skills.rest
luansinezio
luansinezioCOMMUNITY
Explore all skills by this author →
GitHub

nanobanana-ratos

Generate images from prompts via Gemini API using curl and Python.

Updated Aug 23, 2026
Search Tags:#image-generation#curl#prompt-engineering#ai-art#gemini-api#visual-content
One-click install
npx skills add https://github.com/luansinezio/Beza-OS --skill nanobanana-ratos
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nanobanana-ratos
Source: https://github.com/luansinezio/Beza-OS/tree/main/.claude/skills/nanobanana-ratos
Command: npx skills add https://github.com/luansinezio/Beza-OS --skill nanobanana-ratos

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Nano Banana image generation eliminates the manual process of sourcing or creating visuals by generating images from natural language prompts using the Gemini API. It operates with curl and Python, avoiding external dependencies.

Core Features & Use Cases

  • Easy prompt-to-image generation: Build prompts in English to generate high-quality visuals.
  • Output configurability: Control style and output details, including prompts and image saving.
  • Use cases: Create social media visuals, website banners, thumbnails, and marketing illustrations on demand.

Quick Start

Describe the desired image in English and run the skill to generate and save the image.

Frequently Asked Questions about nanobanana-ratos

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

FAQPage Schema
How do I generate images from text prompts using the Gemini API?▼

Generate images from text prompts using the Gemini API by writing a descriptive English prompt and triggering the skill, which uses a curl-based request to create visuals on demand. This process builds high-quality illustrations without manual sourcing.

Do I need to install external Python dependencies for AI image generation?▼

No, you do not need to install external Python dependencies for AI image generation. The skill operates with standard curl and Python, avoiding additional library installations while handling image creation and saving outputs locally.

How do I securely store my Gemini API key for prompt-to-image generation?▼

Securely store your Gemini API key for prompt-to-image generation in a local .env file. The skill loads the key prior to making curl API calls, ensuring your credentials remain protected during visual content creation.

Can I use generated AI art for website banners and marketing illustrations?▼

Yes, you can use generated AI art for website banners and marketing illustrations. The skill supports design workflows for creating social media visuals, thumbnails, and marketing illustrations on demand from natural language prompts.

What are the limitations of using curl and Python for image generation?▼

Limitations of using curl and Python for image generation include relying on English prompts for output quality and needing a valid Gemini API key. The skill includes error reporting to handle failed requests during visual generation.

Related Skills

Explore More Design & Creative Skills→
aberrantCodeaberrantCode
1

credentials

Load API keys from a credentials file into a .env file.

Community
Intermediate
tiankong0101-bytetiankong0101-byte

graphic-design

Create visual assets for branding, marketing, and presentations.

Community
Intermediate
XJTLUmediaXJTLUmedia
28

image-generation

Generate images from text prompts via the z-ai-web-dev-sdk.

Community
Advanced
TTAWDTTTTAWDTT
5

imagegen

Generate and edit images via Google Gemini and OpenAI GPT-Image APIs.

Community
Intermediate