home / skills / openclaw / skills / nano-banana-pro-2

nano-banana-pro-2 skill

safe

This skill helps you generate or edit images with Gemini 3 Pro Image, producing ready-to-use outputs from prompts.

npx playbooks add skill openclaw/skills --skill nano-banana-pro-2

Review the files below or copy the command above to add this skill to your agents.

Files (3)

SKILL.md

1.3 KB

---
name: nano-banana-pro
description: Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro).
homepage: https://ai.google.dev/
metadata: {"moltbot":{"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
- `GEMINI_API_KEY` env var
- Or set `skills."nano-banana-pro".apiKey` / `skills."nano-banana-pro".env.GEMINI_API_KEY` in `~/.clawdbot/moltbot.json`

Notes
- Resolutions: `1K` (default), `2K`, `4K`.
- Use timestamps in filenames: `yyyy-mm-dd-hh-mm-ss-name.png`.
- The script prints a `MEDIA:` line for Moltbot to auto-attach on supported chat providers.
- Do not read the image back; report the saved path only.

Overview

This skill provides a command-line interface to generate or edit images using Gemini 3 Pro Image (Nano Banana Pro). It wraps a Python script to create single images, edit an existing image, or compose multiple images into one scene. It is designed for batch workflows and integration with Moltbot-style chat providers.

How this skill works

The bundled Python script accepts a text prompt, output filename, resolution flag, and zero or more input images. It uses the Gemini 3 Pro Image API key from an environment variable or Moltbot config to call the model and writes the result to disk. When run inside supported chat setups, the script prints a MEDIA: line so the platform can auto-attach the generated file.

When to use it

Generate concept art, mockups, or visual assets from text prompts.
Edit or enhance a single source image with text-driven instructions.
Combine up to 14 images into a single composed scene.
Automate image creation in batch scripts or CI pipelines.
Attach generated images to chat workflows via Moltbot integration.

Best practices

Set the GEMINI_API_KEY env var or configure skills.nano-banana-pro.apiKey in your Moltbot config.
Use descriptive filenames with timestamps (yyyy-mm-dd-hh-mm-ss-name.png) to avoid collisions.
Start with 1K for fast iteration, then switch to 2K or 4K for final outputs.
When editing, supply a clear, concise instruction prompt and a high-quality input image.
Avoid reading generated binary output back into scripts; report and store the saved path only.

Example use cases

Create UI concept images from a short prompt for a design review.
Retouch a photographed product by running an edit prompt with the original image as input.
Merge a set of character sketches into a single scene for a storyboard.
Run nightly jobs that generate new visual assets and save them with timestamped filenames.
Integrate generation into a chat bot so users receive images as attachments via MEDIA: output.

FAQ

How do I provide the API key?

Set GEMINI_API_KEY in your environment or place the key in skills."nano-banana-pro".apiKey or skills."nano-banana-pro".env.GEMINI_API_KEY in ~/.clawdbot/moltbot.json.

What resolutions are supported?

Supported resolution flags are 1K (default), 2K, and 4K. Use higher resolutions for final assets but expect longer runtimes and larger files.