Nano Banana

A Claude Code skill for generating and editing images using the Gemini CLI’s nanobanana extension.

Features

• Text-to-image generation - Create images from natural language prompts
• Image editing - Modify existing images with instructions
• Photo restoration - Repair damaged or old photos
• Icon generation - Create app icons and favicons
• Diagram creation - Generate flowcharts and architecture diagrams
• Pattern generation - Create seamless textures and patterns
• Story/sequential images - Generate narrative image sequences

Prerequisites

1. Gemini CLI - Install from gemini-cli
2. Gemini API Key - Get one from Google AI Studio
3. nanobanana extension - Installed via Gemini CLI

Installation

1. Install the Gemini CLI

npm install -g @google/gemini-cli

2. Set your API key

export NANOBANANA_GEMINI_API_KEY="your-api-key"

3. Install the nanobanana extension

gemini extensions install https://github.com/gemini-cli-extensions/nanobanana

4. Install this skill

Copy the SKILL.md file to your Claude Code skills directory:

mkdir -p ~/.claude/skills/nano-banana
cp SKILL.md ~/.claude/skills/nano-banana/

Or clone this repository directly:

git clone https://github.com/kkoppenhaver/cc-nano-banana ~/.claude/skills/nano-banana

Usage

Once installed, Claude Code will automatically use this skill when you ask for image generation. Examples:

• “Generate a blog header image for a post about machine learning”
• “Create a YouTube thumbnail for a coding tutorial”
• “Make an app icon for a productivity tool”
• “Draw a flowchart showing user authentication”
• “Edit this image to remove the background”

Available Commands

Common Options

Output

Generated images are saved to ./nanobanana-output/ in your current working directory.

Model Selection

Default model: gemini-2.5-flash-image (~$0.04/image)

For higher quality output:

export NANOBANANA_MODEL=gemini-3-pro-image-preview

License

MIT

Contributing

Contributions are welcome! Please open an issue or submit a pull request.