Appllama App Design Skill
A rigorous playbook for designing and shipping Expo/React Native screens that feel truly native, verified by simulator screen recordings.
Design & UIAdvanced★ 2,444⑂ 119AI score 9/10Last updated: Sep 6, 2026
What it does
- Enforces native fidelity laws for an Expo + Expo Router + TypeScript stack: semantic colors in both themes, SF Symbols,
borderCurve: 'continuous', platform type ramps, safe-area handling, haptics as punctuation, product-grade number formatting. - Codifies navigation semantics: push vs replace vs
dismissTo, choosing modal / formSheet / fullScreenModal / transparentModal, guarding one-way doors (sign-in, onboarding, purchase) withStack.Protected, and defining what back does on iOS and Android. - Anti-slop rules with a mechanical pre-flight count: one accent hue, one grey family, one radius scale, zero emoji in chrome, no unjustified gradients.
- Motion laws: a frequency gate (high-frequency interactions get platform defaults only), sub-300ms strong ease-out timing, springs that inherit gesture velocity, Reanimated worklets on the UI thread, Reduce Motion support.
- Also covers state architecture (TanStack Query, Zustand, MMKV), perceived performance (FlashList, skeletons, expo-image), and an image-asset generation pipeline, with depth split into five
references/docs. - A mandatory simulator loop: record the whole flow via
xcrun simctl io booted recordVideo, watch it twice (feel, then frame-by-frame) hunting dropped frames, wrong-theme flashes, and layout jumps.
Who it's for
- Expo / React Native developers and indie app builders.
- Anyone whose AI-generated screens keep looking like a template.
- Teams without a designer aiming for top-of-store UI polish.
Examples
- "Design the onboarding" → research reference patterns first, then land the final step with
replace+Stack.Protectedso back can't re-enter onboarding. - "Polish this paywall" → run the anti-slop pre-flight (one accent, one radius scale, no emoji), then verify light/dark and Dynamic Type XL in the simulator.
- "The bottom sheet feels stiff" → hand release velocity into a spring with detents, and confirm cancel-mid-drag behavior in the recording.
· · · Install guide · · ·
Try it now, no install
Paste this into Claude to use the skill without installing anything.
Read the instructions in this file and follow them to help me: https://raw.githubusercontent.com/Appllama/appllama-skills/HEAD/skills/appllama-app-design-skill/SKILL.md What I want: (describe your task here)
If Claude can't open the link, open it yourself and paste the contents instead.
↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.
Install in the Claude app (no terminal)
- Download the ZIP with the button below.
- In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
- Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
Install in Claude Code
Let Claude do it — paste this into Claude Code
Install the skill I found on Claude Skill Mart. Copy the skills/appllama-app-design-skill folder from the GitHub repo Appllama/appllama-skills into my ~/.claude/skills/appllama-app-design-skill/. When it's done, tell me in one line what this skill can do.
Install with a command instead
git clone https://github.com/Appllama/appllama-skills.git && mkdir -p ~/.claude/skills && cp -r appllama-skills/skills/appllama-app-design-skill ~/.claude/skills/⚠ This is a third-party skill. Check the source repository before installing.
- Open your terminal.
- Clone the repo:
git clone https://github.com/Appllama/appllama-skills.git - Create the skills folder:
mkdir -p ~/.claude/skills - Copy the skill:
cp -r appllama-skills/skills/appllama-app-design-skill ~/.claude/skills/ - Confirm the
references/markdown files came along with it. - Restart Claude Code, then try a prompt like "make this screen feel native".
- Optional: connect the Appllama MCP for reference-screen research, and install Xcode's iOS Simulator so the motion verification pass can actually run.
View source on GitHub ↗License: MIT