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.

Recreate a mockup as a faithful UI v1.0.0

Use this resource to recreate a mockup or screenshot as a web interface

New

  • 459 downloads
  • 213 likes
  • 223 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install image-to-ui-recreation

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 looks at the image, notes dimensions, text, spacing, fonts and colors, then builds the page with your project's components. It renders the page at the reference's size, compares the two and fixes the gaps. You get a faithful interface with an honest account of what was actually compared.

Mostly picked by

Updated November 2, 2026

No preview supplied: the skill ships no image.

Details

Generates with
Your agent's model
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: a three-step method (inspect, implement, compare and correct)
  • Fidelity rules: no redesign, no invented assets
  • A reporting rule that flags the remaining differences

Good fit for

  • Going from a Figma mockup or screenshot to a coded page
  • Faithfully cloning a reference screen supplied by a client
  • Recoding a page from an approved visual

Not for

  • Imagining a design from a brief with no image
  • Improving or retouching a mockup's design
  • Generating images or illustrations

Tags

  • mockup
  • screenshot
  • html
  • css
  • interface

About

You say

"Here is my homepage mockup: recreate it exactly in HTML and CSS and compare it with a screenshot."

No preview supplied: the skill ships no image.

Skill published by UIZZE under the MIT license.

Show more

Prerequisites

You bring
The reference image (screenshot or mockup) and The project or folder where the page goes

How to use it

  1. Install the skill and add the reference image.
  2. Point to the target page or project.
  3. Review the report and the differences it flags.

Content preview

Files

  • LICENSE1.1 KB
  • NOTICE-PALATEKIT.md0.4 KB
  • SKILL.md3.1 KB

Origin and licence

Modified by PalateKit

Author
uizze
Source
github.com/uizze/uizze/tree/40b0ee439ba88aecb65d68bcb379da0e716b899e/skills/image-to-ui
Licence
MIT

Notice

Version modifiée de « image-to-ui » (uizze, 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 the agent need to see the image?

Yes, it has to look at the image itself; if its tool can't, it will ask for a readable copy.

Are missing fonts replaced?

The skill asks the agent to flag the limit rather than substitute silently; supply the fonts for an exact match.