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.

How plugin quality is scored v1.0.0

Use this resource to understand and interpret the quality score of a skill or plugin

New

  • 441 downloads
  • 106 likes
  • 160 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install plugin-quality-scoring-method

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 explains the composite score of a skill or plugin, interprets a low score on one dimension and suggests fixes. It also reminds you that the experimental LLM-judge and Monte Carlo layers are only rough signals.

Mostly picked by

Updated November 2, 2026

Card for the “How plugin quality is scored” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: evaluation layers, composite score and badges
  • references/rubrics.md: judge rubric anchors
  • references/improving-scores.md: fixes for each anti-pattern

Good fit for

  • Your skill scores low and you don't know which dimension to fix
  • You set quality thresholds for a marketplace

Not for

    Tags

    • scoring
    • plugins
    • quality
    • rubrics

    About

    You say

    “Explain why my skill only gets 61 on triggering and how to raise it.”

    Card for the “How plugin quality is scored” skill

    Skill published by wshobson 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 understand and interpret the quality score of a skill or plugin
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/improving-scores.md5.6 KB
    • references/rubrics.md22.7 KB
    • SKILL.md7.9 KB

    Origin and licence

    Listed unmodified

    Author
    wshobson
    Source
    github.com/wshobson/agents/tree/0874a27b17a22e2b7c2e2bcd725768e0803cad06/plugins/plugin-eval/skills/evaluation-methodology
    Licence
    MIT

    Notice

    « evaluation-methodology » (wshobson, 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.