google-image

Generate images, animations, slides, and web mockups via Gemini CLI.

2|Updated Feb 10, 2026
One-click install
npx skills add https://github.com/japhet19/gemini-image-skill --skill google-image
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: google-image
Source: https://github.com/japhet19/gemini-image-skill/tree/main
Command: npx skills add https://github.com/japhet19/gemini-image-skill --skill google-image

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires jq, python-pptx, ffmpeg, imagemagick, webp, poppler, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill automates the creation of high-quality AI-generated images, animations, presentation slides, and web mockups directly from text prompts, eliminating the need for complex software or manual design work.

Core Features & Use Cases

  • Image Generation: Create diverse visuals from simple descriptions to complex structured prompts.
  • Web Design Mockups: Generate landing pages, dashboards, and mobile layouts with specific presets.
  • Animations: Produce frame-by-frame animations as GIFs, WebPs, or MP4s.
  • Presentation Slides: Automate the creation of PPTX slides with AI-generated visuals and speaker notes.
  • Image Editing: Modify existing images using natural language commands.
  • Use Case: A marketer needs a hero image for a new product launch. They can describe the product and desired style, and the Skill generates multiple options, which can then be refined or used to create accompanying social media graphics and ad banners.

Quick Start

Use the google-image skill to generate an image of a red apple on a white background.

Frequently Asked Questions about google-image

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

FAQPage Schema
How do I generate AI images from text prompts using Gemini CLI?

To generate AI images from text prompts using Gemini CLI, you provide a text description and the system creates diverse visuals. It supports simple descriptions and complex structured prompts to produce high-quality graphics without manual design work.

Can I create presentation slides automatically with AI-generated visuals?

Yes, you can create presentation slides automatically with AI-generated visuals. The system automates PPTX slide creation from JSON plans, incorporating AI imagery and speaker notes directly into your presentation deck.

Do I need Node.js and the nanobanana extension to generate web mockups?

Yes, you need Node.js, the Gemini CLI, and the nanobanana extension to generate web mockups. These dependencies are required for the system to produce landing pages, dashboards, and mobile layouts using web design presets.

How does animation sequencing work for generating GIFs and MP4s?

Animation sequencing works by generating frame-by-frame visuals that are compiled into GIFs, WebPs, or MP4s. The system uses ffmpeg to process the sequence, producing animated output directly from your text prompts.

What's the best way to edit existing images using natural language commands?

The best way to edit existing images using natural language commands is through the system's image editing feature. You simply provide natural language instructions to modify images, leveraging Imagemagick and the Gemini CLI for processing.