Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

Image classification and image-text search with CLIP v1.0.0

Use this resource to classify images without training and search images by text

New

  • 529 downloads
  • 175 likes
  • 138 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install image-text-zero-shot-clip

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent loads a CLIP model, computes the similarity between an image and a list of labels or texts, then displays ranked results. You get match scores to classify or search images.

Mostly picked by

Updated November 2, 2026

Card for the “Image classification and image-text search with CLIP” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md: installation, model loading and zero-shot classification
  • references/applications.md: use cases such as semantic search and moderation

Good fit for

  • You need to classify images with no labelled dataset
  • You want to find visuals in a library from a sentence

Not for

    Tags

    • clip
    • vision
    • classification
    • image-search
    • model

    About

    You say

    “Classify these product photos as: shoe, bag, watch.”

    Card for the “Image classification and image-text search with CLIP” skill

    Skill published by Orchestra Research under the MIT license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to classify images without training and search images by text
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/applications.md5.2 KB
    • SKILL.md6.5 KB

    Origin and licence

    Listed unmodified

    Author
    Orchestra Research
    Source
    github.com/nousresearch/hermes-agent/tree/0c74cc682dc81bf78b78a1737b3ee77a820ccb79/optional-skills/mlops/clip
    Licence
    MIT

    Notice

    « clip » (Orchestra Research, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.