openai-images-video

Directory structure

skills/openai-images-video/
  SKILL.md
  references/
    images/
      README.md
      image-generation.md
      image-generation-tool.md
      moderation-and-errors.md
    vision/
      README.md
      image-input.md
      image-tokens-and-limitations.md
      vision-fine-tuning.md
    video/
      README.md
      video-generation.md
      video-references-and-characters.md
      video-extend-and-edit.md
      video-batch-and-library.md
  samples/
    README.md
    image-generation.md
    image-editing-mask.md
    image-editing-reference.md
    image-generation-tool.md
    vision-image-understanding.md
    video-generation-sora.md
    video-status-polling-download.md
  scripts/
    README.md
    image-generation.md
    video-generation.md
    vision-input.md

Exploration procedure

Look up the category from the task, and identify the target page in the category's README.md:

1. Find the category corresponding to the task in the mapping table below
2. For that category, references/{category}/README.md refer to and identify the target page
3. For the relevant page, .md Read to check the details

Task → Category Mapping

Task	Category	Reference README
Text-to-image generation,images.generate / images.edit standalone calls to	images	references/images/README.md
Image editing using mask / reference images, Responses API's image_generation tools, moderation and error handling	images	references/images/README.md
Passing image input (vision) to Responses/Chat Completions,detail level specification	vision	references/vision/README.md
image token cost calculation, vision constraints, vision fine-tuning	vision	references/vision/README.md
Video generation with Sora, videos endpoint job lifecycle and polling	video	references/video/README.md
Video extend / edits, characters / reference frame, batch rendering and library management	video	references/video/README.md
Want to know typical usage	samples	samples/README.md
Want to call Images / Videos / vision endpoints directly with curl	scripts	scripts/README.md

Notes

• The basic call format of the Responses API (common specifications for input/output, streaming, and tool calling) is handled by openai-api-core is in charge
• The overall framework of built-in tools (web search / file search / code interpreter, etc.) is handled by openai-agents is in charge. This skill's image_generation tools are treated as the image-generation-specialized page within that