Mobile Ui Design logo

Mobile Ui Design

Organization
openvetta
mobile-ui-design

Design mobile-style HTML pages (iOS / Android) for preview in the Mobile UI Preview panel. Use when the user asks to build a mobile screen, app UI, phone mockup page, or "make this look like a native app". Enforces correct status-bar and bottom safe-area handling so content never hides under the notch/Dynamic Island or the home indicator.

Overview

Publisheropenvetta
Repositoryopen-vetta
Skill namemobile-ui-design
Stars
299
Forks
51
Bundled files
Instructions only
LicenseApache-2.0
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 openvetta on GitHub. Read the source before you install it.

Installation

Install the Mobile Ui 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.
    https://github.com/openvetta/open-vetta/tree/main/packages/plugins/externals/mobile-ui-preview/agent/skills/mobile-ui-design
  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/openvetta/open-vetta.git /tmp/open-vetta
mkdir -p .claude/skills
cp -r /tmp/open-vetta/packages/plugins/externals/mobile-ui-preview/agent/skills/mobile-ui-design .claude/skills/mobile-ui-design
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mobile Ui 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 Mobile Ui 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 Mobile Ui 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.

Mobile UI Design

Build single-file HTML pages that look like native mobile screens and preview correctly inside the Mobile UI Preview panel (iPhone / Android / iPad device frames).

The preview panel renders your HTML edge to edge inside the device screen and draws its own immersive status bar (clock, signal, wifi, battery) floating on top of your content. It does not shrink your content into the safe area for you. That means the two things that go wrong most often are:

  1. Content collides with the status bar at the top (title/text sits under the clock and battery).
  2. Content collides with the home indicator / gesture bar at the bottom (a fixed CTA button gets cut by the gesture area).

This skill exists to prevent both. Reserve the top and bottom safe areas explicitly; never paint interactive or important content into them.

Non-negotiable rules

  1. Viewport meta is required and must be viewport-fit=cover:

    html
    <meta name="viewport" content="width=device-width, initial-scale=1, viewport-fit=cover" />
  2. Reserve the top safe area (status bar). The panel overlays a status bar of roughly:

    • iPhone with Dynamic Island (15 Pro): ~54px
    • iPhone with notch (14): ~47px
    • Classic iPhone SE: ~20px
    • Android: ~28px
    • iPad: ~20–24px

    The iframe has no real notch, so env(safe-area-inset-top) resolves to 0. Do not rely on it alone. Use a variable with a sensible fallback and let env() upgrade it on real devices:

    css
    :root {
      --safe-top: max(env(safe-area-inset-top), 54px);
      --safe-bottom: max(env(safe-area-inset-bottom), 34px);
    }

    Default --safe-top to the tallest target you care about (54px covers Dynamic Island). If the design is meant only for SE-class devices, lower it to 20px.

  3. Reserve the bottom safe area (home indicator). Modern iPhones/Android reserve ~34px for the gesture bar. Any bottom-fixed bar (tab bar, primary CTA) must sit above it:

    css
    .bottom-bar { padding-bottom: var(--safe-bottom); }
  4. Fixed headers get the top inset, scroll content clears it. A sticky/fixed app header must add padding-top: var(--safe-top) so its title sits below the clock. A full-bleed hero image may extend under the status bar, but any text or control on it must still start below --safe-top.

  5. Full height, no page scroll bleed. Use height: 100dvh (or 100vh fallback) on the app root; scroll happens in an inner content region, not the <body>.

Reusable scaffold

Start every mobile page from this structure and fill in the content region:

html
<!doctype html>
<html lang="zh">
<head>
  <meta charset="utf-8" />
  <meta name="viewport" content="width=device-width, initial-scale=1, viewport-fit=cover" />
  <style>
    :root {
      --safe-top: max(env(safe-area-inset-top), 54px);
      --safe-bottom: max(env(safe-area-inset-bottom), 34px);
      --bg: #f2f2f7;
      --card: #ffffff;
      --text: #1c1c1e;
      --muted: #8e8e93;
      --tint: #007aff; /* iOS system blue */
    }
    * { box-sizing: border-box; margin: 0; padding: 0; }
    html, body { height: 100%; }
    body {
      font-family: -apple-system, "SF Pro Text", "Segoe UI", Roboto, system-ui, sans-serif;
      background: var(--bg);
      color: var(--text);
      -webkit-font-smoothing: antialiased;
    }
    .app { display: flex; flex-direction: column; height: 100dvh; }

    /* Fixed header: clears the status bar via --safe-top */
    .app-header {
      padding-top: var(--safe-top);
      padding-inline: 16px;
      padding-bottom: 10px;
      background: var(--card);
      border-bottom: 1px solid rgba(0,0,0,0.08);
    }
    .app-header h1 { font-size: 20px; font-weight: 700; }

    /* Scrollable content: never under the top bar, ends above the tab bar */
    .content { flex: 1; overflow-y: auto; padding: 16px; }

    /* Bottom bar: lifted above the home indicator via --safe-bottom */
    .tab-bar {
      background: var(--card);
      border-top: 1px solid rgba(0,0,0,0.08);
      padding-top: 8px;
      padding-bottom: var(--safe-bottom);
      display: flex;
      justify-content: space-around;
    }
  </style>
</head>
<body>
  <div class="app">
    <header class="app-header"><h1>标题</h1></header>
    <main class="content"><!-- 内容区 --></main>
    <nav class="tab-bar"><!-- 底部导航 --></nav>
  </div>
</body>
</html>

Platform style cues

Match the target OS the user names (default to iOS if unspecified):

  • iOS: system blue #007aff tint; generous 16px side padding; grouped rounded cards (border-radius: 12px); large bold navigation titles; -apple-system font; subtle hairline separators; bottom tab bar with icon + tiny label.
  • Android (Material): primary color surfaces, elevation via soft shadows, ripple-style buttons, FAB for the primary action, top app bar; Roboto. Reserve ~28px top inset instead of 54.

Layout checklist before finishing

  • viewport-fit=cover present.
  • --safe-top / --safe-bottom defined with max(env(...), fallback).
  • App header adds --safe-top; no title/icon overlaps the clock or battery.
  • Bottom bar / primary CTA adds --safe-bottom; nothing important touches the gesture bar.
  • Root is 100dvh, scrolling is inside .content, body itself does not scroll.
  • Tested mentally at the tallest device (Dynamic Island) and the shortest (SE): content still clears both insets.

Working with the preview

  • Save the page as a .html file inside the current scope; the panel lists it automatically and reloads on save.
  • Switch device model / orientation in the panel toolbar to verify safe areas across frames.
  • After the design is solid, "Generate engineering prompt" in the panel export menu turns the current page into an engineering prompt for productionizing it.

Frequently asked questions

What does the Mobile Ui Design AI skill do?

Design mobile-style HTML pages (iOS / Android) for preview in the Mobile UI Preview panel. Use when the user asks to build a mobile screen, app UI, phone mockup page, or "make this look like a native app". Enforces correct status-bar and bottom safe-area handling so content never hides under the notch/Dynamic Island or the home indicator.

Why use Mobile Ui Design on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/openvetta/open-vetta/tree/main/packages/plugins/externals/mobile-ui-preview/agent/skills/mobile-ui-design. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Mobile Ui 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 Mobile Ui Design?

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

Is the Mobile Ui Design AI skill free?

Yes. It is published on GitHub by openvetta under the Apache-2.0 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 👇