Android Kotlin Compose logo

Android Kotlin Compose

Community
haidrrrry
android-kotlin-compose

Jetpack Compose UI engineering for 2026 — edge-to-edge, Material 3, recomposition stability, Modifier ordering, LazyColumn performance, and animations. Use when building composables, fixing jank, theming, adaptive layouts, Canvas drawing, auditing screens, or asking "why does my screen recompose", "Modifier order", "edge to edge Compose", "audit this composable", "review this screen".

Overview

Publisherhaidrrrry
Repositorycompose-kotlin-agent-skills
Skill nameandroid-kotlin-compose
Stars
63
Forks
8
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Android Kotlin Compose 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/haidrrrry/compose-kotlin-agent-skills/tree/main/skills/android-kotlin-compose
  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/haidrrrry/compose-kotlin-agent-skills.git /tmp/compose-kotlin-agent-skills
mkdir -p .claude/skills
cp -r /tmp/compose-kotlin-agent-skills/skills/android-kotlin-compose .claude/skills/android-kotlin-compose
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Android Kotlin Compose 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 Kotlin Compose 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 Kotlin Compose 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 Kotlin — Compose UI Module

Parent kit: ../../SKILL.md · Index: ../../AGENTS.md · Banned list: ../../references/00-banned-antipatterns.md

REVIEW MODE

Trigger phrases: "audit this file", "check this composable", "review this screen", "review mode", "a11y pass on this composable".

When triggered, silently run this 6-point checklist on the target file before responding. Cite failures by checklist number and banned-antipattern row from ../../references/00-banned-antipatterns.md.

#CheckFail if
1Modifier paramMissing modifier: Modifier = Modifier or not last optional param
2State hoistingScreen/business state inside @Composable that belongs in ViewModel
3Lazy list keysLazyColumn/LazyRow items missing key = {} or contentType = {}
4Lifecycle collectionUses collectAsState() instead of collectAsStateWithLifecycle()
5Side effects in compositionIO, DB, network, or viewModelScope work directly in composable body
6StabilityData class params to child composables lack @Stable or @Immutable

Output format for REVIEW MODE:

## Compose audit — <filename>

| # | Status | Finding |
|---|--------|---------|
| 1 | PASS/FAIL | ... |
...

### Banned antipatterns hit
- Row N: <pattern> → <fix>

### Suggested diff
<code block with minimal fix>

Load ../../references/17-accessibility.md when audit includes TalkBack, touch targets, or contrast.


AUTHORING MODE

Default behavior when writing new Compose UI (not auditing). Follow all rules below.

Read First

FileWhen
../../references/02-compose-ui.mdStability, slots, Material 3, CompositionLocal themes
../../references/03-animations.mdSprings, Canvas, gestures
../../references/10-performance.mdderivedStateOf, LazyColumn keys, baseline profiles
../../references/16-coil-image.mdAsyncImage, Coil 3.4 network dep
../../references/17-accessibility.mdSemantics, 48dp targets, WCAG

Edge-to-Edge (Default — AGP 9 / API 35+)

kotlin
class MainActivity : ComponentActivity() {
    override fun onCreate(savedInstanceState: Bundle?) {
        enableEdgeToEdge()
        super.onCreate(savedInstanceState)
        setContent {
            AppTheme {
                Scaffold(
                    modifier = Modifier.fillMaxSize(),
                    contentWindowInsets = WindowInsets(0, 0, 0, 0)
                ) { innerPadding ->
                    NavHost(
                        modifier = Modifier
                            .fillMaxSize()
                            .padding(innerPadding)
                    )
                }
            }
        }
    }
}
  • enableEdgeToEdge() on every ComponentActivity
  • Respect WindowInsets — never hardcode status bar padding
  • Use WindowInsets.safeDrawing for interactive content
  • Test gesture nav bar + display cutout on physical device

Composable Contract

kotlin
@Composable
fun AccountCard(
    account: AccountUi,
    onClick: () -> Unit,
    modifier: Modifier = Modifier  // always first param after required data
) {
    Card(
        modifier = modifier
            .fillMaxWidth()
            .clip(RoundedCornerShape(12.dp))
            .clickable(onClick = onClick)
    ) {
        Text(
            text = stringResource(R.string.account_title, account.name),
            style = MaterialTheme.typography.titleMedium
        )
    }
}

Recomposition Rules

  1. Extract sub-composables for separate restart scopes
  2. Defer scroll/animation reads: Modifier.offset { IntOffset(...) }
  3. @Immutable on UiState / list wrappers passed to children
  4. remember(keys) { derivedStateOf { } } for expensive derived values
  5. Never write state in composable body after read (backwards write)

LazyColumn Checklist

  • key = { it.id } on every items()
  • contentType when row layouts differ
  • Stable lambdas: remember(id) { { onClick(id) } }
  • No nested verticalScroll + LazyColumn
  • Sort/filter in ViewModel or remember, not inline in items {}

Anti-Patterns (Compose)

BannedFix
Hardcoded Text("Save")stringResource(R.string.action_save)
collectAsState() on AndroidcollectAsStateWithLifecycle()
Modifier.clickable before padding when touch target should exclude marginOrder: padding → clip → background → clickable
items(list) without keyitems(list, key = { it.id })
Raw fontSize = 16.spMaterialTheme.typography.bodyLarge

Full list: ../../references/00-banned-antipatterns.md

Frequently asked questions

What does the Android Kotlin Compose AI skill do?

Jetpack Compose UI engineering for 2026 — edge-to-edge, Material 3, recomposition stability, Modifier ordering, LazyColumn performance, and animations. Use when building composables, fixing jank, theming, adaptive layouts, Canvas drawing, auditing screens, or asking "why does my screen recompose", "Modifier order", "edge to edge Compose", "audit this composable", "review this screen".

Why use Android Kotlin Compose on TypingMind?

Because you install it once and use it with any model. Android Kotlin Compose 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 Kotlin Compose in TypingMind?

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

Which AI models can use Android Kotlin Compose?

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 Kotlin Compose?

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

Is the Android Kotlin Compose AI skill free?

Yes. It is published on GitHub by haidrrrry 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 👇