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.

Design a RAG system: chunking, index, retrieval, evaluation v1.0.0

Use this resource to design and evaluate a RAG system for document retrieval

New

  • 466 downloads
  • 155 likes
  • 159 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install rag-retrieval-pipeline-design

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 chunks documents with a suitable strategy, generates embeddings, configures a vector store and hybrid search with reranking, then evaluates retrieval quality. It suits applications that answer from internal documents.

Mostly picked by

Updated November 2, 2026

Card for the “Design a RAG system: chunking, index, retrieval, evaluation” skill

Details

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

Similar resources

View all

What you get

  • references/chunking-strategies.md and embedding-models.md: chunking and embedding choice
  • references/vector-databases.md, retrieval-optimization.md, rag-evaluation.md: index, retrieval and evaluation

Good fit for

  • Your assistant answers poorly because it retrieves the wrong passages
  • You are building semantic search over an internal document base

Not for

    Tags

    • rag
    • embeddings
    • search
    • vectors

    About

    You say

    “Design a RAG pipeline over our support PDFs: section-based chunking, hybrid search and a recall measure.”

    Card for the “Design a RAG system: chunking, index, retrieval, evaluation” skill

    Skill published by jeffallan 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 design and evaluate a RAG system for document retrieval
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/chunking-strategies.md25.4 KB
    • references/embedding-models.md15.5 KB
    • references/rag-evaluation.md24.5 KB
    • references/retrieval-optimization.md22.2 KB
    • references/vector-databases.md14.5 KB
    • SKILL.md8.1 KB

    Origin and licence

    Listed unmodified

    Author
    jeffallan
    Source
    github.com/jeffallan/claude-skills/tree/b7f220d32a0925c9bbfd24995e208e76bb74507c/skills/rag-architect
    Licence
    MIT

    Notice

    « rag-architect » (jeffallan, 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.