generate-image

Generate images from descriptive prompts using Google's Gemini 3 Pro API.

2|Updated Nov 13, 2025

Search Tags:#automation #presentations #api #image generation #CLI #slides #Gemini 3 Pro

Ready to run

npx skills add https://github.com/yermilov/pragmatic-vibe-clauding-ua --skill generate-image-yermilov

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: generate-image
Source: https://github.com/yermilov/pragmatic-vibe-clauding-ua/tree/main/.claude/skills/generate-image
Command: npx skills add https://github.com/yermilov/pragmatic-vibe-clauding-ua --skill generate-image-yermilov

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @google/genai, and includes scripts (resource) components.

What problem does it solve?

This Skill automates the creation of high-quality images for slides and visual content by leveraging Google's Gemini 3 Pro API, saving hours of manual design and iteration.

Core Features & Use Cases

Automated Image Generation: Generate images from descriptive prompts for decks, presentations, and social visuals.
Aspect Ratio Support: Generate with common ratios (16:9, 4:3, 1:1, 4:5) to fit slide and asset requirements.
Output & API Key Management: Images saved to src/assets/generated; GEMINI_API_KEY is used securely via .env.local.

Quick Start

bun --env-file=.env.local .claude/skills/generate-image/scripts/generate.ts
--prompt "Abstract dark terminal with glowing code, cyberpunk aesthetic"
--ratio "16:9"
--output "slide-background.png"