Skip to content
SkillModel-led4,626 tokens in use

appllama-app-design-skill

Build native-feeling Expo and React Native screens that hold up next to top-grossing apps: Apple HIG fidelity, navigation rules, restrained motion and a simulator-verified loop.

5,393 stars on the repository MIT LicenseAppllama/appllama-skills · skills/appllama-app-design-skill
npx skills@latest add appllama/appllama-skills --skill appllama-app-design-skill
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing appllama-app-design-skill costs

186tokens idle
4,626tokens in use
9,431tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter15/15
  • Structure19/25
  • Examples3/15
  • Output15/15
  • Size13/15
  • Resources15/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Fair
  • Development activity36
  • Maintenance20
  • Community44
  • Maturity20
  • Momentum40

This skill sets the quality bar and method for mobile UI work in Expo and React Native. It starts with research (study real top-grossing app screens, ideally through the Appllama MCP), then applies laws for native fidelity, navigation, anti-slop styling, motion, state and perceived performance.

A screen counts as finished only after it runs in the simulator, is screen-recorded as a whole flow and passes a per-screen checklist covering light and dark mode, safe areas, Dynamic Type, empty, loading and error states.

What You Get

  • A research-first workflow that pulls 10 or more reference screens for the screen type before any UI code
  • Native fidelity, navigation, anti-slop and motion laws the agent applies to every screen
  • A mechanical slop pre-flight that counts accent hues, corner radii, emoji icons and duplicate labels
  • A definition-of-done checklist and a simulator loop with full-flow screen recordings and a device matrix

Common Use Cases

  • Design and build an onboarding flow and paywall that match category conventions
  • Polish a screen so it feels native in light and dark mode
  • Decide which screens push, present as sheets or replace, and block going back after a purchase
  • Audit animations for what to delete, what runs on the wrong thread and what lacks velocity

What Makes It Unique

It combines design taste with checks the agent can run: counted anti-slop rules, a frequency gate that often concludes an animation should be deleted, spring rules that carry gesture velocity, navigation semantics for one-way doors, and a mandatory recorded and scrubbed simulator pass that screenshots alone cannot replace.

Under The Hood

The skill is instructions with five reference files and no scripts. The agent writes Expo and React Native code in your project, launches the iOS Simulator or Android emulator, takes screenshots and records video of flows with simctl, and may call the Appllama MCP, a remote service that returns real app screens and spends credits on a paid plan. It may also call an image generation tool or the Higgsfield MCP for illustration assets and run profiling tools.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers