// the find
Appllama/appllama-skills
A builder, not just a researcher. Agent skills that turn top-grossing app patterns into native-quality mobile screens.
A pair of 'agent skills' (installable into Claude Code, Cursor, Codex, etc.) that tell a coding agent how to build Expo/React Native mobile screens matching the UI patterns of top-grossing apps. One skill drives research against Appllama's paid MCP design library, the other is a build-quality bar (native controls, navigation rules, animation discipline, simulator verification). It's aimed at teams using AI agents to build mobile app UI who want a shortcut past generic-looking screens.
The design skill's reference docs (motion.md, native-controls.md, simulator-loop.md) encode real mobile UI opinions — push vs. replace navigation, no animations on the JS thread, springs matched to finger velocity — that's more specific than the usual 'make it look nice' skill prompt. It's distributed through the skills.sh convention so it installs the same way across 70+ agent clients, not just Claude. The design skill is explicitly usable standalone without the paid MCP, so there's a real free subset. MIT licensed with a clear trademark carve-out.
The actual differentiator — the library of top-grossing app screens — sits behind a paid MCP with a credit system, so the open-source repo is really a prompt wrapper around a closed commercial backend; you can't evaluate or reproduce the 'studied against top apps' claim yourself. There's no code in this repo at all, just markdown: no tests, no CI, no versioning, so there's no way to tell if a SKILL.md edit breaks behavior before it ships. Efficacy claims (native-quality, simulator-verified) are unverifiable without both the agent and a paid account, and the install path going through a third-party `skills@latest` CLI adds a dependency and trust surface beyond the repo itself.