This skill allows an agent to generate multiple images based on a single prompt or a set of random but structured prompts using OpenAI's latest image generation models. It automates the process of calling the API and organizes the output into a local HTML gallery for easy review.
Use this skill when the user needs visual assets, mockups, or a series of conceptual images. It is particularly useful for exploring different styles (e.g., vivid vs natural) or sizes across different OpenAI models.
gen.py for handling the API requests, prompt sampling, and HTML gallery generation.Designed for agents with shell access and Python capabilities (e.g., OpenClaw, Claude Code, Cursor).
This skill has not been reviewed by our automated audit pipeline yet.