Stats
Actions
Tags
From nano-banana-pro
Generate, edit, remix, and optimize images using Google Gemini 3 Pro Image Preview (Nano Banana Pro)
How this skill is triggered — by the user, by Claude, or both
Slash command
/nano-banana-pro:generateThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Generate, edit, remix, and optimize images using Google's Gemini 3 Pro Image Preview model.
Generate, edit, remix, and optimize images using Google's Gemini 3 Pro Image Preview model.
| Command | Description |
|---|---|
gen | Generate an image from a text prompt |
edit | Edit an existing image with instructions |
remix-url | Create an image styled from a webpage |
optimize | Reduce image size for GitHub, Slack, web |
Use --model pro (higher quality, default) or --model flash (faster) with any command. Set the default in your configuration via default_model.
# Generate/edit/remix
uv run --directory "${CLAUDE_PLUGIN_ROOT}" python "${CLAUDE_PLUGIN_ROOT}/skills/generate/scripts/nanobanana.py" <command> [options]
# Optimize
uv run --directory "${CLAUDE_PLUGIN_ROOT}" python "${CLAUDE_PLUGIN_ROOT}/skills/generate/scripts/optimize.py" <image> [--preset github|slack|web|thumbnail]
After generating any image, check the file size. If over 500KB (or user's configured threshold), suggest optimization:
Generated image: ./banner.png (2.3MB)
⚠️ This image is large for GitHub/web use. To optimize:
/optimize-image ./banner.png --preset github
| Preset | Max Size | Max Width | Use Case |
|---|---|---|---|
github | 500KB | 1280px | README images, PR screenshots |
slack | 128KB | 800px | Slack/Discord messages |
web | 200KB | 1200px | Blog posts, documentation |
thumbnail | 50KB | 400px | Previews, icons |
This plugin includes 5 specialized agents for automated, high-quality image creation:
| Phase | Agent | Role |
|---|---|---|
| Planning | Retriever | Finds brand assets, colors, fonts in your project |
| Planning | Planner | Creates detailed visual specifications |
| Planning | Stylist | Applies aesthetic guidelines and design principles |
| Refinement | Visualizer | Executes image generation (only agent that writes) |
| Refinement | Critic | Evaluates output, requests revisions (up to 3 rounds) |
Agents are enabled/disabled via configuration. See /configure agents.
npx claudepluginhub fakoli/fakoli-plugins --plugin nano-banana-proGenerates, edits, and composes images using Google's Gemini 3 Pro Image model. Supports text-to-image, multi-image composition, aspect ratio control, and search-grounded generation for data visuals.
Generates AI images from text prompts, edits images, and composes from multiple references using Gemini models. Supports t2i, i2i, product mockups, and stickers.
Generates and edits images using Gemini CLI image models for blog featured images, YouTube thumbnails, icons, diagrams, patterns, illustrations, and visuals. Activates on create, generate, make, draw, design, or edit image requests.