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.

Online evaluations with LLM judges on variations v1.0.0

Use this resource to automatically score an agent's response quality with LLM judges

New

  • 450 downloads
  • 175 likes
  • 192 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install online-llm-judge-evaluations

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 or picks judges, attaches them to variations, sets the sampling rate and fallback value, then tracks quality scores. Each judge returns a score between 0 and 1. You get continuous evaluation of your responses.

Mostly picked by

Updated November 2, 2026

Card for the “Online evaluations with LLM judges on variations” 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: creating custom judges, attaching them and setting the fallback
  • README.md: prerequisites, compatible server SDKs and built-in judges

Good fit for

  • Your agent passes tests but its real quality is unknown
  • You want to catch a regression after a prompt change

Not for

    Tags

    • evaluation
    • llm judge
    • quality
    • sampling
    • scores

    About

    You say

    “Attach a relevance judge to 10% of the support variation's replies and track the scores.”

    Card for the “Online evaluations with LLM judges on variations” skill

    Skill published by launchdarkly 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 automatically score an agent's response quality with LLM judges
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE0.6 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • README.md1.3 KB
    • SKILL.md17.7 KB

    Origin and licence

    Listed unmodified

    Author
    launchdarkly
    Source
    github.com/launchdarkly/ai-tooling/tree/c26f86ad64ade56b205afea30a40f3a25f51983f/skills/agentcontrol/online-evals
    Licence
    Apache-2.0

    Notice

    « online-evals » (launchdarkly, 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.