Ky Design to HTML

Convert visible UI references such as screenshots, exported mockups, Figma frame images, SaaS empty states, dashboards, and landing page screenshots into high-quality HTML/CSS by decomposing layout, separating visual assets from code-rendered UI, implementing the page, then validating with browser screenshots and iterative visual correction. Use when the user asks to recreate, copy, convert, or implement a visual design as HTML/CSS from an image or equivalent visual reference. Do not use for ordinary frontend feature work without a visual reference, designing new pages from text only, backend

166 stars 23 forksFrontend & Design

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add KyrieCheungYep/ky-design-to-html-skill --skill ky-design-to-html
Manual install
git clone --depth 1 https://github.com/KyrieCheungYep/ky-design-to-html-skill.git /tmp/ky-design-to-html-skill
mkdir -p ~/.claude/skills
cp -r /tmp/ky-design-to-html-skill/ky-design-to-html ~/.claude/skills/ky-design-to-html

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# KY Design to HTML

## Core Rule

Do not jump directly from image to HTML.

Treat design recreation as an error-reduction loop:

1. Read the visual reference and produce a page map.
2. Split elements into code-rendered UI and external visual assets.
3. Decide the reference canvas, display viewport, and scaling strategy.
4. Build the HTML/CSS structure with fixed asset slots.
5. Render in a real browser and capture screenshots.
6. Compare the screenshot with the reference.
7. Correct specific visual errors and repeat when needed.

The skill exists to avoid cheap-looking output caused by asking the model to solve layout, style, and complex asset creation in one step.

Keep analysis compact. Produce enough page-map detail to guide implementation, but do not spend large token budgets describing obvious UI unless the user asks for a detailed teardown.

## Inputs To Establish

Before implementation, infer or ask only when necessary:

- Visual reference: screenshot, mockup image, Figma export image, browser screenshot, or another concrete visual artifact.
- Reference canvas: use the image dimensions and aspect ratio when available; otherwise choose a reasonable desktop canvas and note it.
- Display viewport: the browser/window size used to preview the result.
- Output type: single HTML file, project component, or app route.
- Asset availability: original logos, illustrations, product images, icons, screenshots, or only the reference image.
Read the full skill on GitHub

Details

Skill name
ky-design-to-html
Path
ky-design-to-html/SKILL.md
Repo updated
2 June 2026

FAQ

What does the Ky Design to HTML skill do?

Convert visible UI references such as screenshots, exported mockups, Figma frame images, SaaS empty states, dashboards, and landing page screenshots into high-quality HTML/CSS by decomposing layout, separating visual assets from code-rendered UI, implementing the page, then validating with browser screenshots and iterative visual correction. Use when the user asks to recreate, copy, convert, or implement a visual design as HTML/CSS from an image or equivalent visual reference. Do not use for ordinary frontend feature work without a visual reference, designing new pages from text only, backend

How do I install the Ky Design to HTML skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add KyrieCheungYep/ky-design-to-html-skill --skill ky-design-to-html. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Ky Design to HTML popular?

It lives in KyrieCheungYep/ky-design-to-html-skill, which has 166 GitHub stars and 23 forks.

Related skills

Browse the most popular Claude skills, all frontend & design skills, or write your own with the skills generator.