firecrawl-website-design-clone

Extract any website's design system into an agent-ready DESIGN.md using Firecrawl scrape evidence. Use when the user wants colors, fonts, spacing, components,…

INSTALLATION
npx skills add https://github.com/firecrawl/firecrawl-workflows --skill firecrawl-website-design-clone
Run in your project or agent environment. Adjust flags if your CLI version differs.

SKILL.md

$27

  • The branding format for structured design tokens.
  • A full-page screenshot for visual context.

Example:

firecrawl scrape "https://example.com" --format branding -o ".firecrawl/example-branding.json" --pretty &

firecrawl scrape "https://example.com" --full-page-screenshot -o ".firecrawl/example-screenshot.png" &

wait

If the screenshot scrape returns a remote image URL (e.g. signed storage link) instead of a local file, download it to the same .firecrawl/ path so DESIGN.md can reference a stable local asset.

Use the structured branding output as the primary source for colors, typography, components, imagery, personality, and confidence notes. Use the screenshot as the primary visual reference for layout, hierarchy, and overall feel. Add supplemental formats only when these two are insufficient for the final artifact.

Collect:

  • branding data for colors, typography, spacing, buttons, logos, imagery, personality, and confidence
  • a full-page screenshot saved locally in .firecrawl/ so it can be embedded in DESIGN.md
  • page markdown for headings, copy hierarchy, CTAs, navigation, and section order when needed
  • metadata and links for brand, product, and page-purpose clues when needed
  • HTML only when the branding output and screenshot are insufficient to infer classes, font names, CSS variables, or component structure
  • related pages only when the user asks for a broader site system

Do not over-crawl by default. The first version should be useful from a single representative page.

What To Extract

Infer and document the site's design language:

  • colors: primary, secondary, accents, backgrounds, borders, text, states
  • typography: font families if detectable, type scale, weights, line heights, heading/body treatment
  • spacing: container widths, section rhythm, grid gaps, padding scale, density
  • layout: page structure, hero patterns, cards, grids, nav, footer, responsive assumptions
  • components: buttons, inputs, cards, badges, nav items, pricing blocks, testimonials, feature rows, forms
  • imagery and icons: style, shape language, illustration/photo treatment, logo constraints
  • motion and interaction: hover states, transitions, animation style when observable or inferable
  • voice and content patterns: CTA wording, heading style, product copy rhythm

When a value cannot be measured exactly from scrape output, label it as inferred and give a practical approximation.

Parallel Work

If appropriate, use sub-agents or equivalent parallel task runners. Natural splits include one page per researcher for multi-page sites, or one reviewer each for colors, typography, spacing, and components.

Each parallel researcher should return source URLs, extracted evidence, inferred design tokens, and confidence notes.

Final Deliverable

Create or return a DESIGN.md with this structure. Embed the full-page screenshot near the top so a coding agent gets visual context alongside the tokens.

# DESIGN.md: [Source Site]

## Source

- URL: [source URL]

- Capture date: [date]

- Evidence: [scrape/screenshot/html/links used]

## Reference Screenshot

![Full-page screenshot of [Source Site]](./.firecrawl/[source]-screenshot.png)

Use this screenshot as the visual source of truth for layout, hierarchy, density, and feel. Tokens below describe the same page in machine-readable form.

## Design Summary

[Short description of the visual language and what an agent should recreate]

## Design Tokens

### Colors

[Named color roles with hex values when known; mark inferred values clearly]

### Typography

[Fonts, fallback recommendations, scale, weights, heading/body rules]

### Spacing And Layout

[Spacing scale, containers, grids, radius, shadows, borders]

## Components

[Buttons, cards, nav, forms, hero, feature sections, pricing, footer, etc.]

## Page Patterns

[Section order, common layouts, responsive behavior]

## Content Style

[Voice, CTA style, heading patterns, copy density]

## Agent Build Instructions

[Concrete instructions an AI coding agent can follow to create a new site in this style]

## Rerun Inputs

workflow: firecrawl-website-design-clone

source_url: [url]

target_stack: [stack]

output: DESIGN.md

If the user asks to implement, first produce or update DESIGN.md, then use it as the source of truth for the build.

Quality Bar

  • Do not imply the user has rights to third-party logos, images, trademarks, or copy.
  • Prefer reusable design tokens over one-off observations.
  • Distinguish observed facts from inferred approximations.
  • Keep the output compact enough that another agent can paste it into context and build from it.
  • Preserve source URLs and scrape artifacts for review.
BrowserAct

Let your agent run on any real-world website

Bypass CAPTCHA & anti-bot for free. Start local, scale to cloud.

Explore BrowserAct Skills →

Stop writing automation&scrapers

Install the CLI. Run your first Skill in 30 seconds. Scale when you're ready.

Start free
free · no credit card