Brand To Design Md logo

Brand To Design Md

Community
shaom
brand-to-design-md

Convert a public brand URL into a practical DESIGN.md file and optional single-file HTML demo. Use when the user asks to extract, distill, compile, generate, or validate a DESIGN.md/design system from a website, brand page, press kit, or public visual identity.

Overview

Publishershaom
Repositorybrand-to-design-md-skill
Skill namebrand-to-design-md
Stars
208
Forks
16
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 shaom on GitHub. Read the source before you install it.

Installation

Install the Brand To 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.
    https://github.com/shaom/brand-to-design-md-skill/tree/main/skills/brand-to-design-md
  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/shaom/brand-to-design-md-skill.git /tmp/brand-to-design-md-skill
mkdir -p .claude/skills
cp -r /tmp/brand-to-design-md-skill/skills/brand-to-design-md .claude/skills/brand-to-design-md
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Brand To 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 Brand To 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 Brand To 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.

Brand To DESIGN.md

Overview

Use this skill to turn public brand evidence into a token-ready DESIGN.md that a coding agent can use to generate consistent UI. When useful, also create a demo HTML page and verify it in a browser.

Start from the Google Labs DESIGN.md standard, not from example directories or third-party showcase pages. The output should be practical, source-aware, and executable by an agent.

Workflow

1. Confirm Scope And Standard

Clarify only if needed:

  • Target brand URL or brand name.
  • Required outputs: DESIGN.md only, or DESIGN.md plus demo HTML and screenshots.
  • Target context: website, app UI, developer docs, product page, editorial asset, or general system.

Use the Google Labs DESIGN.md format as the structural reference: metadata, design tokens, component guidance, imagery rules, logo boundaries, and Do/Don't guidance.

2. Gather Evidence

Prefer primary and high-signal sources:

  • Official homepage and product pages.
  • Official brand, press, newsroom, media kit, or legal trademark pages.
  • Public CSS, font declarations, SVG logos, favicons, images, and screenshots.
  • Design agency case studies when they explain the identity system.
  • Third-party brand databases only as secondary support.

Record evidence in four groups:

  • Direct evidence: observed CSS, SVG fills, image colors, font names, layout behavior.
  • Official prose: brand usage rules, typography descriptions, press-kit notes.
  • Design rationale: motifs, concepts, color names, type-system explanations.
  • Inference: practical agent decisions not explicitly stated by sources.

If access is blocked by a CAPTCHA, login, or security challenge, do not bypass it. Use accessible official pages, cached/search snippets, press kits, downloaded public assets, or clearly mark the limitation.

3. Extract Tokens

Translate evidence into roles, not just values.

Core token groups:

  • colors: primary, secondary, tertiary, neutral, surface, on-primary, text, border, status/accent colors.
  • typography: display, h1, h2, body, label, mono/code when present.
  • rounded: small, medium, large, special brand shapes.
  • spacing: base scale, common section gaps.
  • components: buttons, cards, inputs, links, code panels, notices, navigation.
  • imagery: photography style, illustration style, texture, gradient, motion, icon rules.

For each major token, prefer a role explanation:

  • Where it came from.
  • What it should be used for.
  • What should not use it.

4. Compile DESIGN.md

Write a concise but usable file:

markdown
---
version: alpha
name: Brand Name
description: One sentence identity summary.
sources:
  - https://...
notes:
  - Evidence and limitation notes.
colors:
  primary: "#..."
typography:
  display:
    fontFamily: ...
components:
  button-primary:
    backgroundColor: "{colors.primary}"
---

## Overview
...

## Colors
...

## Typography
...

## Layout
...

## Components
...

## Imagery
...

## Logo And Usage
...

## Do's and Don'ts
...

Keep the writing concrete. Avoid generic claims such as "modern, clean, innovative" unless the evidence supports them and they are translated into specific design actions.

5. Generate A Demo When Useful

If asked for a demo, build a single-file HTML artifact in the workspace.

The demo should prove that the DESIGN.md is usable:

  • First screen should be an actual branded product or site experience, not an explanation page.
  • Include palette, typography, buttons, cards, forms, data/code panels, and one brand-specific motif.
  • Use extracted public assets when allowed and useful.
  • Recreate the brand's behavior and hierarchy, not only its colors.
  • Keep the page responsive and readable on mobile.

For browser-based artifacts, use real browser or preview-environment verification:

  • Open the file in an available browser or preview environment.
  • Check console errors.
  • Check horizontal overflow.
  • Capture desktop and mobile screenshots.
  • Confirm critical images and fonts fall back cleanly.

6. Report Output

Return:

  • DESIGN.md path.
  • Demo HTML path if created.
  • Screenshot paths if created.
  • Source summary.
  • Verification result.
  • Any limitations or inferred choices.

Quality Bar

A good output lets a future coding agent produce a page that feels recognizably tied to the brand without needing more context.

Check for:

  • Tokens map to meaningful roles.
  • The brand has distinct visual behavior beyond color.
  • Logo and trademark boundaries are respected.
  • Demo page uses the system in several UI contexts.
  • The output distinguishes evidence from inference.

When To Read More

For a compact checklist and output templates, read references/workflow-checklist.md.

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 Brand To Design Md AI skill do?

Convert a public brand URL into a practical DESIGN.md file and optional single-file HTML demo. Use when the user asks to extract, distill, compile, generate, or validate a DESIGN.md/design system from a website, brand page, press kit, or public visual identity.

Why use Brand To Design Md on TypingMind?

Because you install it once and use it with any model. Brand To 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 Brand To Design Md in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/shaom/brand-to-design-md-skill/tree/main/skills/brand-to-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 Brand To 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 Brand To Design Md?

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

Is the Brand To Design Md AI skill free?

It is published on GitHub by shaom. 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 👇