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.

Semantic deduplication of a corpus before indexing v1.0.0

Use this resource to remove near-duplicates from a corpus before indexing it

New

  • 594 downloads
  • 141 likes
  • 170 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install corpus-near-duplicate-removal

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 chains the detection levels (exact, MinHash with LSH, SimHash, embeddings with DBSCAN), sets thresholds and picks one representative per group. You get a cleaned corpus and the list of removed duplicates.

Mostly picked by

Updated November 2, 2026

Card for the “Semantic deduplication of a corpus before indexing” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: exact deduplication, MinHash with LSH and SimHash
  • SKILL.md: embedding clustering with DBSCAN, FAISS deduplication and group resolution

Good fit for

  • Your corpus contains repeated web pages or emails
  • Your search results return the same document several times

Not for

    Tags

    • deduplication
    • corpus
    • minhash
    • embeddings

    About

    You say

    “Deduplicate this corpus of 200,000 web pages before indexing and keep the longest version of each group.”

    Card for the “Semantic deduplication of a corpus before indexing” skill

    Skill published by claude-dev-suite 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 remove near-duplicates from a corpus before indexing it
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md8.7 KB

    Origin and licence

    Listed unmodified

    Author
    claude-dev-suite
    Source
    github.com/claude-dev-suite/claude-dev-suite/tree/e10ab644ba43abe2abc923399226df4af7337214/skills/embeddings/semantic-dedup
    Licence
    MIT

    Notice

    « semantic-dedup » (claude-dev-suite, 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.