Appllama

View saved version →

---
name: appllama-app-design-skill
description: Build native-feeling, benchmark-quality mobile app screens (Expo / React Native). Use when designing or implementing any mobile UI — screens, flows, onboarding, paywalls, tab bars, sheets, settings, empty states — or when polishing motion, navigation, typography, dark mode, or perceived performance. Enforces Apple HIG fidelity, semantic colors, native controls, anti-slop discipline, navigation semantics (push vs replace, modal vs sheet vs overlay, the one-way doors where back must not exist), purposeful Reanimated motion, a full-motion simulator-verified iteration loop, and a study-real-apps-first workflow (pairs with the Appllama MCP). Trigger on "build a screen", "make this screen better", "design the onboarding", "wire up this flow", "polish the UI", "make it feel native", or any mobile design/implementation task.
license: MIT
metadata:
  author: Appllama (appllama.io)
  version: 1.3.0
---

# Appllama App Design Skill

You are building screens that will sit on a phone next to the best-designed apps
in the world. The user will compare your output to those apps within seconds of
launching it. This skill defines the bar and the method for clearing it.

## The Prime Directive: study before you draw

Never design a screen from imagination when you can study how top apps solved
the same screen. Real, shipping, revenue-ranked apps encode thousands of hours
of design iteration and A/B testing. Your first move on any screen is research:

1. If the **Appllama MCP** is connected, pull real screens for the category and
   screen type you are building (see the `appllama-usage` skill for the exact
   research playbooks). Study 20–30 screens before writing a line of UI code.
2. Extract the **pattern, not the pixels**: layout skeleton, information
   hierarchy, control choices, spacing rhythm, where the primary CTA sits, what
   gets an illustration vs. plain text, how progress is communicated.
   Note: every Appllama image and video carries a small Appllama watermark in
   the top-left corner. It is provenance, not design — ignore it when reading
   a screen (it may sit over the status bar or a back button) and never
   reproduce it in anything you build.
3. Then design **your** screen: same proven skeleton, your product's voice.
   Copying a competitor's screen 1:1 is both lazy and legally risky; shipping a
   screen that ignores every convention users already know is worse.

## Platform baseline

Default stack assumptions (override only if the project already differs):

- **Expo + Expo Router**, React Native, TypeScript.
- `react-native-reanimated` for motion, `react-native-gesture-handler` for
  gestures, `@shopify/flash-list` (or FlashList v2) for any list that can grow.
- `expo-image` for images (and SF Symbols via `source="sf:name"` on iOS),
  `expo-video` / `expo-audio` (never the deprecated `expo-av`).
- `react-native-safe-area-context` for insets. Never hard-code notch numbers.
- `process.env.EXPO_OS` over `Platform.OS` for compile-time platform checks.

## Native fidelity laws

These are the details that separate "web page in a wrapper" from "native app".
Violating any of them is a finding, not a style preference.

1. **Semantic colors, both themes, day one.** Use system/semantic color tokens
   (e.g. `Color` from `expo-router` on iOS: `Color.ios.label`,
   `Color.ios.secondarySystemBackground`; Material dynamic colors on Android).
   Every screen must render correctly in light AND dark before it is "done".
   Never pass semantic color objects into Reanimated animated styles — resolve
   to strings first.
2. **Native controls over rebuilt ones.** Switch, Slider, SegmentedControl,
   context menus, date pickers: use the native control or a faithful wrapper.
   A rebuilt toggle that animates 50 ms differently than iOS's reads as fake
   instantly.
3. **SF Symbols / Material Symbols for iconography.** On iOS prefer SF Symbols
   (`expo-image` with `sf:` sources, or `expo-symbols`); t

Preview of the first 4,000 characters. Read full instructions →

Referenced files: 5 — file references are metadata, not package contents.

View saved version →

---
name: appllama-usage
description: Use the Appllama MCP (mcp.appllama.io) well — research real top-grossing mobile apps, their screens, flows, and UI elements, then build from what you learn. Load when the Appllama MCP is connected and the task involves building a mobile app or screen, researching app design patterns, studying onboarding/paywall/feature flows, improving an existing screen, or whenever an appllama_* / search_apps / list_app_screens tool is available. Covers the tool map, pagination, expiring media, and the full build-from-research playbooks.
license: MIT
metadata:
  author: Appllama (appllama.io)
  version: 1.1.0
---

# Appllama Usage Skill

Appllama is the design library of top-grossing mobile apps — their real
screens, flows, and UI patterns, with revenue and download context. The MCP
puts that library in an agent's hands: **not just a research tool, a builder's
tool.** You study what already wins, then you build something better.

Pair this skill with **appllama-app-design-skill** for every design/implementation
step — this skill tells you what to study; that one tells you how to build.

## Ground rules (read first)

1. **Start with `get_credits` — it's free.** It tells you the balance,
   limits, and reset date. Pro includes 1,500 credits a month (they reset in
   full on the 1st, UTC); every other call spends 1 credit.
2. **Go deep.** Design language lives in the whole journey, not a sample —
   walk every screen of the apps that matter for the task, images included.
   That is exactly what the library is for. The one thing that's against the
   terms is harvesting: sweeping the catalog to extract the dataset itself
   rather than to answer a real task. That isn't research, and it's detected
   server-side.
3. **Media URLs expire in ~1 hour.** Download/view what you study promptly.
   If links died mid-task, re-request that page for fresh ones — screen ids
   are durable, links are not.
4. **Ignore the watermark.** Every Appllama image and video carries a small
   Appllama watermark in the top-left corner. It is provenance, not part of
   the screen — don't let it skew your read of that corner (status bar,
   back button, title), and never reproduce it in anything you build.
5. **Pagination is sequential.** Every list response carries `next_cursor`;
   pass it back to continue. You cannot jump to page N — and a cursor only
   works for the same query that minted it. If a cursor errors, drop it and
   restart from page one.
6. **If you hit a rate limit, wait it out.** The per-minute and per-day
   limits sit far above real research; on the rare hit, wait the stated
   time — don't retry-hammer.
7. **Errors are instructions.** Tool errors are written to be acted on
   (expired cursor → restart; out of credits → tell the user their credits
   reset on the 1st and they can request more in Settings → Usage).

## Tool map

| Tool | What it gives you | Typical use |
|---|---|---|
| `get_credits` | Balance, limits, reset date. **Free.** | Session start |
| `search_apps` | 10 apps/page: name, revenue, downloads, rating, launch date, screens count, **flow list with screen counts**. Natural-language `query` + filters (revenue/downloads/rating/launch date/price/onboarding steps) + `sort` + `board_id` | Find the top apps for a category or need |
| `get_app` | One app in full: ratings breakdown, category rank, IAP pricing, top countries, flows | Decide if an app deserves a deep study |
| `list_app_screens` | 10 screens/page **in journey order** (welcome → onboarding → paywall → product), each with media URL, flow, UI elements, colors. Filter by `flow` or `section` | Walk an app screen by screen |
| `search_screens` | Screens across the whole library. `mode="keyword"` matches screen names + filters (flow, screen_type, element, app_id); `mode="semantic"` searches by meaning/visual language | Gather design references for one screen type |
| `get_screen` | One screen in full + up to 5 visually similar screens from other 

Preview of the first 4,000 characters. Read full instructions →

Referenced files: 4 — file references are metadata, not package contents.