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.

File-based RAG quality evaluation v1.0.0

Use this resource to measure the retrieval and answer quality of a RAG system

New

  • 374 downloads
  • 217 likes
  • 243 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install rag-quality-evaluation-benchmark

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 prepares the corpus and test file, runs the evaluation script, adjusts retrieval and generation options to compare results, then analyzes the RAGAS scores and failures. You get a reproducible quality measurement.

Mostly picked by

Updated November 2, 2026

Card for the “File-based RAG quality evaluation” skill

Details

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

Similar resources

View all

What you get

  • references/dataset-and-conversion.md: corpus and test set preparation
  • references/evaluate-rag-cli.md and benchmark-execution.md: running the evaluation
  • references/result-analysis.md: reading the results

Good fit for

  • You change the embedding model and want to compare answers
  • A document assistant sometimes gives wrong answers

Not for

    Tags

    • rag
    • evaluation
    • ragas
    • retrieval

    About

    You say

    “Evaluate our documentation RAG on the help corpus and compare it with the previous version.”

    Card for the “File-based RAG quality evaluation” skill

    Skill published by practicalswan 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 measure the retrieval and answer quality of a RAG system
    3. Review and adjust the result

    Content preview

    Files

    • BENCHMARK.md2.9 KB
    • CHANGELOG.md5.1 KB
    • eval/h100.json2.9 KB
    • eval/nvidia_hosted.json1.9 KB
    • LICENSE1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/benchmark-execution.md8.3 KB
    • references/dataset-and-conversion.md8.3 KB
    • references/evaluate-rag-cli.md4.3 KB
    • references/result-analysis.md2.9 KB
    • skill-card.md2.7 KB
    • SKILL.md10.9 KB
    • skill.oms.sig5.7 KB

    Origin and licence

    Listed unmodified

    Author
    practicalswan
    Source
    github.com/practicalswan/agent-skills/tree/6cf63517700aa9ba0b80e711a93837e3bea13d0a/rag-eval
    Licence
    Apache-2.0

    Notice

    « rag-eval » (practicalswan, 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.