What image formats does it support?

PNG, JPEG, GIF, and WebP. The skill errors if a file is not a supported image.

What happens to large images?

The skill automatically resizes and compresses them before loading them into context. Extremely large images are rejected by pixel count before full processing.

Does it change the original file?

No. The original file is left untouched.

Attach Image

SkillMedia

attach-image is a skill that loads an image file from disk into the model's context as a viewable attachment, so a vision-capable model can directly see it. It is meant for screenshots, diagrams, charts, photos, and scanned pages, and it supports PNG, JPEG, GIF, and WebP. Large images are resized or compressed before loading, and the original file is left untouched.

Connect your AI Use it in a pipeline

Then ask your AI: use the Attach Image skill

Details

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Account requirements not reviewed. Check the skill instructions before use; Ahel provides instructions and does not run this skill.

No other account needed.

Have a vision-capable model available, since the skill errors clearly if the current model is not vision-capable.

What your AI can do with it

Load a PNG, JPEG, GIF, or WebP file into the model's context
Attach several images at once with attach_image("a.png", "b.jpg")
Resize and compress large images before they are loaded
Flatten animated images to their first frame when compression is needed
Composite transparent images onto a neutral gray background when compressing
Reject extremely large images by pixel count before full processing

Getting started

Have a vision-capable model available, since the skill errors clearly if the current model is not vision-capable.
Make sure the image file is on disk in PNG, JPEG, GIF, or WebP format.
Call the prepared attach_image import in the Python kernel, for example print(await attach_image("diagram.png")).
Pass more than one path to attach several images in the same call, for example attach_image("a.png", "b.jpg").

What this skill tells your AI

The instructions your AI receives, as published by primeintellect-ai/prime-agent in skills/attach-image/SKILL.md and read by Ahel’s review.

Load on-disk images into the model's context as multimodal attachments. The image is sent to the model the same way a pasted image is, so the model can actually look at it.

When to use this

The user points at an image file and wants you to look at it.
You need to read text, a chart, a diagram, or a layout from an image.
A screenshot needs visual interpretation.

When NOT to use this

For programmatic work on an image — measuring pixels, cropping, resizing, computing a hash, comparing files byte-by-byte — open it in the kernel with a library instead:

from PIL import Image
img = Image.open("diagram.png")
print(img.size)

That path does not put the image in the model's context; it only lets you compute over it. Use attach_image when you need to see the image.

Usage

Call the prepared attach_image import directly in the Python kernel:

print(await attach_image("diagram.png"))
print(await attach_image("a.png", "b.jpg"))

The skill automatically resizes and compresses large images before loading them into context. Animated images that need compression are flattened to their first frame. Transparent images that need compression are composited onto a neutral gray background. Extremely large images are rejected by pixel count before full processing. The original file is left untouched.

Supported formats: PNG, JPEG, GIF, WebP. The skill errors if a file is not a supported image, or if the current model is not vision-capable.

Signals

GitHub stars: 22k
Forks: 2k
Last commit: Oct 2026

Questions

What image formats does it support?: PNG, JPEG, GIF, and WebP. The skill errors if a file is not a supported image.
Does it require a vision-capable model?: Yes. The skill errors clearly if the current model is not vision-capable.
What happens to large images?: The skill automatically resizes and compresses them before loading them into context. Extremely large images are rejected by pixel count before full processing.
Does it change the original file?: No. The original file is left untouched.

Advanced

Item type: skill
Key: attach-image
Source: github.com/primeintellect-ai/prime-agent

github.com/primeintellect-ai/prime-agent