemini models, offering a 1-million-token context window for full-codebase analysis and native multimodal support for processing images and videos. It bridges the gap between text-based coding and visual requirements through the Nano Banana extension, which handles image creation, editing, and restoration. Whether you're debugging via screenshots, analyzing massive documentation, or needing high-speed inference for repetitive tasks, this integration provides the versatility and scale required for modern software development.

Key Features

Access to Gemini 2.5 Flash, Pro, and 3.0 Deep Think models
Smart model selection logic based on task complexity and speed requirements
0 GitHub stars
Native multimodal processing for screenshots, diagrams, and video analysis
Integrated Nano Banana extension for image generation and photo restoration
1M+ token context window for massive codebase and document analysis

Use Cases

Debugging UI/UX issues by providing screenshots for direct visual analysis
Analyzing entire project architectures or massive PDF documentation sets
Generating and editing project assets like icons, diagrams, and UI mockups

About

Key Features

Access to Gemini 2.5 Flash, Pro, and 3.0 Deep Think models
Smart model selection logic based on task complexity and speed requirements
0 GitHub stars
Native multimodal processing for screenshots, diagrams, and video analysis
Integrated Nano Banana extension for image generation and photo restoration
1M+ token context window for massive codebase and document analysis

Use Cases

Debugging UI/UX issues by providing screenshots for direct visual analysis
Analyzing entire project architectures or massive PDF documentation sets
Generating and editing project assets like icons, diagrams, and UI mockups