jetpack-compose-expert

jetpack-compose-expert is a skill for Claude Code from Aarvion-AI/stackwise-skills. It costs 145 tokens per session (2,500 once invoked), scanned A, original, MIT.

A guide for building and troubleshooting native Android apps with Jetpack Compose, Android’s Kotlin toolkit for declaring user interfaces in code.

In plain words
What is it for?
Use it for Compose screens, Material 3, ViewModel and StateFlow data, navigation, dependency injection with Hilt, Room databases, side effects, UI tests, insets, and performance work.
Why use it?
It helps avoid outdated Android patterns and catches state, lifecycle, recomposition, performance, and testing problems.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the stackwise plugin — 15 skills shipped together

Good fit Use it for Compose screens, Material 3, ViewModel and StateFlow data, navigation, dependency injection with Hilt, Room databases, side effects, UI tests, insets, and performance work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aarvion-ai/stackwise-skills/jetpack-compose-expert
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Aarvion-AI/stackwise-skills --skill jetpack-compose-expert
Clone the repo
git clone --depth 1 https://github.com/Aarvion-AI/stackwise-skills

Made for: Claude Code.

Or install stackwise, the plugin that ships this one along with the rest of its 15 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for jetpack-compose-expert

README.md
[![agentmods](https://agentmods.dev/badge/skills/aarvion-ai/stackwise-skills/jetpack-compose-expert.svg)](https://agentmods.dev/skills/aarvion-ai/stackwise-skills/jetpack-compose-expert)
Your own site
<a href="https://agentmods.dev/skills/aarvion-ai/stackwise-skills/jetpack-compose-expert"><img src="https://agentmods.dev/badge/skills/aarvion-ai/stackwise-skills/jetpack-compose-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 145 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,500 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00145 $0.02500
Opus 5 $0.00072 $0.01250
Sonnet 5 $0.00029 $0.00500
Haiku 4.5 $0.00015 $0.00250

Measured 8d ago against content hash 9341d6782154, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

jetpack-compose-expert scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/jetpack-compose-expert/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Jetpack Compose Expert

Turns Claude into a senior Android engineer shipping idiomatic Kotlin 2.x / Compose BOM 2026 code - unidirectional data flow, stable recomposition, lifecycle-correct state collection, and verified builds, not the 2021-era LiveData/collectAsState patterns that dominate training data.

When to Use This Skill

  • Building screens or components with Compose + Material 3 in an existing Android app
  • Fixing recomposition storms, unstable parameters, or laggy lazy lists
  • Wiring ViewModel + StateFlow state exposed to composables the lifecycle-correct way
  • Adding Navigation Compose routes (type-safe, @Serializable route classes)
  • Setting up or extending Hilt DI and Room + Flow data layers
  • Handling side effects: LaunchedEffect, DisposableEffect, rememberUpdatedState, snapshotFlow
  • Writing Compose UI tests (composeTestRule, semantics) and Robolectric-hosted tests
  • Edge-to-edge/insets work and performance passes (baseline profiles, derivedStateOf)

Core Workflow

  1. Analyze - Read gradle/libs.versions.toml and module build.gradle.kts before writing anything: confirm the Compose BOM version, that the org.jetbrains.kotlin.plugin.compose Gradle plugin is applied (required with Kotlin 2.x - composeOptions.kotlinCompilerExtensionVersion is gone), and which of Hilt/Room/Navigation/serialization are present. Skim the existing ui/ package for the project's screen/state/ViewModel conventions and match them.
  2. Implement - Write the change with unidirectional data flow: stateless composables that take state down and send events up, state hoisted to the lowest common owner, screen state in a @HiltViewModel exposing a single StateFlow<UiState> via stateIn(viewModelScope, WhileSubscribed(5_000), initial). Collect in UI only with collectAsStateWithLifecycle(). Use Material 3 components, type-safe navigation routes, and immutable UI models.
  3. Verify lint/compile - Run ./gradlew lint (plus ./gradlew :app:compileDebugKotlin if lint is configured lightly); fix all reported issues and re-run until clean before proceeding. Treat Compose lint checks (ComposableNaming, RememberReturnType, FrequentlyChangingValue, coroutine-in-composition errors) as real defects, not noise.
  4. Test - Write or update unit tests for ViewModel/state logic (coroutine runTest + Turbine for Flows) and Compose UI tests for the changed UI, then run ./gradlew test; fix all failures and re-run until clean. For instrumented UI tests, run ./gradlew connectedAndroidTest on a device/emulator; fix all reported issues and re-run until clean.
  5. Prove it works - Install and launch the app (./gradlew installDebug, then start via adb shell am start), exercise the changed flow, and watch adb logcat for crashes and Choreographer/StrictMode warnings. For performance work, confirm with Layout Inspector recomposition counts or a Macrobenchmark that recompositions/frame times actually dropped.

Read the full file on GitHub · 121 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 121 lines · 145 tokens per session scan A 9341d6782154

Subscribe to this mod's changes

jetpack-compose-expert is a skill published in the GitHub repository Aarvion-AI/stackwise-skills (5 stars, last pushed 5d ago), licensed MIT. It adds 145 tokens to every session and 2,500 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

swift-patterns

Swift and SwiftUI development patterns for building native iOS/iPadOS applications. Use when implementing views, view models, data persistence, networking, concurrency, and navigation. Covers Swift 6.2, SwiftUI, SwiftData, iOS 26 features including Liquid Glass and Foundation Models.

shahtuyakov/claude-setup · 63 tokens

build-android-binary

Compile a PAM control's Android Kotlin module into the runtime-loadable DEX for a .ppmplugin. Creates a staged Gradle build with the pinned wrapper and react-android compile dependency, verifies manifest/module/package alignment and runtime-loading constraints, builds the release AAR, then runs d8 --min-api 24. Writes…

microsoft/power-platform-skills · 150 tokens

kotlin-patterns

Kotlin: coroutines, Flow, sealed/data classes, null safety, Ktor, Compose, KMP. Triggers: Kotlin, coroutine, Flow, suspend, Ktor, Jetpack Compose, KMP, kotlinx.

softspark/ai-toolkit · 51 tokens

swift-patterns

Swift/iOS: SwiftUI, Combine, async/await, actors, SPM, Core Data, UIKit interop. Triggers: Swift, SwiftUI, Combine, iOS, Xcode, actor, Core Data, @MainActor, @State.

softspark/ai-toolkit · 57 tokens

generators

Code generator skills that produce production-ready Swift code for common app components. Use when user wants to add logging, analytics, onboarding, review prompts, networking, authentication, paywalls, settings, persistence, error monitoring, CI/CD pipelines, localization, push notifications, deep linking, testing…

rshankras/claude-code-apple-skills · 176 tokens

android-development

Android development with Kotlin, Jetpack Compose, and modern Android architecture. Use when building Android apps, implementing Material Design, or following Android best practices.

travisjneuman/.claude · 33 tokens