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.

Continuous RAG evaluation in CI v1.0.0

Use this resource to block RAG quality regressions in CI

New

  • 515 downloads
  • 183 likes
  • 171 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install rag-continuous-evaluation

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 creates a versioned golden dataset, writes regression tests with DeepEval or RAGAS in pytest, then schedules a nightly evaluation and a GitHub Actions workflow. You get a merge gate that blocks pull requests that lower quality.

Mostly picked by

Updated November 2, 2026

Card for the “Continuous RAG evaluation in CI” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: golden dataset as a fixture and merge gate with DeepEval and pytest
  • SKILL.md: nightly RAGAS evaluation, comparison against a baseline and GitHub Actions workflow

Good fit for

  • Each change to your RAG may break answers without you noticing
  • You want to track your RAG's quality over time

Not for

    Tags

    • rag
    • evaluation
    • ci
    • regression

    About

    You say

    “Add a merge gate to our CI that blocks a pull request if the faithfulness score drops by more than 5%.”

    Card for the “Continuous RAG evaluation in CI” skill

    Skill published by claude-dev-suite 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 block RAG quality regressions in CI
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md10.1 KB

    Origin and licence

    Listed unmodified

    Author
    claude-dev-suite
    Source
    github.com/claude-dev-suite/claude-dev-suite/tree/e10ab644ba43abe2abc923399226df4af7337214/skills/rag/continuous-evaluation
    Licence
    MIT

    Notice

    « continuous-evaluation » (claude-dev-suite, 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.