generate-image

Generate images from entity file prompts and embed references.

4|Updated Jan 21, 2026
One-click install
npx skills add https://github.com/hopeoverture/Worldbuilding-System --skill generate-image-hopeoverture
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: generate-image
Source: https://github.com/hopeoverture/Worldbuilding-System/tree/main/.claude/skills/generate-image
Command: npx skills add https://github.com/hopeoverture/Worldbuilding-System --skill generate-image-hopeoverture

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill automates image creation for worldbuilding entities by extracting the prompt from the entity file and generating a visual asset using an AI image model, then updates the entity to reference the generated image.

Core Features & Use Cases

  • Prompt-driven image generation: Reads the filled prompt from an entity file and generates a matching image.
  • Automated asset linking: Saves the generated image locally and updates the entity with a reference to the file.
  • Use Case: Produce consistent character portraits, settlement visuals, or item illustrations for worldbuilding projects.

Quick Start

Use the generate-image skill to create an image for an entity by providing its path or name. The skill will locate the entity, extract the appropriate prompt, generate the image using the gpt-image-1.5 model, save it next to the entity file, and embed a reference to the image in the entity.

Frequently Asked Questions about generate-image

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

FAQPage Schema
How do I generate images for worldbuilding entities automatically?

To generate images for worldbuilding entities, this skill extracts prompts from entity files, creates visuals using the gpt-image-1.5 model, and embeds the image reference back into the entity automatically.

What is the best way to add consistent visual assets to a worldbuilding project?

The best way to add consistent visual assets is using prompt-driven image generation, which reads prompts from entity files, generates matching images, and saves them locally next to the entity file.

How does prompt extraction work for automated image generation?

Prompt extraction for automated image generation works by reading the filled prompt field within an entity file, passing it to the gpt-image-1.5 model, and updating the entity with the downloaded image file reference.

Can I use this automated image generation for characters, settlements, and items?

Yes, you can use this automated image generation for characters, settlements, items, creatures, and geography, producing consistent portraits and illustrations across all worldbuilding workflows.

How do I start generating worldbuilding images for an entity?

To start generating worldbuilding images, provide the entity's path or name to the skill, which then locates the entity, extracts the prompt, generates the image, and embeds the reference.