agentsclimarketplace

Nano banana pro

Skill ComeOnOliver/skillshub/skills/happycapy-ai/Happycapy-skills/nano-banana-pro

Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro) with AI Gateway support.From its SKILL.md

Install
npx -y skills add ComeOnOliver/skillshub --skill nano-banana-pro

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

SKILL.md

2.6 KB, 619 tokens by cl100k_base, as published. Nobody here has run it

Nano Banana Pro (Gemini 3 Pro Image)

Generate or edit images using Gemini 3 Pro Image via AI Gateway or direct API.

Quick Start

Generate an image:

python3 {baseDir}/scripts/generate_image.py \
  --prompt "your image description" \
  --filename "output.png" \
  --resolution 1K

Usage Examples

Generate Image

python3 {baseDir}/scripts/generate_image.py \
  --prompt "a cute cat sitting on a wooden floor" \
  --filename "cat.png"

Edit Image (requires GEMINI_API_KEY)

Note: Image editing currently requires direct Gemini API access.

export GEMINI_API_KEY="your-gemini-key"
python3 {baseDir}/scripts/generate_image.py \
  --prompt "make it more colorful" \
  --filename "cat-colorful.png" \
  -i "cat.png"

Multi-image Composition (up to 14 images, requires GEMINI_API_KEY)

python3 {baseDir}/scripts/generate_image.py \
  --prompt "combine these into one scene" \
  --filename "combined.png" \
  -i img1.png -i img2.png -i img3.png

API Key Configuration

The skill automatically detects API keys in this priority order:

  1. AI_GATEWAY_API_KEY (recommended) - Uses AI Gateway
  2. GEMINI_API_KEY - Direct Gemini API access
  3. --api-key argument - Manual key override

Recommended: AI Gateway (default)

export AI_GATEWAY_API_KEY="your-gateway-key"  # Usually pre-configured

✅ No additional dependencies required ✅ Cost-efficient and unified API management ❌ Image editing not currently supported

Alternative: Direct Gemini API

export GEMINI_API_KEY="your-gemini-key"

✅ Supports image editing and multi-image composition ❌ Requires google-genai package: pip install google-genai

Options

  • --prompt, -p: Image description (required)
  • --filename, -f: Output filename (required)
  • --resolution, -r: Resolution (1K, 2K, 4K, default: 1K)
  • --input-image, -i: Input image(s) for editing (up to 14, requires GEMINI_API_KEY)
  • --api-key, -k: Manual API key override

Notes

  • Resolutions: 1K (default), 2K, 4K
  • Use descriptive filenames with timestamps: 2024-12-31-cat.png
  • The script outputs a MEDIA: line for OpenClaw integration
  • AI Gateway mode works with standard Python 3, no extra tools needed

What ships with it

13.6 KB alongside SKILL.md, 1 of them executable

GitHub clipped this repository’s file list, so this is at least 2 files and may be more.

scripts/

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.