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.

Three-AI comparison video v1.0.0

Use this resource to compare three AI models on one brief in a video

New

  • 480 downloads
  • 149 likes
  • 153 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install ai-model-showdown-video

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 collects the brief, the three models and their logos, then enforces fair-test rules: one try, one renderer, same settings. It then assembles the three outputs into a 16:9 layout for a newsletter and a 1080 x 1920 vertical reel. You get a comparison the audience can judge for themselves.

Mostly picked by

Updated November 2, 2026

Vertical reel with three stacked animations, each labelled with its AI model name.

Details

Generates with
ffmpeg
Uses
  • ffmpeg
  • A renderer that turns HTML pages into video
Licence
MIT

Similar resources

View all
  • Free

    Video

    App window with zoom

    • 365365 downloads
    • 125125 likes
    • 188188 saves
    Works with
    • Claude Code
    • Codex
    • Cursor
    • and 3 more
    + HyperFrames
  • Free

    Video

    One big number

    • 463463 downloads
    • 223223 likes
    • 100100 saves
    Works with
    • Claude Code
    • Codex
    • Cursor
    • and 3 more
    + HyperFrames
  • PRO

    Video

    Three bars head to head

    • 348348 downloads
    • 133133 likes
    • 182182 saves
    Works with
    • Claude Code
    • Codex
    • Cursor
    • and 3 more
    + HyperFrames
  • PRO

    Video

    Before / after slider

    • 322322 downloads
    • 248248 likes
    • 238238 saves
    Works with
    • Claude Code
    • Codex
    • Cursor
    • and 3 more
    + HyperFrames
  • PRO

    Video

    Three-card carousel

    • 418418 downloads
    • 157157 likes
    • 101101 saves
    Works with
    • Claude Code
    • Codex
    • Cursor
    • and 3 more
    + HyperFrames
  • PRO

    Video

    Chat exchange

    • 564564 downloads
    • 127127 likes
    • 161161 saves
    Works with
    • Claude Code
    • Codex
    • Cursor
    • and 3 more
    + HyperFrames
  • PRO

    Video

    Checklist ticking off

    • 442442 downloads
    • 233233 likes
    • 160160 saves
    Works with
    • Claude Code
    • Codex
    • Cursor
    • and 3 more
    + HyperFrames

What you get

  • SKILL.md: steps, fair-test rules and render instructions
  • The text to add to the brief so all three models produce HTML rendered the same way
  • A ready ffmpeg command that stacks three panels into a vertical reel
  • Pitfalls to avoid: safe zone, logo legibility, full model names

Good fit for

  • A "same prompt, three AIs" post for a newsletter or reel
  • Comparing models on a motion design brief
  • Publishing a test viewers can verify

Not for

  • Comparing text or still images
  • A test where results are retouched until the best one wins
  • Disguised advertising for one model

Tags

  • comparison
  • ai
  • reel
  • newsletter
  • ffmpeg

About

You say

"Run a three-model showdown on this logo animation brief, in 16:9 for my newsletter and as a vertical reel."

Vertical reel with three stacked animations, each labelled with its AI model name.

Skill published by charlie947 under the MIT license.

Show more

Prerequisites

You bring
The exact brief and access to three models and Each model's logo file
Dependencies
ffmpeg and A renderer that turns HTML pages into video

How to use it

  1. Give the exact brief, the three models and their logo files.
  2. Add the supplied render text to the brief, then collect each model's first try.
  3. Let the agent assemble it and check a mid-video frame before you publish.

Content preview

Files

  • LICENSE1.1 KB
  • NOTICE-PALATEKIT.md0.4 KB
  • SKILL.md4.2 KB

Origin and licence

Modified by PalateKit

Author
charlie947
Source
github.com/charlie947/motion-graphics-skills/tree/229022ebca76972e119e36ada23a1648d51665ab/skills/model-showdown
Licence
MIT

Notice

Version modifiée de « model-showdown » (charlie947, MIT) : traduction française et fiche par PalateKit.

User reviews

–

No ratings yet

Loading reviews…

Delete your review?

Your rating and comment will be removed from the page.

Frequently asked questions

Does it work on its own?

Yes for the protocol and the assembly. It mentions brand-intake, reel-export, brand.md and MOTION.md, which help but are optional: otherwise give your colors, a font and a logo.

What do I need to install?

ffmpeg and a renderer that runs the HTML page (window.seek) to export each output to MP4 with the same settings.