Gemini Nano Banana

Auto-generated skill for gemini tools via OneKey Gateway.

Security Scan

The skill's code and instructions match its stated purpose (calling a OneKey Gateway to generate Gemini images) and its only required secret is a OneKey API key; nothing appears disproportionate or malicious.

Purpose & Capability

The name/description say this is a Gemini image tool via OneKey Gateway and the included Python scripts invoke OneKeyAgentRouter with model/api IDs. The required DEEPNLP_ONEKEY_ROUTER_ACCESS key and the declared npm/python dependencies are consistent with that purpose. (Minor metadata mismatch: registry summary earlier listed no required env vars, but SKILL.md declares the OneKey API key.)

Instruction Scope

SKILL.md instructs the agent to use the OneKey access key, run the provided CLI examples, and optionally read a user-supplied JSON payload file. The scripts only read the payload and the single DEEPNLP_ONEKEY_ROUTER_ACCESS env var, then call router.invoke and print the result. There are no instructions to read unrelated system files, harvest other env vars, or post data to unexpected endpoints beyond the OneKey gateway.

Install Mechanism

This is an instruction-only skill in the registry but SKILL.md recommends installing an npm package (@aiagenta2z/onekey-gateway) and a Python package (ai-agent-marketplace). Those are registry installs (npm/pip) rather than downloads from arbitrary URLs, which is standard. Confirm these package names are the official packages you expect before installing globally (npm -g).

Credentials

Only one credential is required (DEEPNLP_ONEKEY_ROUTER_ACCESS), which is appropriate for a gateway service. The scripts do not request additional secrets or config paths. Note the registry header omitted this env var while SKILL.md requires it.

Persistence & Privilege

The skill is not marked always:true and does not request persistent system-wide privileges or modify other skills. disable-model-invocation is false (normal), and user-invocable is true.

Assessment

This skill appears to do what it says: it sends image-generation requests to a OneKey Gateway and returns results. Before installing, verify you trust the OneKey provider (deepnlp.org) and the npm/pip package names referenced; installing global npm packages can affect your system. Only provide a OneKey API key that has the minimum required permissions and avoid putting sensitive files or credentials into the payload/data-file or output_folder. If you want extra safety, run the included scripts in a sandboxed environment, review the pip/npm packages on their registries, and rotate or scope the API key you use. Also note a small metadata inconsistency: the registry summary omitted the required env var while SKILL.md requires DEEPNLP_ONEKEY_ROUTER_ACCESS—this likely indicates stale metadata rather than malicious behavior.

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:

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

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

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

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

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

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

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.

pip install ai-agent-marketplace

Alternatively, install dependencies from the requirements file:

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 onekey CLI as the preferred method to run the skills.