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.

Benchmarking and improving an agent skill v1.0.0

Use this resource to evaluate and improve an agent skill through comparison

New

  • 469 downloads
  • 225 likes
  • 222 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install agent-skill-benchmark-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 runs matched attempts, with and without the skill, and grades them with the repo's schemas. It selects the executor for your environment, Codex CLI or Claude Code, and writes an evaluation report.

Mostly picked by

Updated November 2, 2026

Card for the “Benchmarking and improving an agent skill” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: test, improve and benchmark method and minimum eval rules
  • references/codex-cli.md: procedure for running with Codex CLI
  • assets/grading.schema.json: grading schema

Good fit for

  • You want to check whether a skill really improves agent answers
  • You iterate on a skill and need a measured baseline

Not for

    Tags

    • skills
    • evaluation
    • benchmark
    • agents

    About

    You say

    “Evaluate my code review skill against a run without the skill on three tasks.”

    Card for the “Benchmarking and improving an agent skill” skill

    Skill published by rstackjs 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 evaluate and improve an agent skill through comparison
    3. Review and adjust the result

    Content preview

    Files

    • assets/grading.schema.json1.2 KB
    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/codex-cli.md13.8 KB
    • SKILL.md5.3 KB

    Origin and licence

    Listed unmodified

    Author
    rstackjs
    Source
    github.com/rstackjs/agent-skills/tree/2ee8100ab8efb6d6c3c4c6d901fcb665b10163fc/.agents/skills/rstack-skill-evaluator
    Licence
    MIT

    Notice

    « rstack-skill-evaluator » (rstackjs, 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.