skills.rest
duotify
duotifyOFFICIAL
Explore all skills by this author →
WebsiteGitHub

gemini-nanobanana

Generate, edit, and compose images via a Gemini Nano Banana CLI workflow.

252|52|Updated Mar 22, 2026
Search Tags:#api#cli#grounding#gemini#image-generation#nanobanana#wrapper
One-click install
npx skills add https://github.com/duotify/GitHubClawToolkit --skill gemini-nanobanana
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gemini-nanobanana
Source: https://github.com/duotify/GitHubClawToolkit/tree/main/templates/codex-gemini-api/.agents/skills/gemini-nanobanana
Command: npx skills add https://github.com/duotify/GitHubClawToolkit --skill gemini-nanobanana

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

The Nano Banana skill enables users to generate, edit, and compose images using Gemini's image-generation models, simplifying complex visual tasks with a single, repeatable workflow.

Core Features & Use Cases

  • Text-to-image generation from descriptive prompts, supporting grounding and up-to-date information when needed.
  • Image editing and multi-image composition, handling multiple references (up to 14) to create cohesive outputs.
  • Output sizing controls, aspect-ratio options, and automatic saving to a default output directory.

Quick Start

Run the Gemini Nano Banana CLI wrapper with a prompt to generate or edit an image, and outputs will be saved to nanobanana-output.

Frequently Asked Questions about gemini-nanobanana

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate images with Gemini using a CLI wrapper?▼

Gemini image generation is executed by running the CLI wrapper with a text prompt, which triggers the Nano Banana model to create and save visual output directly to your local directory.

Can I edit an existing image and combine multiple reference images with Gemini?▼

Image editing and multi-image composition are supported by submitting up to 14 reference images to the CLI, allowing the Gemini model to generate a cohesive edited output.

How does grounding with Google Search work for Gemini image generation?▼

Grounding via Google Search can be enabled for text-to-image generation, allowing the Gemini model to incorporate up-to-date information into the generated visual output when required.

Do I need an API key to run the Gemini Nano Banana workflow?▼

An API key is required and enforced by default to authenticate requests, ensuring the CLI wrapper successfully communicates with the Gemini image-generation models.

What output sizing and aspect ratio options are available for Gemini image generation?▼

Output sizing controls and aspect-ratio options are configurable parameters within the CLI, allowing you to dictate the exact dimensions of the generated or edited images.

What are the limitations when using a CLI wrapper for Gemini image generation?▼

Limitations include a maximum of 14 reference images for composition tasks, and dependencies on proper API key configuration and prompt validation to prevent execution errors.

Related Skills

Explore More Software Engineering Skills→
lucasFR2lucasFR2

baoyu-danger-gemini-web

Generate images and text via the reverse-engineered Gemini Web API.

Community
Advanced
k97k97
4

favicon

Generate favicon assets from a source image using ImageMagick.

Community
Intermediate
SheshiyerSheshiyer
4

nano-banana-2

Generate Gemini 3.1 flash image previews from prompts via the inference.sh CLI.

Community
Intermediate
oldwinteroldwinter
5

baoyu-danger-gemini-web

Generate images and text through the Gemini Web API.

Community
Advanced