Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

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.

Testing language model integrations v1.0.0

Use this resource to test an LLM integration and check the quality of its outputs

New

  • 300 downloads
  • 132 likes
  • 243 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install llm-output-testing-patterns

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 sets up mocked responses for deterministic tests, writes quality evaluations with DeepEval or RAGAS and validates structured output formats. It also applies the agentic workflow that repairs broken tests.

Mostly picked by

Updated November 2, 2026

Card for the “Testing language model integrations” skill

Details

Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md: overview, mock setup and quality thresholds
  • rules/: output evaluation and mocking of model responses
  • references/healer-agent.md: agent that repairs broken tests

Good fit for

  • You test a feature that relies on a language model
  • You want deterministic CI tests that do not call the model

Not for

    Tags

    • llm tests
    • evaluation
    • structured output

    About

    You say

    “Add tests that check the JSON format of the model's response, with no network call.”

    Card for the “Testing language model integrations” skill

    Skill published by yonatangross 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 test an LLM integration and check the quality of its outputs
    3. Review and adjust the result

    Content preview

    Files

    • checklists/llm-test-checklist.md2.9 KB
    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/healer-agent.md1.9 KB
    • references/langfuse-v4.md3.1 KB
    • references/ork-delta.md7 KB
    • rules/_sections.md0.4 KB
    • rules/llm-evaluation.md3.4 KB
    • rules/llm-mocking.md3.7 KB
    • SKILL.md10.3 KB
    • test-cases.json2.4 KB

    Origin and licence

    Listed unmodified

    Author
    yonatangross
    Source
    github.com/yonatangross/orchestkit/tree/18a6aaa53d9971ef094b0758b08dfc606a1ea4bc/src/skills/testing-llm
    Licence
    MIT

    Notice

    « testing-llm » (yonatangross, 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.