alpha

Lists the conventions an Android engineer follows in Jetpack Compose apps, covering state hoisting, unidirectional data flow, side effects, stable models and localisation.
# 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


Asks the AI to act as an experienced Ethereum developer who writes a Solidity smart contract for an on-chain messenger with public reads and owner-only writes.
act-as, crypto, coding

Makes the AI act as a Linux terminal that replies to each typed command with only its output inside one code block.
simulator, linux, coding

English Translator and Improver
Turns the AI into an English translator and editor that detects the input language and returns only an improved, more literary English version.
act-as, translation, rewriting, proofreading
Loading reviews…
Loading comments…