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.

Generating synthetic LLM test inputs v1.0.0

Use this resource to generate varied test inputs to evaluate an LLM pipeline

New

  • 543 downloads
  • 110 likes
  • 220 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install synthetic-eval-dataset

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 defines dimensions of variation tied to the failures you expect, drafts test tuples with you and has an LLM expand them into natural queries. It filters the results for quality before they run through the pipeline. You get a synthetic evaluation dataset.

Mostly picked by

Updated November 2, 2026

Card for the “Generating synthetic LLM test inputs” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: defining dimensions and generating tuples
  • SKILL.md: conversion to queries, quality filtering and anti-patterns

Good fit for

  • You are starting an evaluation set and lack enough real data
  • You want to stress-test a specific failure hypothesis

Not for

    Tags

    • synthetic data
    • test set
    • evaluation
    • llm

    About

    You say

    “Generate 50 test questions for my legal chatbot, covering international contracts and limitation periods.”

    Card for the “Generating synthetic LLM test inputs” skill

    Skill published by hamelsmu 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 generate varied test inputs to evaluate an LLM pipeline
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md5.4 KB

    Origin and licence

    Listed unmodified

    Author
    hamelsmu
    Source
    github.com/hamelsmu/evals-skills/tree/22418da2bfb159f28a1b0dcf64e969e14ae56c99/skills/generate-synthetic-data
    Licence
    MIT

    Notice

    « generate-synthetic-data » (hamelsmu, 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.