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.

Choosing and evaluating RAG chunking v1.0.0

Use this resource to choose and evaluate a document chunking strategy for RAG

New

  • 409 downloads
  • 131 likes
  • 153 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install rag-chunking-strategy

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 recommends a chunk size (256 to 1024 tokens), an overlap (10 to 20%) and a method for detecting semantic boundaries based on your documents. It checks chunk coherence and measures retrieval precision and recall.

Mostly picked by

Updated November 2, 2026

Card for the “Choosing and evaluating RAG chunking” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: three-step method, from choice to validation
  • references/strategies.md and semantic-methods.md: strategies and semantic methods
  • references/evaluation.md: precision and recall measures

Good fit for

  • Your RAG returns passages cut in the middle of an idea
  • You process long documents before indexing them

Not for

    Tags

    • chunking
    • rag
    • embeddings
    • evaluation

    About

    You say

    “What chunk size should I use for my 80-page reports in RAG?”

    Card for the “Choosing and evaluating RAG chunking” skill

    Skill published by giuseppe-trisciuoglio 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 choose and evaluate a document chunking strategy for RAG
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/advanced-strategies.md47.9 KB
    • references/evaluation.md31.3 KB
    • references/implementation.md25.9 KB
    • references/research.md12 KB
    • references/semantic-methods.md50.3 KB
    • references/strategies.md13.6 KB
    • references/tools.md19.3 KB
    • references/visualization-tools.md49.2 KB
    • SKILL.md6.6 KB

    Origin and licence

    Listed unmodified

    Author
    giuseppe-trisciuoglio
    Source
    github.com/giuseppe-trisciuoglio/developer-kit/tree/fe73fb33a09ee6562eeec7415a3f9a3bcf795177/plugins/developer-kit-ai/skills/chunking-strategy
    Licence
    MIT

    Notice

    « chunking-strategy » (giuseppe-trisciuoglio, 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.