Design System logo

Design System

Community
Darcos-Loft
design-system

Generate a unique, production-grade brand design system from a short brief. Use when starting a new site or product, defining or extending design tokens (color, type, spacing, radii, shadows, motion), producing a token file plus Tailwind config plus a brand rules doc plus a storybook, or giving a project a distinct visual identity. Encodes a house DNA and forces per-brand variation so no two systems look alike.

Overview

PublisherDarcos-Loft
Repositoryfluid
Skill namedesign-system
Stars
3
Forks
0
Bundled files
17
LicenseMIT
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.

  • 17 bundled files

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

  • Open source

    Published by Darcos-Loft on GitHub. Read the source before you install it.

Installation

Install the Design System 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/Darcos-Loft/fluid/tree/main/design-system
  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/Darcos-Loft/fluid.git /tmp/fluid
mkdir -p .claude/skills
cp -r /tmp/fluid/design-system .claude/skills/design-system
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Design System 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 Design System 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 Design System 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.

Design System

A factory for brand identities. Given a short brief, it produces a complete, unique design system in the house DNA: a token file, a Tailwind config, a brand rules doc the agent obeys, a storybook, and a human spec. The opposite of a template: the DNA (method and quality bar) stays constant, the output (palette, type, shape, mood) is different every time.

It is the piece that kills the generic look at the source. The fluid skill handles motion, the detector catches slop after the fact, this gives each project an identity from line one.

Built from four hand-made systems: MVP "Liquid Glass" (the structural template), LeCoffre (the delivery format), PLR @plr/ui, and Vigie.

When to use

  • Starting a new client site or product and you need its visual identity defined.
  • Producing or extending design tokens (color, type, spacing, radii, shadows, motion).
  • You want a tokens.css + Tailwind config + brand CLAUDE.md + storybook for a project.
  • An existing UI feels generic and needs a committed identity.

The two halves

A system here is DNA (constant) plus brand (variable). Get both right.

  • The DNA is the house method and quality bar. It never changes. See reference/dna.md.
  • The brand is what makes this system unlike any other: palette, type, shape, surface, mood. Derived per project from the brief. This is where you must NOT converge.

init: the workflow

  1. Gather the brief (ask only what is missing):

    • Brand name and sector/positioning.
    • Personality, pick an extreme: institutional/refined, editorial, luxury, playful/energetic, techy/precise, brutalist/raw, organic/warm. Half-measures read as generic.
    • Light, dark, or both (auto).
    • Surface treatment: flat, soft (subtle shadow/relief), or glass (liquid, translucent).
    • One anchor or constraint: an existing logo color, a reference you admire, a competitor you must NOT resemble.
  2. Derive the brand variables (commit, do not hedge):

    • Start from the database: pick a palette from data/palettes.md (100+ committed palettes), a type pairing from data/type-pairings.md (50+ distinctive pairings), a style direction from data/styles.md, and a layout archetype from data/layouts.md that fit the brief. Adapt the exact values; never improvise a generic default, and never default to the split-hero-plus-three-cards skeleton. Two clients in the same sector get different picks, including a different page shape. For motion reach into data/motion-presets.md, for any data display into data/chart-types.md, and for the build pick a stack from data/tech-stacks.md.
    • Color: one dominant brand hue + one sharp accent + semantic (success/warn/danger) + tuned neutrals. Never pure black. See reference/color.md.
    • Type: a distinctive display font paired with a refined body font, self-hosted. Never Inter/Roboto/Arial as the primary. See reference/typography.md.
    • Shape: a radii scale (sharp 4 to 8, rounded 12 to 22, or pill) chosen to match the personality.
    • Surface/relief: flat, soft-shadow, or glass tokens.
    • Motion: the house easings, already in the template (--ease-out, --spring, --ease-in-out), shared with fluid.
  3. Map to light/dark tokens: decide which tokens invert (bg, surface, text, glass, tints, on-tint) and which hold (brand hues, accent). See reference/color.md.

  4. Emit the files from templates/ (fill the {{placeholders}}):

    • tokens.css: the source of truth (CSS variables + base classes).
    • tailwind.config.js: same tokens for Tailwind/TanStack sites (omit for CSS-pur projects).
    • CLAUDE.md: the brand rules the agent obeys on every UI task.
    • storybook.html: a live showcase of every token and base component.
    • DESIGN_SYSTEM.md: the human-readable spec. Put them in a <project>/design-system/ folder (the LeCoffre pattern).
  5. Wire it: load the fonts, import tokens.css (or extend Tailwind), and from then on every color/space/radius is var(--token), never a raw value.

Stack note (light/dark strategy)

  • App with auto theme (like MVP): light by default, dark via @media (prefers-color-scheme: dark). CSS pur, no Tailwind needed.
  • Vitrine site with a theme toggle (like LeCoffre, TanStack/Tailwind): dark via :root[data-theme="dark"] / .dark, plus the tailwind.config.js.

The template carries both, keep the one you use.

Anti-generic rules (non negotiable)

  • Commit to ONE dominant color and ONE sharp accent. Timid, evenly spread palettes read as generic. Ration the brand: a thin accent beats a full wash.
  • Never the purple-on-white gradient. Never Inter/Roboto/Arial as the primary font. Never pure black, use a tuned near-black.
  • Every color, space, radius, shadow goes through a token. No raw hex on text or surface.
  • Bespoke SVG over stock icons, zero decorative emoji. (MVP runs a 3-tier icon system: glossy 3D for large elements, duotone gradient-sheen inline, bespoke SVG art for brand marks.)
  • Keyboard accessibility is part of premium: a global :focus-visible ring, defined with :where() so components can override.
  • Vary every system. Two projects must never share a palette or a type pairing. Do not default to the same fonts each time.
  • Distinctive does not mean loud. Refined minimal and bold maximal both work; intentionality is the bar.

Output checklist

  • One dominant + one accent, committed, not a timid spread.
  • Distinctive type pairing, self-hosted, no generic primary.
  • Full token set: color (light + dark), type scale, base-8 spacing, radii, shadows, motion.
  • Light and dark both resolve through tokens, both tested.
  • No raw hex on text/surface, no #000, no emoji.
  • Global :focus-visible, and a reduced-motion path (CSS and JS).
  • tokens.css + (tailwind.config.js) + CLAUDE.md + storybook.html + DESIGN_SYSTEM.md emitted.
  • Distinct from the last system produced (different palette and type).
  • Run the fluid detector on the result.

Database (pick from these first)

  • data/palettes.md: 100+ committed palettes by sector and mood (dominant + accent + neutrals).
  • data/type-pairings.md: 50+ distinctive display + body + mono pairings, never Inter primary.
  • data/styles.md: 53 aesthetic directions with their token tendencies.
  • data/layouts.md: 14 page-shape archetypes (bento, centered editorial, index, full-bleed, single column, broken grid, maximalist type, lineup, sidebar, poster, and more). Pick one per page, vary across pages so two never share a silhouette.
  • data/motion-presets.md: ready-to-use motion recipes in the house easings (reveals, hovers, press, overlays, ambient).
  • data/chart-types.md: 32 chart and data-viz types, which one answers which question, with house data-viz defaults.
  • data/tech-stacks.md: 10 curated build stacks by project type, each wired back to the house tokens and motion.

Reference

  • reference/rules.md: the hard rules (locks, hero discipline, layout honesty, bans). Read before shipping.
  • reference/dna.md: the constant house DNA.
  • reference/typography.md: choosing a distinctive type pairing.
  • reference/color.md: building a committed palette and the light/dark token map.
  • reference/glass.md: liquid-glass and surface recipes (the actual CSS, plus the shimmer button and card).
  • reference/icons.md: the 3-tier bespoke icon system, with code.
  • templates/: tokens.css, tailwind.config.js, CLAUDE.md, storybook.html.

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 Design System AI skill do?

Generate a unique, production-grade brand design system from a short brief. Use when starting a new site or product, defining or extending design tokens (color, type, spacing, radii, shadows, motion), producing a token file plus Tailwind config plus a brand rules doc plus a storybook, or giving a project a distinct visual identity. Encodes a house DNA and forces per-brand variation so no two systems look alike.

Why use Design System on TypingMind?

Because you install it once and use it with any model. Design System 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 Design System in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Darcos-Loft/fluid/tree/main/design-system. 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 Design System?

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 Design System?

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

Is the Design System AI skill free?

Yes. It is published on GitHub by Darcos-Loft under the MIT license. 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 👇