Full product DNA. One file. Voice, UX, content, architecture, behavior, performance, tech stack. 36 extraction passes. 200+ data points.

stackmd crawls any URL and extracts the full product DNA: brand voice, UX patterns, content strategy, visual design, information architecture, component behavior, SEO structure, and technology stack. 36 extraction passes. 200+ data points. 20 structured sections. Everything an AI agent needs to rebuild a product that works, feels, and thinks like the original.

$ npx stackmd https://example.com click to copy

What it looks like

terminal
$ stackmd https://linear.app
stackmd · full product DNA extraction
https://linear.app
Extraction complete
STACK.md → ./STACK.md
Summary
18 colors · 3 fonts · 5 components · 8 UX patterns
Voice: technical, warm, accessible · Page: landing · Score: 78/100
Stack: React, Next.js + Tailwind CSS

20 sections of product DNA · 36 extraction passes

Every STACK.md captures the complete picture. Here's what each section gives an AI agent.

01
Product Identity
Name, tagline, page type, frameworks, personality
02
DNA Score
0-100 across visual, voice, UX, a11y, SEO, perf
03
Brand Voice
Personality, reading level, pronouns, CTA style
04
Content Strategy
Headings, labels, placeholders, microcopy
05
Visual Design
Colors, type, spacing, depth, gradients, font loading
06
Components
Buttons, inputs, cards, nav with full CSS
07
UX Patterns
Hero, CTAs, forms, social proof, pricing
08
Architecture
Navigation, sections, footer, structure stats
09
Behavior
Modals, tooltips, validation, hover states
10
Motion
Durations, easings, keyframes, scroll behavior
11
Responsive
Breakpoints from @media rules
12
Accessibility
WCAG contrast, landmarks, ARIA, color matrix
13
SEO & Perf
Meta, structured data, DOM nodes, lazy loading
14
Tech Stack
Frameworks, analytics, hosting, third-party
15
Icons & Media
SVG system, image formats, video, figures
16
Layout System
Flex/grid patterns, container widths, gaps
17
Social Presence
Twitter, GitHub, Discord, LinkedIn links
18
Structured Data
JSON-LD, microdata, OpenGraph, Twitter Cards
19
Deep Report
Typography, color, layout, forms, media, nav, a11y, perf, content metrics
20
Agent Guide
Full prompt: identity + visual + voice + UX

Brand Voice Analysis

stackmd doesn't just read CSS. It reads the words. Every heading, paragraph, CTA, label, and piece of microcopy is analyzed for personality traits, reading level, pronoun strategy, punctuation style, and vocabulary patterns.

brand voice profile
tone profile
formality
25
warmth
65
technical
40
urgency
15
playful
10
signals
personality: warm, technical, accessible
reading level: standard (12 words/sentence)
pronouns: balanced (we + you)
CTA pattern: low-commitment (try/free)
punctuation: standard
density: concise

Install

terminal
npm install -g stackmd
FlagDescriptionDefault
-o, --outputOutput file path./STACK.md
--jsonOutput raw data as JSONfalse
--darkExtract dark mode tokensfalse
--wait <ms>Wait time for dynamic content3000

Programmatic API

app.js
import { stack } from "stackmd"

const result = await stack("https://example.com")

result.data.brandVoice             // personality, reading level, CTA patterns
result.data.uxAnalysis             // page type, conversion, navigation
result.data.designSystem           // colors, fonts, spacing, components
result.data.techStack              // React, Next.js, Tailwind, analytics
result.data.architecture           // navLinks, sections, footerLinks
result.data.behavior               // modals, tooltips, validation
result.data.dnaScore               // 0-100 across 10 dimensions

Disclaimer

Educational & Experimental Use Only

This tool is provided strictly for educational and experimental purposes. It reads publicly visible content and computed CSS from rendered web pages, equivalent to what any browser's developer tools expose.

  • No proprietary code, assets, or non-public information is accessed
  • Extracted data represents publicly visible content and styling
  • No ownership of any product identity or brand is claimed
  • Users are responsible for compliance with applicable terms of service
  • Does not bypass any access controls, authentication, or rate limiting
  • Output should not be used to create confusingly similar products

The author provides this tool as-is with no warranty. Use responsibly.