Nothing Design logo

Nothing Design

CommunityPopular
dominikmartn
nothing-design

This skill should be used when the user explicitly says "Nothing style", "Nothing design", "/nothing-design", or directly asks to use/apply the Nothing design system. NEVER trigger automatically for generic UI or design tasks.

Overview

Publisherdominikmartn
Repositorynothing-design-skill
Skill namenothing-design
Stars
2.8K
Forks
168
Bundled files
3
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.

  • 3 bundled files

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

  • Open source

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

Installation

Install the Nothing Design 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/dominikmartn/nothing-design-skill.git /tmp/nothing-design-skill
mkdir -p .claude/skills
cp -r /tmp/nothing-design-skill/nothing-design .claude/skills/nothing-design
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Nothing Design 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 Nothing Design 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 Nothing Design 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.

Nothing-Inspired UI/UX Design System

A senior product designer's toolkit trained in Swiss typography, industrial design (Braun, Teenage Engineering), and modern interface craft. Monochromatic, typographically driven, information-dense without clutter. Dark and light mode with equal rigor.

Before starting any design work, declare which Google Fonts are required and how to load them (see references/tokens.md Section 1). Never assume fonts are already available.


1. DESIGN PHILOSOPHY

  • Subtract, don't add. Every element must earn its pixel. Default to removal.
  • Structure is ornament. Expose the grid, the data, the hierarchy itself.
  • Monochrome is the canvas. Color is an event, not a default — except when encoding data status (see Section 3).
  • Type does the heavy lifting. Scale, weight, and spacing create hierarchy — not color, not icons, not borders.
  • Both modes are first-class. Dark mode: OLED black. Light mode: warm off-white. Neither is "derived" — both get full design attention. Ask the user which mode to start with.
  • Industrial warmth. Technical and precise, but never cold. A human hand should be felt.

2. CRAFT RULES — HOW TO COMPOSE

2.1 Visual Hierarchy: The Three-Layer Rule

Every screen has exactly three layers of importance. Not two, not five. Three.

LayerWhatHow
PrimaryThe ONE thing the user sees first. A number, a headline, a state.Doto or Space Grotesk at display size. --text-display. 48–96px breathing room.
SecondarySupporting context. Labels, descriptions, related data.Space Grotesk at body/subheading. --text-primary. Grouped tight (8–16px) to the primary.
TertiaryMetadata, navigation, system info. Visible but never competing.Space Mono at caption/label. --text-secondary or --text-disabled. ALL CAPS. Pushed to edges or bottom.

The test: Squint at the screen. Can you still tell what's most important? If two things compete, one needs to shrink, fade, or move.

Common mistake: Making everything "secondary." Evenly-sized elements with even spacing = visual flatness. Be brave — make the primary absurdly large and the tertiary absurdly small. The contrast IS the hierarchy.

2.2 Font Discipline

Per screen, use maximum:

  • 2 font families (Space Grotesk + Space Mono. Doto only for hero moments.)
  • 3 font sizes (one large, one medium, one small)
  • 2 font weights (Regular + one other — usually Light or Medium, rarely Bold)

Think of it as a budget. Every additional size/weight costs visual coherence. Before adding a new size, ask: can I create this distinction with spacing or color instead?

DecisionSizeWeightColor
Heading vs. bodyYesNoNo
Label vs. valueNoNoYes
Active vs. inactive navNoNoYes
Hero number vs. unitYesNoNo
Section title vs. contentYesOptionalNo

Rule of thumb: If reaching for a new font-size, it's probably a spacing problem. Add distance instead.

2.3 Spacing as Meaning

Spacing is the primary tool for communicating relationships.

Tight (4–8px)   = "These belong together" (icon + label, number + unit)
Medium (16px)    = "Same group, different items" (list items, form fields)
Wide (32–48px)   = "New group starts here" (section breaks)
Vast (64–96px)   = "This is a new context" (hero to content, major divisions)

If a divider line is needed, the spacing is probably wrong. Dividers are a symptom of insufficient spacing contrast. Use them only in data-dense lists where items are structurally identical.

2.4 Container Strategy (prefer top)

  1. Spacing alone (proximity groups items)
  2. A single divider line
  3. A subtle border outline
  4. A surface card with background change

Each step down adds visual weight. Use the lightest tool that works. Never box the most important element — let it float on the background.

2.5 Color as Hierarchy

In a monochrome system, the gray scale IS the hierarchy. Max 4 levels per screen:

--text-display (100%) → Hero numbers. One per screen.
--text-primary (90%)  → Body text, primary content.
--text-secondary (60%) → Labels, captions, metadata.
--text-disabled (40%) → Disabled, timestamps, hints.

Red (#D71921) is not part of the hierarchy. It's an interrupt — "look HERE, NOW." If nothing is urgent, no red on the screen.

Data status colors (success green, warning amber, accent red) are exempt from the "one accent" rule when encoding data values. Apply color to the value itself, not labels or row backgrounds. See references/tokens.md for the full color system.

2.6 Consistency vs. Variance

Be consistent in: Font families, label treatment (always Space Mono ALL CAPS), spacing rhythm, color roles, component shapes, alignment.

Break the pattern in exactly ONE place per screen: An oversized number, a circular widget among rectangles, a red accent among grays, a Doto headline, a vast gap where everything else is tight.

This single break IS the design. Without it: sterile grid. With more than one: visual chaos.

2.7 Compositional Balance

Asymmetry > symmetry. Centered layouts feel generic. Favor deliberately unbalanced composition:

  • Large left, small right: Hero metric + metadata stack.
  • Top-heavy: Big headline near top, sparse content below.
  • Edge-anchored: Important elements pinned to screen edges, negative space in center.

Balance heavy elements with more empty space, not with more heavy elements.

2.8 The Nothing Vibe

  1. Confidence through emptiness. Large uninterrupted background areas. Resist filling space.
  2. Precision in the small things. Letter-spacing, exact gray values, 4px gaps. Micro-decisions compound into craft.
  3. Data as beauty. 36GB/s in Space Mono at 48px IS the visual. No illustrations needed.
  4. Mechanical honesty. Controls look like controls. A toggle = physical switch. A gauge = instrument.
  5. One moment of surprise. A dot-matrix headline. A circular widget. A red dot. Restraint makes the one expressive moment powerful.
  6. Percussive, not fluid. Imagine UI sounds: click not swoosh, tick not chime. Design transitions that feel mechanical and precise.

2.9 Visual Variety in Data-Dense Screens

When 3+ data sections appear on one screen, vary the visual form:

FormBest forWeight
Hero number (large Doto/Space Mono)Single key metricHeavy — use once
Segmented progress barProgress toward goalMedium
Concentric rings / arcsMultiple related percentagesMedium
Inline compact barSecondary metrics in rowsLight
Number-only with status colorValues without proportionLightest
SparklineTrends over timeMedium
Stat row (label + value)Simple data pointsLight

Lead section → heaviest treatment. Secondary → different form. Tertiary → lightest. The FORM varies, the VOICE stays the same.


3. ANTI-PATTERNS — WHAT TO NEVER DO

  • No gradients in UI chrome
  • No shadows. No blur. Flat surfaces, border separation.
  • No skeleton loading screens. Use [LOADING...] text or segmented spinner.
  • No toast popups. Use inline status text: [SAVED], [ERROR: ...]
  • No sad-face illustrations, cute mascots, or multi-paragraph empty states
  • No zebra striping in tables
  • No filled icons, multi-color icons, or emoji as UI
  • No parallax, scroll-jacking, or gratuitous animation
  • No spring/bounce easing. Use subtle ease-out only.
  • No border-radius > 16px on cards. Buttons are pill (999px) or technical (4–8px).
  • Data visualization: differentiate with opacity (100%/60%/30%) or pattern (solid/striped/dotted) before introducing color.

4. WORKFLOW

  1. Declare fonts — tell the user which Google Fonts to load (see references/tokens.md)
  2. Ask mode — dark or light? Neither is default.
  3. Sketch hierarchy — identify the 3 layers before writing any code
  4. Compose — apply craft rules (Sections 2.1–2.9)
  5. Check tokens — consult references/tokens.md for exact values
  6. Build components — consult references/components.md for patterns
  7. Adapt to platform — consult references/platform-mapping.md for output conventions

5. REFERENCE FILES

For detailed token values, component specs, and platform-specific guidance:

  • references/tokens.md — Fonts, type scale, color system (dark + light), spacing scale, grid, motion, iconography, dot-matrix motif
  • references/components.md — Cards, buttons, inputs, lists, tables, nav, tags, segmented controls, progress bars, charts, widgets, overlays, state patterns
  • references/platform-mapping.md — HTML/CSS, SwiftUI, React/Tailwind, Paper output conventions

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 Nothing Design AI skill do?

This skill should be used when the user explicitly says "Nothing style", "Nothing design", "/nothing-design", or directly asks to use/apply the Nothing design system. NEVER trigger automatically for generic UI or design tasks.

Why use Nothing Design on TypingMind?

Because you install it once and use it with any model. Nothing Design 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 Nothing Design in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/dominikmartn/nothing-design-skill/tree/main/nothing-design. 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 Nothing Design?

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 Nothing Design?

As many as you like. As long as a model supports skills, you can use Nothing Design with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Nothing Design AI skill free?

Yes. It is published on GitHub by dominikmartn 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 👇