> Jetpack Compose and Compose Multiplatform (KMP/CMP) architecture skill. Only use when the user explicitly mentions "compose-skill", "@compose-skill", or "use compose skill" in their message. Do NOT auto-activate based on keyword matching — this skill should only be triggered by direct user request.
npx skills add https://github.com/Meet-Miyani/compose-skill --skill compose-skill
This skill covers the full Compose app development lifecycle — from architecture and state management through UI, networking, persistence, performance, accessibility, cross-platform sharing, build configuration, and distribution. Jetpack Compose and Compose Multiplatform share the same core APIs and mental model. Not all Jetpack libraries work in commonMain — many remain Android-only. A subset of AndroidX libraries now publish multiplatform artifacts (e.g., lifecycle-viewmodel, lifecycle-runtime-compose, datastore-preferences), but availability and API surface vary by version. Before adding any Jetpack/AndroidX dependency to commonMain, verify the artifact is published for all required targets by checking Maven Central or the library's official documentation. CMP uses expect/actual or interfaces for platform-specific code. MVI (Model-View-Intent) is the recommended architecture, but the skill adapts to existing project conventions.
Do not force migration. If a project already follows MVI with its own conventions (different base class, different naming, different file layout), respect that. Adapt to the project's existing patterns. The architecture pattern — unidirectional data flow with Event, State, and Effect — is what matters, not a specific base class or framework. Only suggest structural changes when the user asks for them or when the existing code has clear architectural violations (business logic in composables, scattered state mutations, etc.).
When helping with Jetpack Compose or Compose Multiplatform code, follow this process:
references/ only when deeper guidance is needed. Use the Quick Routing in the Detailed References section to pick the right file.Before recommending any new dependency or version upgrade, verify:
group:artifact:version) exist and are current.commonMain). Do not assume a Jetpack library works in commonMain unless verified.How to verify:
If verification is not possible (no documentation tool, no network access, docs unavailable), provide the standard or latest known dependency snippet anyway. Add a brief comment (e.g., // Verify latest version) so the user isn't blocked.
When adding a new dependency, upgrading major versions, or verifying latest API patterns, use a documentation MCP tool (e.g., Context7) if available. Before invoking, verify the tool's exact name and parameter schema — tool names vary across environments.
Alternative: Users can add use context7 (or equivalent) to their prompt. Bundled references remain the primary source for architectural patterns and MVI guidance; use documentation tools for API-specific and version-specific queries.
Both MVI and MVVM use unidirectional data flow: UI renders state → user acts → ViewModel updates state → UI re-renders. The difference is how UI actions reach the ViewModel.
sealed interface Event + single onEvent() entry pointonTitleChanged(), save())Both patterns use:
StateFlowChannelDefault recommendation: Preserve the project's existing pattern when it is coherent. For new projects, choose based on team preference and screen complexity. See Architecture & State Management for the decision guide, then mvi.md or mvvm.md for implementation details.
These boundaries apply to both MVI and MVVM:
collectAsStateWithLifecycle(), collects effects via CollectEffect (see compose-essentials.md), binds navigation/snackbar/platform APIsonEvent, MVVM: individual callbacks), renders the screen, adapts callbacks for leaf composablesonEvent() as the single entry point; MVVM: implement named functions for user actionsFor calculator/form screens, split state into four buckets:
| Concern | Where | Example |
|---|---|---|
| Raw field text | state fields | "12", "12.", "" |
| Parsed/derived | state computed props or fields | val hasRequiredFields: Boolean |
| Validation | state.validationErrors or similar | mapOf("name" to "Required") |
| Loading/refresh | state flags | isSaving = true |
| One-off UI commands | Effect via Channel | snackbar, navigate, share |
| Scroll/focus/animation | local Compose state | LazyListState, focus requester |
Apply these unless the project already follows a different coherent pattern.
| Concern | Default |
|---|---|
| ViewModel | One ViewModel per screen (commonMain for CMP, feature package for Android-only). MVI: onEvent(Event) entry point; MVVM: named functions |
| State source of truth | StateFlow<FeatureState> owned by the ViewModel |
| Event handling | MVI: onEvent(event) with when expression; MVVM: named functions. Both map user actions to state updates, effect emissions, and async launches |
| Side effects | Effect sent via Channel<Effect>(Channel.BUFFERED) for UI-consumed one-shots (navigate, snackbar). Async work (network, persistence) launched in viewModelScope |
| Async loading | Keep previous content, flip loading flag, cancel outdated jobs, update state on completion |
| Dumb UI contract | Render props, emit explicit callbacks, keep only ephemeral visual state local |
| Resource access | Semantic keys/enums in state; resolve strings/icons close to UI. CMP uses Res.string / Res.drawable (not Android R). See Resources |
| Platform separation | CMP: share in commonMain, expect/actual (verify Kotlin 1.9 vs 2.0+ via build.gradle.kts or ask user) or interfaces, Koin DI by default. Android-only: standard package, Hilt or Koin DI |
| Navigation | ViewModel emits semantic navigation effect; route/navigation layer executes it |
| Persistence (settings) | DataStore Preferences in commonMain for key-value settings; Typed DataStore (JSON) for structured settings objects; Room for relational/queried data. See DataStore |
| Testing | ViewModel event→state→effect tests via Turbine in commonTest; validators/calculators tested as pure functions; platform bindings tested per target |
import ... as ... aliases to resolve name clashesMutableState, controllers, lambdas, or platform objects in screen statecom.example.pkg.SomeClass.method()) — always import at file topDo not load reference files for basic Compose usage. If you already know how to build the required UI or logic, write the code immediately. Load exactly one reference file only when the task involves advanced concepts (e.g., Paging 3, Nav 3 setup). Pick the right file below — do not load files speculatively.
@Resource routes or type-safe API definitions → networking-ktor.md § Type-Safe ResourcesRun ./scripts/validate.sh to scan the skill package against the agentskills.io spec. It checks token budgets, broken links, file structure, and content quality. Fix any errors before committing.
Comprehensive web quality audit covering performance, accessibility, SEO, and best practices in a single review. Use when asked to "audit my site", "review web quality", "run lighthouse audit", "check page quality", or "optimize my website" across multiple areas at once. Orchestrates specialized skills for depth. Do NOT use for single-area audits — prefer core-web-vitals, web-accessibility, seo, or web-best-practices for focused work.
| Use when launching a new product end-to-end from market research through post-launch monitoring. Orchestrates 15+ specialist agents across 5 phases in a 10-week coordinated workflow including research, development, marketing, sales preparation, launch execution, and ongoing optimization. Employs hierarchical coordination with parallel execution for efficiency and comprehensive coverage.
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting session data.
| Create visually strong landing pages, websites, and app UIs with restrained composition. OpenAI's production frontend playbook.
Pre-build product and feature risk review for founders, product managers, and AI-assisted builders. Use this skill when the user is about to build a landing page, MVP, SaaS product, internal tool, agent workflow, or major feature and needs to check demand, positioning, monetization, retention, trust, distribution, and adoption risk before implementation starts.
This skill helps users extract structured best-selling product data from Amazon via the BrowserAct API. Agent should proactively apply this skill when users express needs like search for best selling products on Amazon, extract Amazon product data based on keywords, find top rated Amazon products, monitor Amazon competitor prices and sales, discover trending products on Amazon marketplace, extract Amazon product titles prices and ratings, gather Amazon product sales volume for market research, search Amazon best sellers in specific region, collect Amazon product reviews and promotion details, analyze Amazon product availability and badges, get Amazon product data for market analysis.
This skill is designed to help users automatically extract product data from Amazon search results. The Agent should proactively apply this skill when users request searching for products related to keywords, finding best-selling items from specific brands, monitoring product prices and availability on Amazon, extracting product listings for market research, collecting product ratings and review counts for competitive analysis, finding specific products with a maximum count, searching Amazon in different languages for localized results, tracking monthly sales estimates for brand products, gathering product URLs and titles for a product catalog, scanning Amazon for Best Seller tags in a specific category, monitoring shipping and delivery information for brand items, building a structured dataset of Amazon search results.
This skill is designed to help users automatically extract reviews from Google Maps via the Google Maps Reviews API. Agent should proactively apply this skill when users request to find reviews for local businesses (e.g., coffee shops, clinics), monitor customer feedback for a specific brand or location, analyze sentiment of reviews for competitors, extract reviews for a chain of stores or services, track reputation of a local restaurant, gather user testimonials for a specific venue, conduct market research on service quality of local businesses, monitor reviews for a new retail location, collect feedback on public attractions or parks, identify common complaints for a specific service provider, research the best-rated places in a city, analyze recurring themes in reviews for a specific industry.
Take meet-miyani/compose-skill from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.