create-image

Orchestrate specialized agents to generate images via the Gemini 3 Pro API.

1|Updated Feb 13, 2026
One-click install
npx skills add https://github.com/noahrasheta/shipfast --skill create-image
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: create-image
Source: https://github.com/noahrasheta/shipfast/tree/main/create-image/skills/create-image
Command: npx skills add https://github.com/noahrasheta/shipfast --skill create-image

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires google-genai, Pillow, python-dotenv, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the complex process of generating high-quality, professional images based on user descriptions, eliminating the need for manual prompt engineering and multi-step agent coordination.

Core Features & Use Cases

  • Multi-Agent Orchestration: Leverages specialized agents for research, prompt architecture, generation, and critique.
  • Adaptive Requirements Gathering: Gathers detailed image specifications through structured, adaptive questioning.
  • Professional Output: Generates 5 variants of an image with detailed critiques and rankings.
  • Use Case: A marketing manager needs a vibrant, photorealistic image for a new product launch campaign. They describe the product and desired mood, and the skill generates multiple options with detailed feedback.

Quick Start

Use the create image skill to generate a photorealistic image of a cat wearing a party hat.

Frequently Asked Questions about create-image

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

FAQPage Schema
How do I generate professional AI art using a multi-agent pipeline?

AI image generation automates professional image creation by orchestrating specialized agents for research, prompt architecture, generation, and critique. This pipeline handles requirements gathering and outputs multiple variants with detailed rankings.

What is the best way to automate prompt engineering for AI image generation?

Automating prompt engineering is best achieved through a multi-agent pipeline that sequentially handles research, prompt architecture, generation, and critique. This approach eliminates manual prompt writing by gathering adaptive requirements to generate multiple professional image variants.

Do I need a Gemini API key to use a multi-agent image generation pipeline?

Yes, you need a Gemini API key to use this multi-agent image generation pipeline. The workflow requires specific Python dependencies including google-genai, Pillow, and python-dotenv to interact with the API and generate images.

Can I use Python and Pillow for AI image generation with Gemini?

Yes, you can use Python and Pillow for AI image generation with Gemini. The pipeline requires Python dependencies like google-genai for API interaction, Pillow for image processing, and python-dotenv for environment variable management.

Why does multi-agent image generation produce multiple variants?

Multi-agent image generation produces multiple variants to provide professional output options. The pipeline generates 5 image variants and includes a critique agent that provides detailed feedback and rankings to ensure high-quality results for use cases like marketing campaigns.