--- name: audit-website-design description: Performs a comprehensive design and technical audit of a website URL. Extracts layout, typography, colors, components, animations, spacing, tech stack, SEO metadata, and brand voice into a detailed reference document for replicating design decisions. Use when analyzing or auditing a website's design. disable-model-invocation: true allowed-tools: WebFetch Bash(curl *) argument-hint: [url] effort: high --- # Website Design Audit Audit the website at `$ARGUMENTS` and produce a comprehensive design reference document that an engineer or LLM can use to replicate the site's design decisions. ## Extraction strategy Gather data through multiple passes, then compile into the final report. ### Pass 1: Raw HTML source Fetch the page source for technical and structural metadata: ```bash curl -sL -A "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36" "$URL" ``` If the output is very large, pipe through `head -1500` to capture `
` and initial ``. If curl returns a Cloudflare challenge or empty body, note this and rely more on WebFetch in Pass 3. Extract from HTML: - `