Update to EmpirioLabs AI

{
  "description": "Create an image from a description. Use when the user asks to generate, draw, design or illustrate a picture, photo, logo, poster or artwork.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 216
    }
  ],
  "name": "ai-image-generator",
  "skill_md_contents": "---\nname: ai-image-generator\ndescription: Create an image from a description. Use when the user asks to generate, draw, design or illustrate a picture, photo, logo, poster or artwork.\n---\n# Create an image\n\n1. Write one clear prompt from the request: subject, setting, style, lighting, and any words that must appear in the image, in quotes.\n2. Call `generate_image` with the `prompt`. Set `model` only when the user names one, and leave it out otherwise. Set `aspect_ratio` when the user asks for a shape (for example `16:9`, `9:16` or `1:1`) and `num_images` when they ask for several.\n3. If the result is still generating, call `get_job` with the job id, and again until the image is ready. Never start the same image twice.\n4. Reply with the image link, the model that made it and the prompt you sent.\n\nTo change the picture afterwards, send a new prompt, or call `edit_image` with the image link when the user wants the same picture altered. To choose a model, call `list_models` with `modality` set to `image`.\n"
}