Which Gemini models does this skill support?

The skill supports Gemini 3.1 Flash (default for speed and features), Gemini 3 Pro (for high-quality deliverables), and Gemini 2.5 Flash (for stable production generation).

What is 'Thinking Mode' in image generation?

Thinking mode allows the Gemini model to process complex prompts involving multiple subjects or specific spatial arrangements more effectively before generating the final image.

Can I edit my own existing images?

Yes, the skill allows you to provide paths to local images as references for editing, modification, or as stylistic guides for new generations.

Does this skill support high-resolution output?

Yes, it supports multiple resolutions including 512px, 1K, 2K, and 4K, along with a wide variety of aspect ratios from 1:1 to 21:9.

How does the multi-turn editing work?

The skill maintains a session state that allows you to give follow-up instructions like 'make it darker' or 'add a cat' to refine the previous output without restarting.

Gemini Image Generator

Name: Gemini Image Generator
Author: christian-schlichtherle

bychristian-schlichtherle

0•

Design Tools

Generates and refines professional-grade images using the Gemini API directly within your development environment.

This skill integrates Gemini's advanced image generation capabilities into Claude Code, allowing developers to create, edit, and iteratively refine visuals through natural language commands. It supports high-resolution outputs up to 4K, multiple aspect ratios, and specialized features like 'thinking' modes for complex compositions and Google Search grounding for real-world accuracy. With built-in support for multi-turn editing sessions and reference image inputs, it streamlines the process of creating assets for applications, documentation, and mockups without leaving the terminal.

Key Features

01Support for reference images and image-to-image editing tasks.

020 GitHub stars

03Text-to-image generation using Gemini 3.1 Flash, Pro 3, and Flash 2.5 models.

04Google Search grounding for accurate rendering of real-world locations and brands.

05Multi-turn conversational editing for iterative image refinement.

06Automatic thinking mode detection for complex spatial and stylistic prompts.

Use Cases

01Creating high-quality marketing or documentation visuals directly from the CLI.

02Iteratively refining project graphics using natural language instructions.

03Generating UI placeholders and visual assets during frontend development.

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add christian-schlichtherle/cs7-claude-plugins generate-image

For use in Claude.ai and ChatGPT

Key Features

01Support for reference images and image-to-image editing tasks.

020 GitHub stars

03Text-to-image generation using Gemini 3.1 Flash, Pro 3, and Flash 2.5 models.

04Google Search grounding for accurate rendering of real-world locations and brands.

05Multi-turn conversational editing for iterative image refinement.

06Automatic thinking mode detection for complex spatial and stylistic prompts.

Use Cases

01Creating high-quality marketing or documentation visuals directly from the CLI.

02Iteratively refining project graphics using natural language instructions.

03Generating UI placeholders and visual assets during frontend development.

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add christian-schlichtherle/cs7-claude-plugins generate-image

For use in Claude.ai and ChatGPT