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.

Skill evaluation by with and without runs v1.0.0

Use this resource to decide whether a skill should be kept, revised or removed

New

  • 316 downloads
  • 243 likes
  • 176 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install skill-ab-evaluation

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 picks the measurement that answers your maintenance decision, then compares runs with and without the skill on your accepted cases. It counts every attempt, including failures, and makes one scoped recommendation. You get a decision: retain, revise, remove, or insufficient evidence.

Mostly picked by

Updated November 2, 2026

Card for the “Skill evaluation by with and without runs” 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: decision rules, question selection and procedure
  • references/: behavioral probes, coding memory readout, dialogue skills and seeding

Good fit for

  • You are unsure whether to keep a skill added six months ago
  • You read A/B results and must decide

Not for

    Tags

    • evaluation
    • skills
    • a/b
    • measurement

    About

    You say

    “Compare runs of this skill with and without it on our accepted cases, and tell me whether to keep it.”

    Card for the “Skill evaluation by with and without runs” skill

    Skill published by boshu2 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 decide whether a skill should be kept, revised or removed
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE11.3 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/behavioral-probes.md4.5 KB
    • references/coding-memory-readout.md2.9 KB
    • references/dialogue-skills.md1.3 KB
    • references/seeding.md5.8 KB
    • SKILL.md14.9 KB

    Origin and licence

    Listed unmodified

    Author
    boshu2
    Source
    github.com/boshu2/agentops/tree/bd63fa648901866d9e8fc3cf011aed1cf3a7d758/skills/skill-eval
    Licence
    Apache-2.0

    Notice

    « skill-eval » (boshu2, 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.