Modern Jetpack Compose logo

Modern Jetpack Compose

Community
anhvt52
modern-jetpack-compose

Guides writing, reviewing, and reasoning about modern Android UI code using Jetpack Compose. Covers best practices for state management, side effects, recomposition, navigation, Material 3 design, accessibility, and performance. Use when reading, writing, or reviewing any Jetpack Compose project.

Overview

Publisheranhvt52
Repositoryjetpack-compose-skills
Skill namemodern-jetpack-compose
Stars
100
Forks
4
Bundled files
12
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.

  • 12 bundled files

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

  • Open source

    Published by anhvt52 on GitHub. Read the source before you install it.

Installation

Install the Modern Jetpack 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/anhvt52/jetpack-compose-skills/tree/master/modern-jetpack-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/anhvt52/jetpack-compose-skills.git /tmp/jetpack-compose-skills
mkdir -p .claude/skills
cp -r /tmp/jetpack-compose-skills/modern-jetpack-compose .claude/skills/modern-jetpack-compose
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Modern Jetpack 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 Modern Jetpack 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 Modern Jetpack 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.

Review or generate Jetpack Compose code for correctness, modern API usage, and adherence to Android best practices. Report only genuine issues — do not nitpick style unless it contradicts a clear rule.

Review / Generation Process

When reviewing existing code, follow these steps in order:

  1. Check for deprecated or outdated APIs → references/api.md
  2. Review composable structure and composition patterns → references/composables.md
  3. Validate state management and data flow → references/state.md
  4. Validate side-effect usage → references/effects.md
  5. Check recomposition stability → references/recomposition.md
  6. Validate navigation implementation → references/navigation.md
  7. Check Material 3 / Expressive design compliance → references/design.md
  8. Validate accessibility → references/accessibility.md
  9. Check performance → references/performance.md
  10. Quick Kotlin code review → references/kotlin.md
  11. Final code hygiene check → references/hygiene.md

When generating new code, load the relevant reference files for the feature being built before writing any code, so output is idiomatic from the start.

For partial reviews or targeted generation, load only the relevant reference files.

Core Instructions

  • Target Compose BOM 2024.x by default. Note where BOM 2025.x (Material Expressive) introduces new components or APIs.
  • Use Material 3. Do not use Material 2 unless the project already uses it.
  • Architecture: MVVM with unidirectional data flow (UDF). ViewModel + StateFlow for screen state. Compose UI observes state, emits events.
  • Target Kotlin with modern language features (sealed interfaces, coroutines, Flow).
  • Do not introduce third-party libraries without asking first.
  • Each composable should live in its own file for non-trivial components.
  • Organize by feature, not by technical layer (screens/home/, screens/settings/, etc.).

Output Format

Organize findings by file. For each issue:

  1. State the file and relevant line(s).
  2. Name the rule being violated.
  3. Show a brief before/after Kotlin snippet.

Skip files with no issues. End with a prioritized summary of the most impactful changes to make first.

Example output:

HomeScreen.kt

Line 14: Use collectAsStateWithLifecycle() instead of collectAsState().

kotlin
// Before
val uiState by viewModel.uiState.collectAsState()

// After
val uiState by viewModel.uiState.collectAsStateWithLifecycle()

Line 42: Provide key in LazyColumn for stable item identity.

kotlin
// Before
LazyColumn {
    items(books) { book ->
        BookItem(book)
    }
}

// After
LazyColumn {
    items(books, key = { it.id }) { book ->
        BookItem(book)
    }
}

Line 67: Image missing contentDescription — required for accessibility.

kotlin
// Before
Image(painter = painterResource(R.drawable.cover), contentDescription = null)

// After — if decorative:
Image(painter = painterResource(R.drawable.cover), contentDescription = null) // OK if truly decorative

// After — if meaningful:
Image(
    painter = painterResource(R.drawable.cover),
    contentDescription = stringResource(R.string.book_cover_description)
)

Summary

  1. State (high): collectAsState() on line 14 does not respect lifecycle — replace with collectAsStateWithLifecycle().
  2. Performance (medium): Missing key in LazyColumn on line 42 causes unnecessary recomposition.
  3. Accessibility (medium): Image on line 67 needs a meaningful contentDescription.

References

  • references/api.md — deprecated APIs and their modern replacements.
  • references/composables.md — composable structure, naming, and composition patterns.
  • references/state.md — state management, ViewModel, StateFlow, and data flow.
  • references/effects.md — side effects: LaunchedEffect, DisposableEffect, SideEffect.
  • references/recomposition.md — recomposition stability, @Stable/@Immutable, derivedStateOf.
  • references/navigation.md — Navigation Compose, type-safe nav, nested graphs.
  • references/design.md — Material 3 / Expressive theming, adaptive layouts.
  • references/accessibility.md — TalkBack, semantics, content descriptions, touch targets.
  • references/performance.md — LazyList optimization, remember, scope of state reads.
  • references/kotlin.md — modern Kotlin patterns for Android.
  • references/hygiene.md — code hygiene, testing, lint.

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 Modern Jetpack Compose AI skill do?

Guides writing, reviewing, and reasoning about modern Android UI code using Jetpack Compose. Covers best practices for state management, side effects, recomposition, navigation, Material 3 design, accessibility, and performance. Use when reading, writing, or reviewing any Jetpack Compose project.

Why use Modern Jetpack Compose on TypingMind?

Because you install it once and use it with any model. Modern Jetpack 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 Modern Jetpack Compose in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/anhvt52/jetpack-compose-skills/tree/master/modern-jetpack-compose. 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 Modern Jetpack 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 Modern Jetpack Compose?

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

Is the Modern Jetpack Compose AI skill free?

Yes. It is published on GitHub by anhvt52 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 👇