nano-banana-pro · swarmclawai — Claude Code image skill: features and setup
Generate images with Gemini 3 Pro Image, edit a single file, or combine several into one composition. You’ll need a Gemini API key.
npx skills add swarmclawai/swarmclaw --skill nano-banana-pro -a claude-codeWhat nano-banana-pro does
The skill runs generate_image.py with uv. It can turn a text prompt into an image, apply edits to one input image, or compose a scene from up to 14 images. The script saves the result to the filename you provide.
Install uv and set GEMINI_API_KEY, or pass the key with --api-key. You can choose 1K, 2K, or 4K resolution and set an aspect ratio. Image generation won’t run without a Gemini API key. Afterward, the agent should report the saved path rather than load the image back into context.
What it helps with
- generate an image from a text prompt
- edit a single image using written instructions
- combine several images into one scene
- choose an output resolution and aspect ratio
Example prompts for the agent
- Create a cover image from this description and save it as
cover.png. - Edit
photo.pngto make the background lighter, then save the result asedited.png. - Combine
img1.pngandimg2.pnginto one scene and save it ascomposition.png.
How to install nano-banana-pro
1Skills CLI (Vercel)
npx skills add swarmclawai/swarmclaw --skill nano-banana-pro -a claude-code2Manually: put the files in place
~/.claude/skills/nano-banana-pro/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/nano-banana-pro/
1Skills CLI (Vercel)
npx skills add swarmclawai/swarmclaw --skill nano-banana-pro -a codex2Manually: put the files in place
.agents/skills/nano-banana-pro/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add swarmclawai/swarmclaw --skill nano-banana-pro -a cursor2Manually: put the files in place
.cursor/skills/nano-banana-pro/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install swarmclawai/swarmclaw nano-banana-pro2Manually: put the files in place
.github/skills/nano-banana-pro/SKILL.md1Skills CLI (Vercel)
npx skills add swarmclawai/swarmclaw --skill nano-banana-pro -a gemini-cli2Platform CLI
gemini skills install https://github.com/swarmclawai/swarmclaw --path skills/nano-banana-proManually: put the files in place
.devin/skills/nano-banana-pro/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add swarmclawai/swarmclaw --skill nano-banana-pro -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about nano-banana-pro
How do I install nano-banana-pro in Claude Code?
Run npx skills add swarmclawai/swarmclaw --skill nano-banana-pro -a claude-code. The skill file is at ~/.claude/skills/nano-banana-pro/SKILL.md.
What does nano-banana-pro do?
It uses Gemini 3 Pro Image to generate images from prompts, edit one image, or combine several images into a composition.
What does nano-banana-pro need to run?
You need uv and a Gemini API key. Set GEMINI_API_KEY or pass the key with --api-key; a composition can use up to 14 images.
Source text
SKILL.md · MIT
---
name: nano-banana-pro
description: Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro). Use when asked to create, generate, or edit images and a Gemini API key is available. Supports text-to-image generation, single-image editing, and multi-image composition (up to 14 images).
metadata:
{
"openclaw":
{
"emoji": "🍌",
"requires": { "bins": ["uv"], "env": ["GEMINI_API_KEY"] },
"primaryEnv": "GEMINI_API_KEY",
"install":
[
{
"id": "uv-brew",
"kind": "brew",
"formula": "uv",
"bins": ["uv"],
"label": "Install uv (brew)",
},
],
},
}
---
# Nano Banana Pro (Gemini 3 Pro Image)
Use the bundled script to generate or edit images.
## Generate
```bash
uv run {baseDir}/scripts/generate_image.py --prompt "your image description" --filename "output.png" --resolution 1K
```
## Edit (Single Image)
```bash
uv run {baseDir}/scripts/generate_image.py --prompt "edit instructions" --filename "output.png" -i "/path/in.png" --resolution 2K
```
## Multi-Image Composition (up to 14 images)
```bash
uv run {baseDir}/scripts/generate_image.py --prompt "combine these into one scene" --filename "output.png" -i img1.png -i img2.png -i img3.png
```
## API Key
Set `GEMINI_API_KEY` as an environment variable, or pass `--api-key <KEY>` to the script.
## Aspect Ratio (optional)
```bash
uv run {baseDir}/scripts/generate_image.py --prompt "portrait photo" --filename "output.png" --aspect-ratio 9:16
```
## Notes
- Resolutions: `1K` (default), `2K`, `4K`.
- Aspect ratios: `1:1`, `2:3`, `3:2`, `3:4`, `4:3`, `4:5`, `5:4`, `9:16`, `16:9`, `21:9`. Without `--aspect-ratio`, the model picks freely.
- Use timestamps in filenames for uniqueness: `yyyy-mm-dd-hh-mm-ss-name.png`.
- Do not read the image back into context; report the saved path only.
© swarmclawai · MIT · swarmclawai/swarmclaw
Similar skills
All skills for AI and ML →nano-banana-pro by other authors comes first.