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.

Publishing a model leaderboard from runs v1.0.0

Use this resource to publish a model leaderboard from validated benchmark submissions

New

  • 593 downloads
  • 138 likes
  • 133 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install benchmark-leaderboard-publishing

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 checks each new run before publication, updates the editorial verdicts, regenerates the benchmark repository report and the public page, then opens the publishing pull requests. Nothing goes public without this step.

Mostly picked by

Updated November 2, 2026

Card for the “Publishing a model leaderboard from runs” skill

Details

Generates with
Your agent's model
Licence
MIT

Similar resources

View all
  • Free

    Skills

    Knowledge wiki setup

    • 418418 downloads
    • 129129 likes
    • 161161 saves
    Works with
    • Claude Code
    • Codex
    • Cursor
    • and 3 more
  • Free

    Skills

    Wiki health check

    • 552552 downloads
    • 202202 likes
    • 127127 saves
    Works with
    • Claude Code
    • Codex
    • Cursor
    • and 3 more
  • Free

    Skills

    Ask your wiki

    • 374374 downloads
    • 131131 likes
    • 214214 saves
    Works with
    • Claude Code
    • Codex
    • Cursor
    • and 3 more
  • Free

    Skills

    Wiki source ingestion

    • 315315 downloads
    • 230230 likes
    • 246246 saves
    Works with
    • Claude Code
    • Codex
    • Cursor
    • and 3 more
  • Free

    Skills

    Wiki auditor agent

    • 556556 downloads
    • 205205 likes
    • 192192 saves
    Works with
    • Claude Code
    • Codex
    • Cursor
    • and 3 more
  • Free

    Skills

    UX research assistant

    • 598598 downloads
    • 142142 likes
    • 236236 saves
    Works with
    • Claude Code
    • Codex
    • Cursor
    • and 3 more
  • Free

    Skills

    Wiki ingestion agent

    • 437437 downloads
    • 162162 likes
    • 191191 saves
    Works with
    • Claude Code
    • Codex
    • Cursor
    • and 3 more
  • Free

    Skills

    Wiki librarian agent

    • 304304 downloads
    • 120120 likes
    • 217217 saves
    Works with
    • Claude Code
    • Codex
    • Cursor
    • and 3 more

What you get

  • SKILL.md: steps for checking new runs and regenerating
  • SKILL.md: rules for writing editorial verdicts

Good fit for

  • You have just merged several benchmark submissions
  • You publish a model ranking and want to avoid data-entry errors

Not for

    Tags

    • benchmark
    • leaderboard
    • models
    • publishing
    • verification

    About

    You say

    “Update the benchmark leaderboard with this week's merged submissions.”

    Card for the “Publishing a model leaderboard from runs” skill

    Skill published by shpigford 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 publish a model leaderboard from validated benchmark submissions
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE4.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md5.3 KB

    Origin and licence

    Listed unmodified

    Author
    shpigford
    Source
    github.com/shpigford/nurb/tree/048c3257bbf2c0fc7d8a984d3c12a9b13d8b2f62/.claude/skills/leaderboard
    Licence
    MIT

    Notice

    « leaderboard » (shpigford, 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.