Skip to main content
prompt GP ChatGPT

Jetpack Compose Android App taste — ChatGPT prompt

The Jetpack Compose Android App taste ChatGPT prompt sets Kotlin and Compose conventions for Android app development. It covers screen architecture, UI state, testing, and builds.

CC0-1.0 ★ 178,201 updated 2026-10-24

Open on GitHub

What Jetpack Compose Android App taste does

The prompt lays out a style for Android apps built with Jetpack Compose. New screens use Compose, while Views remain for interop with legacy parts. It calls for Kotlin, coroutines, and Flow; a ViewModel exposes immutable UiState through StateFlow and receives events. Composables collect flows with collectAsStateWithLifecycle.

The guidance covers Hilt, type-safe Navigation Compose routes, and data storage: Room for local data, with Retrofit or Ktor for network access. WorkManager handles deferrable background tasks. It also sets expectations for @Preview, tests, TalkBack, localization, and ktlint or detekt checks in CI. In Claude Code, place the file at .claude/commands/prompts.csv.md.

What it helps with

  • set conventions for new Jetpack Compose screens
  • define how ViewModels pass state to the UI
  • choose patterns for navigation, tests, and localization

Example prompts for the agent

  • Create a loading screen in Jetpack Compose and follow the prompt's state and preview conventions.
  • Refactor this ViewModel to expose one UiState through StateFlow and handle events.
  • Add ViewModel tests with Turbine and kotlinx-coroutines-test.

How to install Jetpack Compose Android App taste

How to use

Paste the text at the start of a chat or into project instructions

Questions about Jetpack Compose Android App taste

How do I install Jetpack Compose Android App taste in Claude Code?

Place the prompt file at .claude/commands/prompts.csv.md.

What does Jetpack Compose Android App taste do?

It sets Kotlin and Jetpack Compose practices for Android apps, covering UI state, navigation, tests, and background work.

What UI conventions does the prompt recommend?

It recommends hoisting state from composables, collecting flows with collectAsStateWithLifecycle, and adding @Preview functions for screen states. Meaningful images and icon buttons should also expose contentDescription or semantics.

Source text

prompts.csv · CC0-1.0
# Jetpack Compose Android App taste of an Android engineer
- Build new screens entirely in Jetpack Compose and keep Views only behind interop for legacy parts. Confidence: 0.90
- Write the whole app in Kotlin with coroutines and Flow; no new RxJava or Java code. Confidence: 0.90
- Follow unidirectional data flow: the ViewModel exposes one immutable UiState as StateFlow and receives events. Confidence: 0.90
- Collect flows in composables with collectAsStateWithLifecycle, not plain collectAsState. Confidence: 0.85
- Hoist state out of composables so most UI functions are stateless and previewable. Confidence: 0.90
- Pass a Modifier parameter as the first optional argument of every reusable composable. Confidence: 0.85
- Keep side effects in LaunchedEffect, DisposableEffect or the ViewModel, never directly in the composable body. Confidence: 0.90
- Mark UI models immutable and use stable collections so recomposition stays cheap. Confidence: 0.75
- Use Hilt for dependency injection and avoid service locators or global singletons. Confidence: 0.80
- Use the repository pattern with Room for local data and Retrofit or Ktor for the network, offline first where it matters. Confidence: 0.80
- Use type-safe Navigation Compose routes instead of string-built destinations. Confidence: 0.80
- Modularize by feature with a shared core module once the app grows past a handful of screens. Confidence: 0.70
- Manage dependencies with a Gradle version catalog and convention plugins instead of copy-pasted build files. Confidence: 0.85
- Use Material 3 with a custom theme and dynamic color, and never hardcode colors or text sizes in screens. Confidence: 0.85
- Write @Preview functions for every screen state: loading, empty, error, content, dark mode and large font. Confidence: 0.80
- Test ViewModels with Turbine and kotlinx-coroutines-test, and UI with the Compose testing APIs. Confidence: 0.85
- Add contentDescription or semantics to every meaningful image and icon button for TalkBack. Confidence: 0.90
- Use WorkManager for deferrable background work and never keep long tasks alive in a ViewModel. Confidence: 0.85
- Enable R8 with tested keep rules and ship Baseline Profiles for faster startup. Confidence: 0.80
- Run ktlint or detekt and Android Lint in CI and treat new warnings as errors. Confidence: 0.75
- Keep strings in resources from day one so localization never requires a refactor. Confidence: 0.85

© f · CC0-1.0 · f/prompts.chat

Similar prompts

All prompts for Mobile →

From the same set218

The whole set →
React Native App taste The React Native App taste ChatGPT prompt sets engineering preferences for cross-platform React Native apps. Ask for a project plan or an architecture decision to get guidance on Expo, navigation, state, and testing. GP ChatGPT ★ 178,201repo stars Feature Flag Rollout taste Feature Flag Rollout taste — a prompt for ChatGPT and Claude.ai establishes release engineering standards for feature flags. Guides safe rollouts without coupling code deployments to user enablement. GP ChatGPT ★ 178,201repo stars LLM Application taste The LLM Application taste prompt for ChatGPT lays out engineering practices for applications built with language models. It covers prompt evaluation, tool use, and handling untrusted input. GP ChatGPT ★ 178,201repo stars FastAPI Service taste FastAPI Service taste — a prompt for ChatGPT and Claude.ai that enforces backend engineering standards for FastAPI. Sets architectural conventions before generating API code. GP ChatGPT ★ 178,201repo stars Data Pipeline taste Data Pipeline taste — a prompt for ChatGPT and Claude.ai establishes data engineering rules for reliable pipeline design. Guides warehouse modeling around ELT principles and strict schema separation. GP ChatGPT ★ 178,201repo stars Django Web App taste The Django Web App taste prompt for ChatGPT sets Python and Django coding preferences. It covers project structure, APIs, tests, and deployment settings. GP ChatGPT ★ 178,201repo stars Python Auto Typer with Customizable Delay The Python Auto Typer with Customizable Delay prompt creates a Python desktop application for automatic text typing with a configurable delay. It enables the development of a GUI tool that compiles into a Windows executable. GP ChatGPT ★ 178,201repo stars SwiftUI iOS App taste SwiftUI iOS App taste — a set of rules for SwiftUI work: how to build screens, where state lives and which APIs to drop. Useful when an agent writes fresh iOS code. GP ChatGPT ★ 178,201repo stars

Project sponsors

Companies that keep this analytics open