Skill

Fail

Audit score 45

nano-banana-pro

intellectronica/agent-skills

Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API.

What is nano-banana-pro?

Create new images from text descriptions or edit existing images with AI-powered modifications. Use this skill whenever a user asks to generate, create, edit, modify, or alter images, supporting resolutions from 1K to 4K.

Generate new images from text prompts
Edit and modify existing images with instructions
Support three resolution options: 1K (default), 2K, and 4K
Save generated/edited images as PNG files to the current working directory
Accept API key via argument or GEMINI_API_KEY environment variable
Preserve user's creative intent in prompts

How to install nano-banana-pro

npx skills add https://github.com/intellectronica/agent-skills --skill nano-banana-pro

Prerequisites

Google Gemini API key (provide via --api-key argument or GEMINI_API_KEY environment variable)
uv package manager installed

Claude Code

Cursor

Windsurf

Cline

How to use nano-banana-pro

1.For new images: run `uv run ~/.claude/skills/nano-banana-pro/scripts/generate_image.py --prompt "your description" --filename "output-name.png"` with optional `--resolution 1K|2K|4K`
2.For editing: add `--input-image "path/to/image.png"` parameter and provide editing instructions in the prompt
3.Always run from your current working directory so images save where you're working
4.Use timestamp-based filenames in format `yyyy-mm-dd-hh-mm-ss-descriptive-name.png` for organization
5.Optionally specify resolution: 1K for standard, 2K for medium, 4K for high-resolution output

Use cases

Good for

Create a new image from a detailed text description (e.g., 'A serene Japanese garden with cherry blossoms')
Modify an existing photo by changing elements (e.g., 'make the sky more dramatic with storm clouds')
Generate high-resolution artwork for presentations or designs
Edit images to change style, colors, or composition without re-creating from scratch
Batch create variations of images with different resolutions

Who it's for

Content creators and designers
Users needing quick image generation or editing
Anyone working with visual assets in their workflow
Developers and agents automating image creation tasks

nano-banana-pro FAQ

Do I need to read/load the image file first before editing?

No. Do NOT read the image file first—pass the image path directly to the skill using the --input-image parameter.

What resolutions are available?

Three options: 1K (~1024px, default), 2K (~2048px), and 4K (~4096px). Map user requests like 'high-res' or '4K' to the appropriate parameter.

Where are generated images saved?

Images are saved as PNG files in your current working directory (or a specified path if included in the filename). The script outputs the full path.

How do I provide my API key?

Either pass it with --api-key argument in the command, or set the GEMINI_API_KEY environment variable. The script checks both in order.

What's the difference between generation and editing?

Generation creates a new image from a text description. Editing modifies an existing image using the --input-image parameter with editing instructions in the prompt.

Full instructions (SKILL.md)

Source of truth, from intellectronica/agent-skills.

name: nano-banana-pro description: Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.

Nano Banana Pro Image Generation & Editing

Generate new images or edit existing ones using Google's Nano Banana Pro API (Gemini 3 Pro Image).

Usage

Run the script using absolute path (do NOT cd to skill directory first):

Generate new image:

uv run ~/.claude/skills/nano-banana-pro/scripts/generate_image.py --prompt "your image description" --filename "output-name.png" [--resolution 1K|2K|4K] [--api-key KEY]

Edit existing image:

uv run ~/.claude/skills/nano-banana-pro/scripts/generate_image.py --prompt "editing instructions" --filename "output-name.png" --input-image "path/to/input.png" [--resolution 1K|2K|4K] [--api-key KEY]

Important: Always run from the user's current working directory so images are saved where the user is working, not in the skill directory.

Resolution Options

The Gemini 3 Pro Image API supports three resolutions (uppercase K required):

1K (default) - ~1024px resolution
2K - ~2048px resolution
4K - ~4096px resolution

Map user requests to API parameters:

No mention of resolution → 1K
"low resolution", "1080", "1080p", "1K" → 1K
"2K", "2048", "normal", "medium resolution" → 2K
"high resolution", "high-res", "hi-res", "4K", "ultra" → 4K

API Key

The script checks for API key in this order:

--api-key argument (use if user provided key in chat)
GEMINI_API_KEY environment variable

If neither is available, the script exits with an error message.

Filename Generation

Generate filenames with the pattern: yyyy-mm-dd-hh-mm-ss-name.png

Format: {timestamp}-{descriptive-name}.png

Timestamp: Current date/time in format yyyy-mm-dd-hh-mm-ss (24-hour format)
Name: Descriptive lowercase text with hyphens
Keep the descriptive part concise (1-5 words typically)
Use context from user's prompt or conversation
If unclear, use random identifier (e.g., x9k2, a7b3)

Examples:

Prompt "A serene Japanese garden" → 2025-11-23-14-23-05-japanese-garden.png
Prompt "sunset over mountains" → 2025-11-23-15-30-12-sunset-mountains.png
Prompt "create an image of a robot" → 2025-11-23-16-45-33-robot.png
Unclear context → 2025-11-23-17-12-48-x9k2.png

Image Editing

When the user wants to modify an existing image:

Check if they provide an image path or reference an image in the current directory
Use --input-image parameter with the path to the image
The prompt should contain editing instructions (e.g., "make the sky more dramatic", "remove the person", "change to cartoon style")
Common editing tasks: add/remove elements, change style, adjust colors, blur background, etc.

Prompt Handling

For generation: Pass user's image description as-is to --prompt. Only rework if clearly insufficient.

For editing: Pass editing instructions in --prompt (e.g., "add a rainbow in the sky", "make it look like a watercolor painting")

Preserve user's creative intent in both cases.

Output

Saves PNG to current directory (or specified path if filename includes directory)
Script outputs the full path to the generated image
Do not read the image back - just inform the user of the saved path

Examples

Generate new image:

uv run ~/.claude/skills/nano-banana-pro/scripts/generate_image.py --prompt "A serene Japanese garden with cherry blossoms" --filename "2025-11-23-14-23-05-japanese-garden.png" --resolution 4K

Edit existing image:

uv run ~/.claude/skills/nano-banana-pro/scripts/generate_image.py --prompt "make the sky more dramatic with storm clouds" --filename "2025-11-23-14-25-30-dramatic-sky.png" --input-image "original-photo.jpg" --resolution 2K