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.

Writing a code evaluator for a failure mode v1.0.0

Use this resource to write a code evaluator for a failure mode defined by an objective rule

New

  • 567 downloads
  • 102 likes
  • 242 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install code-based-llm-evaluator

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 states the rule, writes a check in your project's language and eval framework, then tests it on passing, failing and borderline cases. If the rule needs interpretation, it points to writing an LLM judge instead.

Mostly picked by

Updated November 2, 2026

Card for the “Writing a code evaluator for a failure mode” 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: rule statement, implementation and tests
  • SKILL.md: code evaluator examples

Good fit for

  • An LLM output format must match a schema
  • You want to check an objective rule on every trace

Not for

    Tags

    • evaluator
    • code
    • llm
    • tests

    About

    You say

    “Write a code evaluator that checks each answer contains valid JSON with the required fields.”

    Card for the “Writing a code evaluator for a failure mode” skill

    Skill published by ai-evals-course 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 write a code evaluator for a failure mode defined by an objective rule
    3. Review and adjust the result

    Content preview

    Files

    • agents/openai.yaml0.3 KB
    • LICENSE11.3 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md1.5 KB

    Origin and licence

    Listed unmodified

    Author
    ai-evals-course
    Source
    github.com/ai-evals-course/evals-skills/tree/80d5f7b0127c7572ed9e9339937adbfd7240ffeb/skills/write-code-eval
    Licence
    Apache-2.0

    Notice

    « write-code-eval » (ai-evals-course, 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.