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.

LLM agent evaluation and testing v1.0.0

Use this resource to test and measure the reliability of an LLM agent

New

  • 380 downloads
  • 186 likes
  • 174 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install llm-agent-evaluation-tests

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 designs behavioral tests for an LLM agent: statistical tests across several runs, behavioral contracts and adversarial tests. It avoids pitfalls such as single-run testing or matching output strings. You get a test suite and reliability indicators.

Mostly picked by

Updated November 2, 2026

Card for the “LLM agent evaluation and testing” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: assessed capabilities, requirements and test patterns
  • sub-skills/: statistical tests, behavioral contracts, adversarial tests and anti-patterns to avoid

Good fit for

  • Your agent passes demos but fails in production
  • You want to compare two versions of an agent on measurable criteria

Not for

    Tags

    • evaluation
    • agents
    • testing
    • reliability

    About

    You say

    “Write a test suite for my support agent, with ten runs per case and adversarial cases.”

    Card for the “LLM agent evaluation and testing” skill

    Skill published by dokhacgiakhoa 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 and measure the reliability of an LLM agent
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE2.4 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md1.6 KB
    • sub-skills/adversarial-testing.md0.1 KB
    • sub-skills/behavioral-contract-testing.md0.1 KB
    • sub-skills/only-happy-path-tests.md0 KB
    • sub-skills/output-string-matching.md0.7 KB
    • sub-skills/single-run-testing.md0 KB
    • sub-skills/statistical-test-evaluation.md0.1 KB

    Origin and licence

    Listed unmodified

    Author
    dokhacgiakhoa
    Source
    github.com/dokhacgiakhoa/agent-skills-4-vibe-coding-cli/tree/c4a059bbf7a8d6b2162071f0fbfe74053faa6d20/.agent/skills/agent-evaluation
    Licence
    MIT

    Notice

    « agent-evaluation » (dokhacgiakhoa, 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.