codex-image

Generate images from natural language prompts via the ChatGPT backend.

361|58|Updated Mar 1, 2026
One-click install
npx skills add https://github.com/OpenMinis/MinisSkills --skill codex-image
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: codex-image
Source: https://github.com/OpenMinis/MinisSkills/tree/main/codex-image
Command: npx skills add https://github.com/OpenMinis/MinisSkills --skill codex-image

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Generates images on demand by leveraging Codex image_generation via the ChatGPT backend, removing manual image creation friction and enabling rapid visuals from natural language prompts.

Core Features & Use Cases

  • Auto-authenticated image generation through the ChatGPT session token, with cached tokens and browser-based login fallback.
  • Supports text-to-image and image-edit style prompts via the codex image endpoints.
  • Returns the generated image file path, size, and any revised prompt used by the generation.

Quick Start

Provide a prompt to generate an image using Codex image-generation workflow with automatic token resolution.

Frequently Asked Questions about codex-image

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

FAQPage Schema
How do I generate images from natural language prompts using the Codex image generation tool?

Generate images from text prompts by providing a natural language description to the Codex image generation workflow, which auto-authenticates via the ChatGPT session token and returns the image file path, size, and revised prompt.

Does Codex image generation require manual token authentication for text-to-image tasks?

Codex image generation does not require manual token authentication because the Skill auto-resolves ChatGPT session tokens, utilizing cached tokens and a browser-based login fallback to satisfy authentication requirements automatically.

Can I use the gpt-image-2 pipeline for image editing and UI concept art?

The Skill supports the gpt-image-2 pipeline for image editing and UI concept art by processing both text-to-image and image-edit style prompts via the Codex image endpoints to accelerate visual decision-making.

What is the best way to automate text-to-image generation via the ChatGPT backend?

Automating text-to-image generation via the ChatGPT backend is handled by the Codex image generation workflow, which auto-authenticates tokens and returns image paths with revised prompts for creative tasks.

What information does the Codex image generation workflow return after processing a prompt?

After processing a prompt, the Codex image generation workflow returns the generated image file path, the image size, and any revised prompt used by the generation process.