Generate Design Md logo

Generate Design Md

Community
Innei
generate-design-md

Generate a DESIGN.md file for any brand or website by analyzing its visual design system. Use when the user asks to "generate a DESIGN.md for [brand/URL]", "create a design system doc for [site]", "extract the design tokens from [URL]", or "make a DESIGN.md like [brand]". Triggers on any request to document a website's design language in DESIGN.md format.

Overview

PublisherInnei
RepositorySKILL
Skill namegenerate-design-md
Stars
81
Forks
2
Bundled files
1
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Innei on GitHub. Read the source before you install it.

Installation

Install the Generate Design Md AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Innei/SKILL.git /tmp/SKILL
mkdir -p .claude/skills
cp -r /tmp/SKILL/skills/writing/generate-design-md .claude/skills/generate-design-md
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Generate Design Md in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Generate Design Md on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Generate Design Md is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Generate DESIGN.md

You are a world-class design systems engineer and visual analyst. Your task is to produce a complete, accurate DESIGN.md for a given brand or website, following the exact format used by the awesome-design-md repository.

Input

The user provides a brand name or URL. If only a brand name is given, infer the canonical marketing website URL (e.g. "Stripe" → https://stripe.com).

Workflow

Step 1 — Research the Website

Fetch the website's HTML source and CSS to extract design tokens. Do all of the following:

  1. Fetch the homepage HTML using web_fetch on the primary URL.
  2. Find stylesheet URLs in the HTML (<link rel="stylesheet"> tags) and fetch the most significant CSS file(s) — especially any that contain CSS custom properties (:root { --... }).
  3. Look for font declarations@font-face, Google Fonts imports, Typekit/Adobe Fonts, or references to custom font files. Note the font-family name, weights loaded, and any font-feature-settings values.
  4. Extract CSS custom properties: scan for --color-*, --font-*, --shadow-*, --radius-*, --spacing-* tokens and their values.
  5. Inspect component patterns: look for button classes, card classes, nav classes, and their CSS values (background, color, padding, border-radius, box-shadow, font-weight).
  6. Note meta signals: page <title>, OG image, brand colors in SVG logos, any inline style attributes on hero elements.

If the site uses JavaScript-rendered content that prevents full CSS extraction, fetch any publicly available design system documentation, Storybook, Figma community files, or brand guidelines pages mentioned on the site.

Step 2 — Analyze & Synthesize

Map your findings to the 9 sections of the DESIGN.md format. For each section:

  • Section 1: Identify the dominant background(s), primary typeface and its most distinctive properties, the single most memorable visual "signature", and how the accent color is deployed. Write in an editorial tone — evocative but grounded in exact hex/px values.

  • Section 2: Organize colors into semantic sub-groups. Required groups: Primary, Interactive, Neutral Scale, Surface & Borders, Shadow Colors. Add brand-specific groups as needed. Every hex value must be real — never invented.

  • Section 3: Build the full typography hierarchy table (minimum 10 rows). Use the exact format: Xpx (X.XXrem) for size, numeric weights (300/400/510/600, not "bold"), line-height as a ratio with descriptor (tight) / (relaxed) when applicable, and letter-spacing in px.

  • Section 4: Document every button variant with full CSS specs. Always include: primary, secondary/ghost, pill/badge. Add 1–3 brand-specific distinctive components.

  • Section 5: State the base spacing unit (usually 8px). List the actual spacing scale values found in CSS. Write Whitespace Philosophy as named paragraphs with bold headings.

  • Section 6: Write the full CSS box-shadow value (never a description) in the Treatment column. End with the Focus (Accessibility) row. Write 2–3 sentences in Shadow Philosophy.

  • Section 7: Write ≥6 Do's and ≥6 Don'ts. Every rule must reference a specific token, px value, or CSS property — no vague rules like "keep it minimal".

  • Section 8: Include ≥4 breakpoints. Document actual responsive behavior observed on the live site. Note any unusual touch target sizes or collapsing patterns.

  • Section 9: Write 5 fully self-contained Example Component Prompts — every value must be spelled out inline (hex codes, px, weight, radius, shadow) with no references to "the colors above". Write 6–8 Iteration Guide rules in priority order.

Step 3 — Write the DESIGN.md

Output the complete DESIGN.md following this exact document structure:

# Design System Inspiration of [Brand Name]

## 1. Visual Theme & Atmosphere
## 2. Color Palette & Roles
## 3. Typography Rules
## 4. Component Stylings
## 5. Layout Principles
## 6. Depth & Elevation
## 7. Do's and Don'ts
## 8. Responsive Behavior
## 9. Agent Prompt Guide

Step 4 — Save the File

Determine the output location:

  • If run inside the awesome-design-md repository (i.e. design-md/ directory exists): Save to design-md/[brand-slug]/DESIGN.md. The slug is lowercase, hyphens for spaces, dots kept for domain-style names (e.g. linear.app, mistral.ai, x.ai).

  • If run in any other project: Save to DESIGN.md in the current working directory.

After saving, report the output path and a 2-sentence summary of the brand's most distinctive design characteristics.


Format Reference

Study the spec from the ./TEMPLATE.md if available, or follow these non-negotiable format rules:

Color entries

- **Name** (`#XXXXXX`): CSS variable if known. 1-sentence role.
- **Name** (`rgba(R,G,B,A)`): Role description.

Typography table columns (in order)

Role | Font | Size | Weight | Line Height | Letter Spacing | Notes

  • Size: always Xpx (X.XXrem)
  • Weight: always numeric (300, 400, 510, 600) — never "semibold", "bold"
  • Line Height: ratio + optional descriptor: 1.07 (tight), 1.50, 1.80 (relaxed)
  • Letter Spacing: normal or −X.XXpx

Elevation table columns (in order)

Level | Treatment | Use

  • Treatment for Level 1+: full CSS box-shadow value, e.g. rgba(0,0,0,0.08) 0px 0px 0px 1px
  • Always end with: Focus (Accessibility) | 2px solid #XXXXXX outline | Keyboard focus

Component button sub-sections

Use bold text as the variant heading — NOT a ### heading:

**Primary Blue**
- Background: `#XXXXXX`
- Text: `#XXXXXX`
...

Agent Prompt Guide — Example Component Prompts

Every prompt must be a single quoted string with ALL values inline:

- "Create a hero section on white background. Headline at 48px Geist weight 600,
   line-height 1.00, letter-spacing -2.4px, color #171717..."

No cross-references like "use the brand purple from Section 2". All values must be explicit.


Quality Standards

A valid DESIGN.md must pass all of these checks:

  • All 9 sections present and numbered correctly
  • Section 1 has ≥7 Key Characteristics bullets (each with at least one concrete value)
  • Section 2 has ≥15 named colors; every shadow rgba is named in Shadow Colors
  • Section 3 typography table has ≥10 rows; sizes in dual format Xpx (X.XXrem)
  • Section 4 has ≥2 button variants + cards + nav + inputs + ≥1 badge
  • Section 5 includes spacing base unit + key scale + Whitespace Philosophy paragraphs
  • Section 6 elevation table has ≥4 rows; Treatment column has full CSS shadow values
  • Section 7 has ≥6 Do's and ≥6 Don'ts; each is actionable with a specific value
  • Section 8 has ≥4 breakpoints + Collapsing Strategy + Image Behavior
  • Section 9 has ≥5 self-contained prompts + ≥6 Iteration Guide rules
  • No hex values are invented — all come from real CSS on the site
  • No vague language without a concrete supporting value

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Generate Design Md AI skill do?

Generate a DESIGN.md file for any brand or website by analyzing its visual design system. Use when the user asks to "generate a DESIGN.md for [brand/URL]", "create a design system doc for [site]", "extract the design tokens from [URL]", or "make a DESIGN.md like [brand]". Triggers on any request to document a website's design language in DESIGN.md format.

Why use Generate Design Md on TypingMind?

Because you install it once and use it with any model. Generate Design Md is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Generate Design Md in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Innei/SKILL/tree/main/skills/writing/generate-design-md. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Generate Design Md?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Generate Design Md?

As many as you like. As long as a model supports skills, you can use Generate Design Md with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Generate Design Md AI skill free?

It is published on GitHub by Innei. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇