Skip to main content
skill Claude Code CX Codex Cursor GitHub Copilot

mobile-design — Claude Code skill: what it does, how to install

Reviews and guides iOS, Android, React Native, and Flutter interfaces for touch targets, offline handling, and rendering performance.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add sickn33/agentic-awesome-skills --skill mobile-design -a claude-code
Open on GitHub

What mobile-design does

This skill stops coding assistants from treating mobile screens like miniature desktops. It enforces platform constraints: 44pt touch targets on iOS, 48dp on Android, thumb-friendly placement for primary actions, and explicit loading states. It flags unbounded ScrollView lists and directs the agent toward virtualized views like FlatList with stable IDs.

The rules separate what should be shared from what must stay native. Business logic and API contracts unify across platforms, while gestures, navigation, and pickers diverge. Hard bans block storing tokens in AsyncStorage, running animations on the JavaScript thread, and leaving debug logs in production.

Static code checks cannot measure battery drain or real frame drops. This skill provides guardrails for UI patterns, not a formal mobile compliance certification. You still need to run profiling on physical hardware before shipping.

What it helps with

  • replace unvirtualized scroll views with FlatList or ListView.builder
  • enforce minimum 44pt iOS and 48dp Android tap targets
  • migrate auth tokens from AsyncStorage to Keychain or SecureStore
  • add offline retry flows and explicit feedback for mobile screens

Example prompts for the agent

  • Review this React Native settings screen for touch target sizes and thumb zone reachability.
  • Check this Flutter list view implementation to eliminate redundant rebuilds and memory issues.
  • Audit our navigation flow to match iOS swipe-back and Android system-back behaviors.

How to install mobile-design

1Skills CLI (Vercel)

npx skills add sickn33/agentic-awesome-skills --skill mobile-design -a claude-code

2Manually: put the files in place

~/.claude/skills/mobile-design/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/mobile-design/

From the same set80

The whole set →
docker-expert sickn33 A skill that turns your AI agent into a Docker reviewer for Dockerfiles, multi-stage builds and container security. Useful when images and Compose files need a second look. Claude Code CX Codex Cursor +1 27,200installs typescript-expert sickn33 A skill for TypeScript and JavaScript work: it reads your project setup, fixes type errors and speeds up type checking. Useful once a TS codebase gets big. Claude Code CX Codex Cursor +1 12,600installs browser-automation sickn33 This skill builds browser checks around observed UI state and explicit outcomes. Use it for UI workflows, timing failures, or authorised page-data collection. Claude Code CX Codex Cursor +1 6,700installs nextjs-supabase-auth sickn33 This skill wires Supabase Auth into the Next.js App Router with clients, middleware, OAuth callbacks, and Server Actions. Use it when you need protected routes and session handling. Claude Code CX Codex Cursor +1 6,500installs 3d-web-experience sickn33 Helps build and debug web 3D scenes, product configurators, and portfolios. Covers stack choice, model loading, scroll interaction, and performance checks. Claude Code CX Codex Cursor +1 5,200installs prisma-expert sickn33 This skill helps inspect Prisma schemas, migrations, and queries. Use it to investigate an error or review database changes before deployment. Claude Code CX Codex Cursor +1 4,200installs playwright-skill sickn33 Write and run Playwright browser tests directly in Claude Code: responsive design checks, login flows, form submissions, screenshots. Executes locally via Node with a visible browser window. Claude Code CX Codex Cursor +1 3,900installs game-development sickn33 Guides game architecture decisions, platform choices, and core loop structure. Directs the assistant to specialized sub-skills for web, mobile, PC, or VR. Claude Code CX Codex Cursor +1 3,800installs

Similar

expo-dom expo Runs web code in a webview on native platforms and renders as-is on web. Lets you use web libraries like recharts or react-syntax-highlighter in Expo without rewriting. Claude Code CX Codex Cursor +1 20,800installs eas-simulator expo Runs remote iOS and Android simulators in the EAS cloud and lets an AI agent control them. Useful for testing mobile apps on Linux, in CI, or inside cloud sandboxes. Claude Code CX Codex Cursor +1 20,500installs antislop-layoutmobile miqdadbadjuber A skill for responsive layouts across phone and desktop widths. It checks breakpoints, reflow, grids, overflow, sizing, tap targets, and navigation. Claude Code CX Codex Cursor +1 5,700installs expo-app-clip expo Adds an iOS App Clip target to Expo projects — a lightweight app invoked from a URL without App Store installation. Claude Code CX Codex Cursor +1 19,600installs argent-screen-recording software-mansion Captures video of an iOS simulator or Android emulator screen as h264 mp4 with touch visualization overlaid. Use it to document app flows, animations, and interactions as self-explanatory video clips. Claude Code CX Codex Cursor +1 17,700installs expo-web-to-native expo Guides an existing React web app into a native iOS/Android app with Expo. Use it for a staged screen-by-screen migration. Claude Code CX Codex Cursor +1 19,500installs vercel-react-native-skills vercel A rules pack for React Native and Expo work: lists, animations, navigation, native modules. Load it so your agent makes mobile changes the same way every time. Claude Code CX Codex Cursor +1 253,900installs animate-expo emilkowalski Builds React Native and Expo animations using Reanimated and Gesture Handler. Helps keep motion on the UI thread and avoid dropped frames on physical devices. Claude Code CX Codex Cursor +1 135,900installs

Questions about mobile-design

How do I install mobile-design in Claude Code?

Run npx skills add sickn33/agentic-awesome-skills --skill mobile-design -a claude-code in your project terminal.

What does the mobile-design skill do?

It instructs the agent to apply mobile-first constraints across iOS, Android, React Native, and Flutter. It blocks common mobile anti-patterns such as undersized buttons, unkeyed list items, and insecure local storage.

Does this skill guarantee app store compliance?

No, it is not a compliance certification tool. Static instructions guide the assistant, but frame rates, touch accuracy, and battery consumption must still be measured on real test devices.

Source text

SKILL.md · MIT
---
name: mobile-design
description: "Design and review iOS, Android, React Native or Flutter interfaces for touch, accessibility, navigation, offline behavior and measured performance. Use for mobile app UI work; not a mobile compliance certification."
risk: critical
source: community
date_added: "2026-02-27"
---
# Mobile Design System

**(Mobile-First · Touch-First · Platform-Respectful)**

> **Philosophy:** Touch-first. Battery-conscious. Platform-respectful. Offline-capable.
> **Core Law:** Mobile is NOT a small desktop.
> **Operating Rule:** Think constraints first, aesthetics second.

This skill exists to **prevent desktop-thinking, AI-defaults, and unsafe assumptions** when designing or building mobile applications.

---

## 1. Scope and risk

Use the existing project/platform requirements and preserve its conventions.
Ask only for missing information that changes the implementation. Do not require
an interview or framework switch for a targeted fix. The former MFRI score was an
unvalidated heuristic with inconsistent dimensions/range; it is not a safety or
release gate. Record concrete interaction, data, accessibility and performance
risks instead.

## 2. Choose the relevant checks

For a new app, establish platform, framework, audience, device classes, navigation,
offline needs and actual output. For existing work, reuse that context. Read only
the reference material needed for the changed behavior. User scope and repository
instructions take precedence over this skill's suggested ceremony.

## 3. Mandatory Reference Reading (Enforced)

### Reference map (read what the task needs)

| File                          | Purpose                            | Status            |
| ----------------------------- | ---------------------------------- | ----------------- |
| **mobile-design-thinking.md** | Anti-memorization, context-forcing | Context reference |
| **touch-psychology.md**       | Fitts’ Law, thumb zones, gestures  | Task-dependent       |
| **mobile-performance.md**     | 60fps, memory, battery             | Task-dependent       |
| **mobile-backend.md**         | Offline sync, push, APIs           | Task-dependent       |
| **mobile-testing.md**         | Device & E2E testing               | Task-dependent       |
| **mobile-debugging.md**       | Native vs JS debugging             | Task-dependent       |

### Platform-Specific (Conditional)

| Platform       | File                |
| -------------- | ------------------- |
| iOS            | platform-ios.md     |
| Android        | platform-android.md |
| Cross-platform | BOTH above          |

Read the relevant platform guidance before changing platform-specific behavior.

---

## 4. AI Mobile Anti-Patterns (Hard Bans)

### 🚫 Performance Sins (Non-Negotiable)

| ❌ Never                   | Why                  | ✅ Always                                |
| ------------------------- | -------------------- | --------------------------------------- |
| ScrollView for long lists | Memory explosion     | FlatList / FlashList / ListView.builder |
| Unmeasured row churn | May cause avoidable work | Profile identity/state updates; memoize only where useful |
| Index as key              | Reorder bugs         | Stable ID                               |
| JS-thread animations      | Jank                 | Native driver / GPU                     |
| console.log in prod       | JS thread block      | Strip logs                              |
| Blanket memoization claims | Can add complexity without benefit | Profile and apply targeted optimization |

---

### 🚫 Touch & UX Sins

| ❌ Never               | Why                  | ✅ Always          |
| --------------------- | -------------------- | ----------------- |
| Undersized hit area | Miss taps | Use platform logical units: typically 44pt iOS / 48dp Android |
| Gesture-only action   | Excludes users       | Button fallback   |
| No loading state      | Feels broken         | Explicit feedback |
| No error recovery     | Dead end             | Retry + message   |
| Ignore platform norms | Muscle memory broken | iOS ≠ Android     |

---

### 🚫 Security Sins

| ❌ Never                | Why                | ✅ Always               |
| ---------------------- | ------------------ | ---------------------- |
| Tokens in AsyncStorage | Easily stolen      | SecureStore / Keychain |
| Embedded app secrets | Can be extracted | Keep server secrets on server; secure per-user credentials |
| Disabled TLS verification | MITM risk | Valid platform TLS; pinning only for a justified managed threat model |
| Log sensitive data     | PII leakage        | Never log secrets      |

---

## 5. Platform Unification vs Divergence Matrix

```
UNIFY                          DIVERGE
──────────────────────────     ─────────────────────────
Business logic                Navigation behavior
Data models                    Gestures
API contracts                  Icons
Validation                     Typography
Error semantics                Pickers / dialogs
```

### Platform Defaults

| Element   | iOS          | Android        |
| --------- | ------------ | -------------- |
| Font      | SF Pro       | Roboto         |
| Min touch | 44pt         | 48dp           |
| Back      | Edge swipe   | System back    |
| Sheets    | Bottom sheet | Dialog / sheet |
| Icons     | SF Symbols   | Material Icons |

---

## 6. Mobile UX Psychology (Non-Optional)

### Fitts’ Law (Touch Reality)

* Finger ≠ cursor
* Accuracy is low
* Reach matters more than precision

**Rules:**

* Primary CTAs live in **thumb zone**
* Destructive actions pushed away
* No hover assumptions

---

## 7. Performance Doctrine

### React Native (fixed-height illustrative pattern)

```ts
const Row = React.memo(({ item }) => (
  <View><Text>{item.title}</Text></View>
));

const renderItem = useCallback(
  ({ item }) => <Row item={item} />,
  []
);

<FlatList
  data={items}
  renderItem={renderItem}
  keyExtractor={(i) => i.id}
  getItemLayout={(_, i) => ({
    length: ITEM_HEIGHT,
    offset: ITEM_HEIGHT * i,
    index: i,
  })}
/>
```

### Flutter (illustrative static widget)

```dart
class Item extends StatelessWidget {
  const Item({super.key});

  @override
  Widget build(BuildContext context) {
    return const Text('Static');
  }
}
```

* `const` everywhere possible
* Targeted rebuilds only

---

## 8. Implementation evidence

State the target platform, changed behavior and checks actually performed. Profile
representative devices/data; a static pattern scan cannot measure touch targets,
contrast, frame rate, battery, platform navigation or secure storage behavior.

## 9. Framework choice

Preserve an existing stack unless a change is requested. For new work compare
team experience, native integrations, accessibility, deployment policies and
measured workload constraints. Expo OTA is bounded by runtime compatibility and
store policies; it does not authorize bypassing review or delivering arbitrary
native code. No framework is universally fastest or smallest.

## 10. Release Readiness Checklist

### Before Shipping

* [ ] Platform hit targets checked in logical units
* [ ] Offline handled
* [ ] Secure storage used
* [ ] Lists optimized
* [ ] Logs stripped
* [ ] Tested on low-end devices
* [ ] Accessibility labels present
* [ ] Concrete risks and any unavailable checks documented

---

## 11. Related Skills

* **frontend-design** – Visual systems & components
* **frontend-dev-guidelines** – RN/TS architecture
* **backend-dev-guidelines** – Mobile-safe APIs
* **error-tracking** – Crash & performance telemetry

---

> **Final Law:**
> Mobile users are distracted, interrupted, and impatient—often using one hand on a bad network with low battery.
> **Design for that reality, or your app will fail quietly.**

---

## When to Use
This skill is applicable to execute the workflow or actions described in the overview.

## Limitations
- Use this skill only when the task clearly matches the scope described above.
- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

## Audit helper and limits

Run `python scripts/mobile_audit.py . --json` from the intended project directory.
The helper is read-only, bounded and advisory. It never imports project code and
never declares compliance; `compliant` is null. Exit 2 means incomplete inspection
or no detected mobile source. Source-pattern hints can match comments or miss
behavior spread across files. Validate findings before editing. No simulator,
real-device, screen-reader or GPU run was performed in this catalog review.

Use [touch guidance](touch-psychology.md), [typography](mobile-typography.md),
[color](mobile-color-system.md), [navigation](mobile-navigation.md) and
[decisions](decision-trees.md) for focused checks. Code blocks are version-sensitive
fragments, not certified complete apps; verify current APIs before execution.

© sickn33 · MIT · sickn33/agentic-awesome-skills

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor