Clip Aware Embeddings

Name: Clip Aware Embeddings
Author: curiositech

Listed

curiositech·vlatest·ai-ml·MIT

This skill generates CLIP-aware embeddings for images and text, enabling powerful semantic search and similarity matching across diverse content.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

Run this in your project

terminal

$ npx skills add curiositech/some_claude_skills --skill clip-aware-embeddings -a claude-code

Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

curiositech

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned 5 Oct 2026

This skill failed 1 of 6 checks. A failure is not proof of bad intent; it means something in the code needs a human to look at it before you run it.

Declares what it does: failed
No SKILL.md was found in the skill's directory.
SKILL.md exists, its frontmatter parses, and it declares a name and a description.
No undeclared network calls: passed
Makes no network calls.
Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.
No obfuscated payloads: passed
No encoded or obfuscated payloads.
No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.
No credential access: passed
Reads no keys, tokens, keychains or credential files.
Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.
No pipe-to-shell installers: passed
No pipe-to-shell or download-and-run installers.
No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.
Pinned to a commit: passed
Scanned curiositech/some_claude_skills at 6713fc7a64.
The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit: 6713fc7a64
Manifest: .claude/skills/clip-aware-embeddings/SKILL.md
Scanned: 0 files

This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.

What each check looks for →

About this skill

What it does

This skill generates embeddings that are aware of visual information. It allows for semantic search and comparison across both text and images, enabling the AI agent to understand relationships between different modalities. The embeddings leverage CLIP (Contrastive Language–Image Pre-training) models for this cross-modal understanding.

When to use it

Image Search: Find images relevant to a textual description or vice versa.
Content Moderation: Identify potentially harmful content by comparing image and text descriptions.
Cross-Modal Retrieval: Retrieve related information from datasets containing both images and text, such as product catalogs or research papers.
Visual Question Answering (VQA): Improve the accuracy of VQA systems by grounding answers in visual context.

Key capabilities

CLIP-aware embeddings generation
Cross-modal semantic search
Image-text comparison
Integration with CLIP models

Example prompts

"Find images similar to this description: 'a fluffy cat sleeping on a windowsill'."
"What text best describes this image [image data]?"
"Compare the similarity between the text 'red apple' and the image of a green apple."

Tips & gotchas

The quality of results depends heavily on the underlying CLIP model’s training data. Ensure your input images are clear and representative for optimal performance.