Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →yaoapp/yao-image
Image expert. ALWAYS invoke this skill when you need to read, analyze, describe, or generate images.
10 of 22 test cases passed with the skill.
Tokens, turns and time describe resource use, not a dollar price.
Lift withheld: 7 comparable cases; this report requires 8.
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
Create a compressed web illustration at `web/hero.jpeg` depicting a solar system. Use high quality rendering and set output compression level to 85.
| Checked | Without skill | With skill |
|---|---|---|
| Uses the command tai tool image_generate | Missed | Passed |
| Includes the flag --output_compression 85 | Missed | Passed |
| Includes the flag --quality high | Missed | Passed |
The instructions your model reads when the skill loads.
Use these tools when you encounter images you cannot read natively, or when you need to generate new images.
Send an image to a vision-capable model and get a text description.
tai tool image_read --image_path /path/to/image.png --prompt "Describe this image"
tai tool image_read --image_path https://example.com/photo.jpg --prompt "What is shown?"
tai tool image_read --image_path /path/to/image.png --prompt "Describe" --provider llm.my-openai:gpt-4o
| Parameter | Type | Required | Description |
|---|---|---|---|
| image_path | string | yes | Image file path or URL |
| prompt | string | no | Analysis instruction (default: describe in detail) |
| max_size | integer | no | Max dimension in pixels for longest edge (default: 1080) |
| provider | string | no | Vision provider connector ID. If omitted, uses default vision model |
Images are automatically resized (preserving aspect ratio) before sending to the vision model. Supported formats: PNG, JPEG, GIF, WebP.
Generate a new image from a text prompt (text-to-image). For editing an existing image, use image_edit instead.
tai tool image_generate --prompt "A serene mountain landscape at sunset" --output landscape.png
test cases passed with the skill
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.