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.

Create and verify an evaluation suite v1.0.0

Use this resource to create a fixed evaluation suite to measure a harness

New

  • 315 downloads
  • 232 likes
  • 221 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install harness-evaluation-bench-suite

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 builds a JSON evaluation suite from a repository's test corpus, then checks that it is well formed. The suite serves as the scoring baseline for harness-evolve, independent of the project's usual tests.

Mostly picked by

Updated November 2, 2026

Card for the “Create and verify an evaluation suite” skill

Details

Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md: creation and verification steps
  • SKILL.md: output shape and exit codes

Good fit for

  • Your repository's tests are slow or flaky
  • You want to compare variants on a fixed corpus

Not for

    Tags

    • evaluation
    • suite
    • benchmark
    • harness

    About

    You say

    “Create an evaluation suite from the repo's tests and verify it.”

    Card for the “Create and verify an evaluation suite” skill

    Skill published by ruvnet 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 create a fixed evaluation suite to measure a harness
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md2.4 KB

    Origin and licence

    Listed unmodified

    Author
    ruvnet
    Source
    github.com/ruvnet/ruflo/tree/89b0cd02dd99ea1f63437fde6c05992ec53cc22b/plugins/ruflo-metaharness/skills/harness-bench
    Licence
    MIT

    Notice

    « harness-bench » (ruvnet, 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.