skills.rest
juanpvh
juanpvhCOMMUNITY
Explore all skills by this author →
GitHub

nanobanana-ratos

Generate images from text prompts using the Google Gemini API.

Updated Apr 28, 2026
Search Tags:#image generation#Claude Code#Nano Banana#text to image#Google Gemini API
One-click install
npx skills add https://github.com/juanpvh/move-skills-claude-codex --skill nanobanana-ratos-juanpvh
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nanobanana-ratos
Source: https://github.com/juanpvh/move-skills-claude-codex/tree/main/plugins/imagem-ratos/skills/nanobanana-ratos
Command: npx skills add https://github.com/juanpvh/move-skills-claude-codex --skill nanobanana-ratos-juanpvh

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires curl, python3, and includes scripts (resource) and assets (resource) components.

What problem does it solve?

This skill provides the capability to generate images from text prompts using the Nano Banana API, streamlining the process of creating visual content directly within Claude Code.

Core Features & Use Cases

  • Text-to-Image Generation: Convert textual descriptions into visual images through the Google Gemini API.
  • No External Tools Needed: Utilizes only curl and Python 3, which are typically pre-installed on macOS systems.
  • Use Case: With this skill, a user can simply input a text prompt such as "generate a cartoon image of a mouse with headphones" and receive a corresponding image.

Quick Start

After installation, generate an image by simply asking Claude Code to "generate an image of a cartoon mouse with headphones."

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 Claude Code?▼

You can generate images from text prompts in Claude Code by using this Skill to send requests to the Google Gemini API. Simply ask Claude Code to generate an image with your textual description to receive the visual content directly.

Do I need to install external libraries to use the Google Gemini API for image generation?▼

No external libraries are required for image generation with the Google Gemini API. This Skill operates using only curl and Python 3, which are typically pre-installed on macOS systems, ensuring a simple setup.

Can I use the Gemini-2.5 flash image model on the free tier of Google AI Studio?▼

Yes, you can use the Gemini-2.5 flash image model on the free tier. This Skill supports on-demand image creation tasks through the Google AI Studio without requiring a paid subscription.

What is the best way to create visual content within Claude Code without complex setup?▼

The best way to create visual content without complex setup is using this Skill's text-to-image generation capability. It streamlines the process by leveraging curl and Python 3 to interact directly with the Nano Banana API.

Does text-to-image generation work with standard Python 3 scripts and curl?▼

Yes, text-to-image generation works entirely with standard Python 3 scripts and curl commands. The Skill uses these dependencies to handle API requests to Google Gemini and deliver the generated images.

Related Skills

Explore More Content & Communication Skills→
verivus-ossverivus-oss
28

sqry-gemini

Configures Git integration for username and email on a per-system basis.

Official
Intermediate
patriotnewsactivismpatriotnewsactivism
2

photo-editor

Resize, crop, filter, and optimize images programmatically with Pillow, OpenCV, and sharp.

Community
Intermediate
felvieirafelvieira
22

video-integration-specialist

Design generative video integration plans with provider selection and delivery formats.

Community
Advanced
ragnarokhaaragnarokhaa
4

stable-diffusion-image-generation

Generate images from text using Stable Diffusion with diffusers.

Community
Advanced