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.

Designing a RAG system v1.0.0

Use this resource to design a RAG system that answers from your documents

New

  • 374 downloads
  • 151 likes
  • 237 saves

Free

Install with the CLI

In a terminal, from the folder you want:

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

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 describes the ingestion, chunking, indexing and retrieval pipeline, then picks the vector storage and the hybrid search and reranking settings. It stresses grounding answers in cited passages and evaluating retrieval and generation separately.

Mostly picked by

Updated November 2, 2026

Card for the “Designing a RAG system” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
Apache-2.0

Similar resources

View all

What you get

  • SKILL.md: pipeline, chunking, hybrid retrieval and evaluation
  • references/VECTOR_STORES.md: choosing vector stores
  • references/ADVANCED_RETRIEVAL.md: advanced retrieval techniques

Good fit for

  • An assistant must answer from your internal documentation
  • Your RAG ignores passages that are indexed

Not for

    Tags

    • RAG
    • embeddings
    • vector search
    • citations

    About

    You say

    “Design a RAG that answers our customers' questions from the product documentation, with citations.”

    Card for the “Designing a RAG system” skill

    Skill published by personamanagmentlayer 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 design a RAG system that answers from your documents
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE10.9 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/ADVANCED_RETRIEVAL.md6.4 KB
    • references/VECTOR_STORES.md7.6 KB
    • SKILL.md10.8 KB

    Origin and licence

    Listed unmodified

    Author
    personamanagmentlayer
    Source
    github.com/personamanagmentlayer/pcl/tree/79ccaa9820486121fa33aaa696ec16fa1607bf02/stdlib/ai/rag-expert
    Licence
    Apache-2.0

    Notice

    « rag-expert » (personamanagmentlayer, 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.