Mobile Design System logo

Mobile Design System

Organization
draftbit
mobile-design-system

Propose and generate a React Native app's design system - semantic color tokens (light + dark), type scale with Dynamic Type bounds, radius/elevation/spacing scales, haptics and motion posture - as a SAFE/RISK proposal, then write the actual theme files (NativeWind config or StyleSheet tokens) and MOBILE-DESIGN.md. Use when starting an app's visual identity, when asked for a theme/palette/design tokens, or when an app has inline styles and needs a token system. For building screens with the system use mobile-taste; for auditing an existing app use mobile-design-review.

Overview

Publisherdraftbit
Repositorymobile-taste-skill
Skill namemobile-design-system
Stars
8
Forks
1
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Mobile 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/draftbit/mobile-taste-skill/tree/main/skills/mobile-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/draftbit/mobile-taste-skill.git /tmp/mobile-taste-skill
mkdir -p .claude/skills
cp -r /tmp/mobile-taste-skill/skills/mobile-design-system .claude/skills/mobile-design-system
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mobile 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 Mobile 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 Mobile 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.

mobile-design-system: Tokens, Theme, and the SAFE/RISK Proposal

One coherent system, proposed honestly, then written as real files. No screens.

Flow

1. Stack sniff + App Read essentials

Read package.json / tailwind config / existing theme files / MOBILE-DESIGN.md. Detect the styling system (NativeWind, StyleSheet, Tamagui, Paper) - the output format follows it. Establish app kind, audience, platform posture, and dials (one line each; inherit from MOBILE-DESIGN.md when present). Apply the category bias table (mobile-taste SKILL.md 1.A2).

2. The SAFE/RISK proposal

Propose the ENTIRE system as one package, split explicitly:

SAFE CHOICES - the category baseline the user expects. For most apps: system fonts, native chrome, a restrained neutral ramp, platform-conventional radii. Say plainly that these are safe and why safe is right here (or isn't).

RISKS (at least 2, at most 4) - deliberate departures, each with:

RISK: <the move>            e.g. "true-black OLED dark mode as the primary theme"
gain: <what it buys>        "distinctive night identity, battery on OLED"
cost: <what it costs>       "elevation must come from borders, not shadows"

A proposal with zero risks is a template; a proposal that is all risks is a costume.

Coherence validation - if two choices fight (dense pro-tool density + playful rounded type; per-platform posture + a fully custom tab bar), flag it in one sentence and propose the resolution. Flag, never silently "fix".

The proposal covers: palette (semantic tokens: background, surface, text-primary, text-muted, accent, border, destructive - light AND dark values), type scale (display/title/body/caption + Dynamic Type bounds per SKILL.md 6.1), spacing scale, radius scale + shape lock, elevation tokens (iOS shadow + Android elevation pairs), icon family + stroke weight, haptics vocabulary, motion posture (the three dials' implications), and the signature element budget.

Hard rules inherited from mobile-taste 6.2: one accent; one gray family; no indigo pipeline; saturation < 80% default; both modes from day one; OLED pure black allowed only as a declared deliberate choice.

3. Preview (optional, offer once)

Offer a self-contained HTML specimen - one file, no external requests: the palette as swatches (both modes, toggle), the type scale rendered in the actual (system or declared) fonts, radius/elevation samples on mock components. Open it locally. This is the no-tooling path and it is the primary path; do not depend on image generation or external binaries.

4. Write the real files

Per the sniffed stack:

  • NativeWind: tailwind.config theme extension + theme/tokens.ts (+ vars() wiring if the project uses CSS-variable theming) + dark values.
  • StyleSheet: theme/tokens.ts with typed color/type/spacing/radius/elevation objects and a useTheme() hook honoring useColorScheme.
  • Existing token file present: EXTEND it; renaming existing token names is on the never-change-silently list (../_shared/references/redesign-protocol.md).

5. Persist to MOBILE-DESIGN.md

Write (or refresh, with a delta report) the ## Design System section: the approved proposal, the RISK register, and where the token files live. Later sessions and sibling skills read this before any UI decision.

Rules that bind this skill

  • Propose once, coherently - not a menu of five palettes to pick from. One system with named risks beats a mood board.
  • Every value in the written files traces to the approved proposal. No stowaway tokens.
  • If the user rejects a RISK, replace it with the SAFE version and note the swap in MOBILE-DESIGN.md; do not quietly keep it.

Frequently asked questions

What does the Mobile Design System AI skill do?

Propose and generate a React Native app's design system - semantic color tokens (light + dark), type scale with Dynamic Type bounds, radius/elevation/spacing scales, haptics and motion posture - as a SAFE/RISK proposal, then write the actual theme files (NativeWind config or StyleSheet tokens) and MOBILE-DESIGN.md. Use when starting an app's visual identity, when asked for a theme/palette/design tokens, or when an app has inline styles and needs a token system. For building screens with the system use mobile-taste; for auditing an existing app use mobile-design-review.

Why use Mobile Design System on TypingMind?

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

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

Which AI models can use Mobile 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 Mobile Design System?

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

Is the Mobile Design System AI skill free?

It is published on GitHub by draftbit. 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 👇