TypingMindTypingMindThe best frontend for AI
Gemini Nano Banana logo

Gemini Nano Banana

Organization
aiagenta2z
gemini-nano-banana

Auto-generated skill for gemini tools via OneKey Gateway.

Overview

Publisheraiagenta2z
Repositoryonekey-gateway
Skill namegemini-nano-banana
Stars
52
Forks
11
Bundled files
2
Links
Skill sourceRepositoryHomepage
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by aiagenta2z on GitHub. Read the source before you install it.

Installation

Install the Gemini Nano Banana AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/aiagenta2z/onekey-gateway/tree/main/skills/gemini-nano-banana
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/aiagenta2z/onekey-gateway.git /tmp/onekey-gateway
mkdir -p .claude/skills
cp -r /tmp/onekey-gateway/skills/gemini-nano-banana .claude/skills/gemini-nano-banana
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Gemini Nano Banana in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Gemini Nano Banana on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Gemini Nano Banana is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

OneKey Gateway

Use One Access Key to connect to various commercial APIs. Please visit the OneKey Gateway Keys and read the docs OneKey MCP Router Doc and OneKey Gateway Doc.

gemini Skill

Use the OneKey Gateway to access tools for this server via a unified access key.

Quick Start

Set your OneKey access key:

bash
export DEEPNLP_ONEKEY_ROUTER_ACCESS=YOUR_API_KEY

Common settings:

  • unique_id: gemini/gemini
  • api_id: one of the tools listed below

Tools

generate_image_gemini

Generates an image using the Gemini Image API. Supported Models (aliases are internal): The model parameter allows selection between available image generation models. - "gemini-2.5-flash-image" (recommended default for stable, fast response). - "gemini-3-pro-image-preview". - "gemini-3-flash"

        Aliases for these models are 'nano-banana 2.5' and 'nano-banana 3 Pro' respectively.
        Please use 'gemini-2.5-flash-image' unless the user specifically requests the Gemini 3 model.

    Args:
        model: The image generation model to use (see supported models above). Defaults to "gemini-2.5-flash-image". Supports: 'gemini-3-flash', 'gemini-3-pro-image-preview', 'gemini-2.5-flash-image'
        prompt: A detailed text description for the image to be generated.
        image_name: The filename for the output image, can be a relative path. Defaults to "gemini_output_images.png".
        output_folder: The optional absolute folder path provided by the user where the image will be saved. Do not use default server locations.
        aspect_ratio: The aspect ratio of the generated image (e.g., '16:9', '1:1', '4:3'). Defaults to '16:9'.
        image_size: The size/resolution of the generated image (e.g., '1K', '2K', '4K'). Defaults to '1K'.

    Return:
        Dict: Result dictionary containing image path, message, and success status.
        output_result["image_path"]: str
        output_result["image_url"]: str
        output_result["message"]: str
        output_result["success"]: bool

Parameters:

  • model (string, optional):
  • prompt (string, optional):
  • image_name (string, optional):
  • output_folder (object, optional):
  • aspect_ratio (string, optional):
  • image_size (string, optional):

generate_image_nano_banana

Generate Image With Nano Banana

    Args:
        model: The image generation model to use. Defaults to "gemini-2.5-flash-image". Supported Models such as follows Google Gemini Doc, such as 'gemini-3-flash', "gemini-3-pro-image-preview", "gemini-2.5-flash-image", note that nano-banana is the alias name of the Gemini Image Model. Nano banana 3 Pro refers to Gemini 3 pro preview, and Nono Banana 2.5 refers to Gemini 2.5. Unless specified by user to use Gemini 3 model preview, general 'Neno Banana' image models, please use 'gemini-2.5-flash-image' for more stable and fast response.
        prompt: A detailed text description for the image to be generated.
        image_name: The filename for the output image, can be a relative path, such as "./new_gemini_image.png", etc. Defaults to "gemini_output_images.png".
        output_folder: The optional absolute folder path provided by the user where the image will be saved. Do not use default server locations.
        aspect_ratio: The aspect ratio of the generated image (e.g., '16:9', '1:1', '4:3'), defaults to '16:9'.
        image_size: The size/resolution of the generated image (e.g., '1K', '2K', '4K'), defaults to '1K'.

    Return:
        Dict:  output_result is the result dict of MCP returned
        output_result["image_path"] = full_path: str
        output_result["message"] = output_message: str
        output_result["success"] = success: bool

Parameters:

  • model (string, optional):
  • prompt (string, optional):
  • image_name (string, optional):
  • output_folder (object, optional):
  • aspect_ratio (string, optional):
  • image_size (string, optional):

Usage

CLI

generate_image_gemini

shell
npx onekey agent gemini-nano-banana/gemini-nano-banana generate_image_gemini '{"model": "gemini-2.5-flash-image", "prompt": "sunrise over mountains", "aspect_ratio": "16:9", "image_size": "1K"}'

generate_image_nano_banana

shell
npx onekey agent gemini-nano-banana/gemini-nano-banana generate_image_nano_banana '{"model": "gemini-2.5-flash-image", "prompt": "robot reading book", "aspect_ratio": "16:9", "image_size": "1K"}'

generate_image_nano_banana_with_reference

shell
npx onekey agent gemini-nano-banana/gemini-nano-banana generate_image_nano_banana_with_reference '{"model": "gemini-3-pro-image-preview", "prompt": "winter coat style", "images": ["https://avatars.githubusercontent.com/u/242328252"], "aspect_ratio": "1:1"}'

ocr_extract_text_from_image

shell
npx onekey agent gemini-nano-banana/gemini-nano-banana ocr_extract_text_from_image '{"images": ["https://avatars.githubusercontent.com/u/242328252"], "model": "gemini-3-flash-preview"}'

list_items_from_image

shell
npx onekey agent gemini-nano-banana/gemini-nano-banana list_items_from_image '{"images": ["https://avatars.githubusercontent.com/u/242328252"], "model": "gemini-3-flash-preview", "output_json": true}'

Scripts

Each tool has a dedicated script in this folder:

  • skills/gemini/scripts/generate_image_gemini.py
  • skills/gemini/scripts/generate_image_nano_banana.py

Example

bash
python3 scripts/<tool_name>.py --data '{"key": "value"}'

Related DeepNLP OneKey Gateway Documents

AI Agent Marketplace
Skills Marketplace AI Agent A2Z Deployment
PH AI Agent A2Z Infra
GitHub AI Agent Marketplace

Dependencies

CLI Dependency

Install onekey-gateway from npm

npm install @aiagenta2z/onekey-gateway

Script Dependency

Install the required Python package before running any scripts.

bash
pip install ai-agent-marketplace

Alternatively, install dependencies from the requirements file:

bash
pip install -r requirements.txt

If the package is already installed, skip installation.

Agent rule

Before executing command lines or running any script in the scripts/ directory, ensure the dependencies are installed. Use the npx onekey CLI as the preferred method to run the skills.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Gemini Nano Banana AI skill do?

Auto-generated skill for gemini tools via OneKey Gateway.

Why use Gemini Nano Banana on TypingMind?

Because you install it once and use it with any model. Gemini Nano Banana is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Gemini Nano Banana in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/aiagenta2z/onekey-gateway/tree/main/skills/gemini-nano-banana. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Gemini Nano Banana?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Gemini Nano Banana?

As many as you like. As long as a model supports skills, you can use Gemini Nano Banana with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Gemini Nano Banana AI skill free?

It is published on GitHub by aiagenta2z. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Related AI Skills

View all
tt-a1i logo

Archify Review

tt-a1i
CommunityPopular

Review Archify issues, PRs, or code through value, cost, and impact to support evidence-based maintenance decisions. Use for issue triage, change reviews, and code quality assessments.

5.1K
75.3K
Instructions
View
ruvnet logo

Adr Verify

ruvnet
CommunityPopular

Read back adr-patterns + adr-edges namespaces, surface dangling refs / supersede cycles / status mismatches; exit 1 on cycles

8.6K
72.7K
Instructions
View
ruvnet logo

Wasm Gallery

ruvnet
CommunityPopular

Browse, publish, and install WASM agents from the community gallery

8.6K
72.7K
Instructions
View
ruvnet logo

Browser Extract

ruvnet
CommunityPopular

Extract structured data via stored browser-templates or one-shot DOM queries, with mandatory AIDefence PII + prompt-injection gates before content reaches the model

8.6K
72.7K
Instructions
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇