OpenParable
Skip to content
← Back to skills

Draw Image

Design

Draw Image is an Agent Skill for design published in the ai-sns/ai-sns repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Generate an image from a text prompt using the default OpenAI-like LLM config (gpt-image-1-mini or compatible image generation API). The image is uploaded to the gofile.io public file sharing service and ONLY the public download page URL is returned.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/ai-sns/ai-sns/blob/HEAD/aisns_backend/skills/draw-image/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/draw-image-cc550a1c, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Draw Image

Generate images via the OpenAI-compatible images/generations endpoint using the default LLM configuration.

Parameters

This skill accepts a JSON object as input params.

  • prompt (string, required)

    • The text description of the image to generate.
  • size (string, optional)

    • Image dimensions. Default: 1024x1024
    • Common values: 1024x1024, 1792x1024, 1024x1792
  • model (string, optional)

    • The image generation model name. Default: gpt-image-1-mini
  • quality (string, optional)

    • Image quality. Values: low, medium, high. Default: low
  • n (integer, optional)

    • Number of images to generate. Default: 1

How to use

  1. Call read_skill with skill_key: "draw_image" to read this document.
  2. Then call run_doc_skill with skill_key: "draw_image" and params.

Example:

{
  "skill_key": "draw_image",
  "prompt": "A futuristic cityscape at sunset with flying cars",
   "size": "1024x1024"

}

Output

The runner prints a JSON object to stdout with:

  • ok (bool): Whether the generation and upload succeeded.
  • download_page (string): The public gofile.io download page URL of the generated image. Only this URL is returned as the result. Open this URL in a browser to download the generated image.
  • note (string): A short hint explaining that download_page is used to download the generated image.
  • error (string): Error message on failure.

Example success output:

{
  "ok": true,
  "download_page": "https://gofile.io/d/WcWZKt",
  "note": "Use this URL to download the generated image."
}