Android Native Ui logo

Android Native Ui

Community
kemiljk
android-native-ui

Build or review Android interfaces in Compose or Views, including Material conventions, accessibility, adaptive layout, and state.

Overview

Publisherkemiljk
Repositoryskills
Skill nameandroid-native-ui
Stars
64
Forks
3
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by kemiljk on GitHub. Read the source before you install it.

Installation

Install the Android Native Ui AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/kemiljk/skills/tree/main/skills/android-native-ui
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/kemiljk/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/android-native-ui .claude/skills/android-native-ui
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Android Native Ui in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Android Native Ui on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Android Native Ui is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Android Native UI

Build and review Android interfaces around platform contracts: Compose semantics, lifecycle-aware state, adaptive windows, Material/system integration, back navigation, and accessibility—not web ARIA or pixel-only parity.

Identify the UI boundary

Map Android Views versus Compose, Material 3/custom design system, minimum SDK, navigation library, state holder, and whether the project is Android-only or Compose Multiplatform.

For Compose Multiplatform, keep portable UI in commonMain; isolate Android APIs such as Context, permissions, back handling, and window APIs at the platform boundary. Verify each shipped target independently.

Fresh platform guidance

Before prescribing or implementing APIs, behaviour, Material conventions, tooling, or verification that may vary by Android/Compose/Kotlin release, search current primary Android sources: developer.android.com, AndroidX release notes, and Kotlin documentation where relevant. Check the project's SDK, Compose BOM/library versions, and shipped Compose Multiplatform targets before recommending an API. The examples here express durable contracts; they are not a substitute for release-specific documentation.

State, effects, and component APIs

Hoist state only as high as the caller that needs to control it. Model durable screen state separately from one-shot events. Collect flows with lifecycle awareness on Android, and use LaunchedEffect, DisposableEffect, or other explicit effects for imperative work—not a composable body.

kotlin
@Composable
fun SaveButton(
    enabled: Boolean,
    onSave: () -> Unit,
    modifier: Modifier = Modifier,
) {
    Button(
        onClick = onSave,
        enabled = enabled,
        modifier = modifier,
    ) {
        Text("Save")
    }
}

Reusable composables should expose a Modifier at the outer boundary, preserve native control semantics, and avoid growing boolean/primitive parameter lists where a state model or slot is clearer. Check modifier order deliberately: hit targets, clipping, padding, indication, and semantics can change with order.

Compose performance and motion

Composition, layout, and drawing are different phases. Do not write layout-derived state that a sibling reads during composition without proving the feedback loop is safe. Avoid expensive allocations or collection work in hot composable bodies; use stable keys in lazy collections. Read animation, scroll, and gesture state in the latest phase that can produce the intended effect.

Animations should be state-driven, cancellable where interaction demands it, and usable when Android's animator duration scale is reduced or disabled. Wait for the visible or semantic completion condition before counting animations or reading final state.

Accessibility and adaptation

Compose uses a semantics tree, not ARIA. Test content descriptions, roles, state descriptions, custom actions, traversal order, merged semantics, focus, TalkBack, touch targets, and disabled state. contentDescription = null is correct only for decorative content.

Use window size classes and available space rather than device labels. Test compact and expanded windows, large font scale, dark theme, display cutouts/insets, keyboard, layout direction, and predictive/system back where relevant.

kotlin
Icon(
    imageVector = Icons.Default.Star,
    contentDescription = null, // decorative beside visible text
)

Read references/android-verification.md before making rendered Android claims. It contains the minimum evidence lane and semantics-based examples.

Prefer / reject

PreferReject
Material/native control semantics with intentional themingClickable layout that loses role, state, or keyboard/accessibility behaviour
Immutable UI state and lifecycle-aware collectionSide effects or mutable event handling in composition
Stable lazy keys and phase-appropriate readsIndex keys and composition/layout feedback loops
Semantics tests plus rendered checksScreenshot-only claims about accessibility or state
Window-size adaptationPhone-only layouts stretched across tablets, foldables, and desktop

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Android Native Ui AI skill do?

Build or review Android interfaces in Compose or Views, including Material conventions, accessibility, adaptive layout, and state.

Why use Android Native Ui on TypingMind?

Because you install it once and use it with any model. Android Native Ui is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Android Native Ui in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/kemiljk/skills/tree/main/skills/android-native-ui. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Android Native Ui?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Android Native Ui?

As many as you like. As long as a model supports skills, you can use Android Native Ui with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Android Native Ui AI skill free?

Yes. It is published on GitHub by kemiljk under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇