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.

Chunking documents for LLMs and RAG v1.0.0

Use this resource to split extracted text into chunks for an LLM or a vector database

New

  • 312 downloads
  • 169 likes
  • 156 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install document-text-chunking

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 sets chunk size and overlap, picks the chunker (Markdown, YAML, semantic) and can size chunks in tokens. You get chunks ready for ingestion, during extraction or with the chunk command.

Mostly picked by

Updated November 2, 2026

Card for the “Chunking documents for LLMs and RAG” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: chunking during extraction and the chunk command
  • references/configuration.md and advanced-features.md: options and chunkers

Good fit for

  • You index PDFs into a vector database
  • Your chunks cut sentences or headings in half

Not for

    Tags

    • chunking
    • rag
    • chunks
    • overlap
    • llm

    About

    You say

    “Split this report into 1000-character chunks with 200 characters of overlap for my RAG.”

    Card for the “Chunking documents for LLMs and RAG” skill

    Skill published by xberg-io 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 split extracted text into chunks for an LLM or a vector database
    3. Review and adjust the result

    Content preview

    Files

    • index.md0.5 KB
    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/advanced-features.md18.6 KB
    • references/cli-reference.md12.9 KB
    • references/configuration.md33.6 KB
    • references/nodejs-api.md13.6 KB
    • references/other-bindings.md8.9 KB
    • references/python-api.md31.4 KB
    • references/rust-api.md12.8 KB
    • references/supported-formats.md20.3 KB
    • SKILL.md6.3 KB

    Origin and licence

    Listed unmodified

    Author
    xberg-io
    Source
    github.com/xberg-io/xberg/tree/82b2f67583c3f2b7b14b67e62bdf949ee5601320/skills/xberg-chunking
    Licence
    MIT

    Notice

    « xberg-chunking » (xberg-io, 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.