Firecrawl Website Design Clone

Point this at any URL and get back a DESIGN.md file with colors, fonts, spacing, components, and layout patterns extracted via Firecrawl's scrape API. It runs two parallel scrapes: one for branding tokens and images, another for a full-page screenshot, then synthesizes everything into a structured markdown file that another AI agent can use to clone or adapt the design. Useful when you want to reverse-engineer a site's visual system without manually inspecting CSS or building a mood board. The workflow is opinionated about not over-crawling and marks inferred values clearly, so you know what's measured versus guessed. Ships with agent build instructions in the output.

install copies · 90 days. Times the install command was copied on this site in the last 90 days, bots filtered.: 19
skills.sh installs: 33.5K
GitHub stars: 221
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add firecrawl/firecrawl-workflows --skill firecrawl-website-design-clone --agent claude-code

Installs into .claude/skills of the current project.

Files

Website design and brand assets

Choose the requested artifact before collecting evidence. For an existing logo, palette, fonts or messaging needed by a slide, proposal or other document, read brand assets and return the compact asset reference. A brand-asset lookup does not require a design-system report or full-page screenshot. For a website's UI system or implementation, follow the design-system mode below. If both are requested, reuse the same source evidence.