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

PalateKit

Menu

Request a resource

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

0 / 280

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.

Segmenting text into contextual chunks for RAG v1.0.0

Use this resource to split text into contextual chunks for RAG or embeddings

New

  • 441 downloads
  • 139 likes
  • 116 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install text-segmentation-for-rag

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 picks the segmentation strategy that fits (window divergence, TF-IDF, punctuation or hybrid NCD and TF-IDF), sets segment size and threshold, then writes the segments to the chosen folder. You get text chunks ready for indexing or similarity analysis.

Mostly picked by

Updated November 2, 2026

Card for the “Segmenting text into contextual chunks for RAG” skill

Details

Generates with
Your agent's model
Licence
Apache-2.0

Similar resources

View all

What you get

  • SKILL.md: strategy options, segment sizes and divergence threshold
  • SKILL.md: command examples and custom output prefix

Good fit for

  • You are preparing a long document for a RAG pipeline
  • You want to split a text into coherent sections for similarity analysis

Not for

    Tags

    • segmentation
    • rag
    • chunking
    • tf-idf
    • embeddings

    About

    You say

    “Split this report into segments with the TF-IDF strategy for my embeddings pipeline.”

    Card for the “Segmenting text into contextual chunks for RAG” skill

    Skill published by trkbt10 under the Apache-2.0 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 split text into contextual chunks for RAG or embeddings
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE10.6 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md2.6 KB

    Origin and licence

    Listed unmodified

    Author
    trkbt10
    Source
    github.com/trkbt10/indexion-skills/tree/7ad5ad35a6688db2f8765c1b270c9f6473da3a51/skills/indexion-segment
    Licence
    Apache-2.0

    Notice

    « indexion-segment » (trkbt10, Apache-2.0) 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.