Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →mkurman/clip
OpenAI CLIP — contrastive language-image pre-training. Zero-shot image classification, image-text similarity, concept search, and cross-modal retrieval. Embed images and text into shared space.
Passed 20 of 24 test cases with the skill, and 12 of 24 without it.
and 9 more in the full report
8 fixed12 passed either way4 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
I am setting up an environment with the uv package manager for multimodal research. What exact terminal command should I run to install the official OpenAI CLIP package?
| Checked | Without skill | With skill |
|---|---|---|
| The command uses uv pip install openai-clip. | Missed | Passed |
The instructions your model reads when the skill loads.
OpenAI CLIP (Contrastive Language-Image Pre-training) learns joint text-image representations. Enables zero-shot image classification, image-text similarity, cross-modal search, and image captioning without task-specific training.
uv pip install openai-clip
import clip
import torch
model, preprocess = clip.load("ViT-B/32")
image = preprocess(load_image("photo.jpg")).unsqueeze(0)
text = clip.tokenize(["a dog", "a cat", "a bird"])
with torch.no_grad():
logits, _ = model(image, text)
probs = logits.softmax(dim=-1)
print(f"Predicted: class {probs.argmax().item()} with {probs.max():.2%} confidence")
images = torch.stack([preprocess(img) for img in [load_image("a.jpg"), load_image("b.jpg")]])
texts = clip.tokenize(["sunset", "ocean", "mountain"])
with torch.no_grad():
similarity = model(images, texts)[0].softmax(dim=-1)
test cases passed, vs 12 / 24 without
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.