Skip to content

aldefy/compose-skill / skills/compose-expert

compose-expert

Unverified

Compose and Compose Multiplatform expert for UI development across Android, Desktop, iOS, and Web. Use whenever the user mentions Compose APIs (@Composable, remember, LaunchedEffect, NavHost, MaterialTheme, LazyColumn, Modifier, recomposition), Compose Multiplatform (commonMain, expect/actual, Res.*, ComposeUIViewController, UIKitView, ComposeViewport), Android TV (tv-material, D-pad, focus, Carousel), Material 3 motion, atomic design systems, design-to-code workflows, Paging 3, or navigation. Activates Review Mode on GitHub PR URLs and review phrases ("review this PR", "what's wrong with this"). Auto-detects Compose projects on session_start. Backed by actual androidx/androidx and JetBrains/compose-multiplatform-core source receipts. See "## When this skill applies" in SKILL.md for the full trigger surface.

FileKindSize
SKILL.mdskill md24.8 KB
agents/openai.yamlconfig278 B
references/accessibility.mdmarkdown11.2 KB
references/adaptive-layout-input.mdmarkdown5.2 KB
references/agentic-ui-a2ui.mdmarkdown4.7 KB
references/agsl-shaders.mdmarkdown11.5 KB
references/animation.mdmarkdown41.7 KB
references/appfunctions.mdmarkdown5.8 KB
references/appstate.mdmarkdown3.9 KB
references/atomic-design.mdmarkdown10.7 KB
references/auto-init.mdmarkdown1.6 KB
references/car-compose.mdmarkdown6.7 KB
references/composition-locals.mdmarkdown6.9 KB
references/deprecated-patterns.mdmarkdown8.3 KB
references/design-to-compose.mdmarkdown23.5 KB
references/graphics-modern.mdmarkdown2.6 KB
references/ink.mdmarkdown5.1 KB
references/lists-scrolling.mdmarkdown14.5 KB
references/material3-motion.mdmarkdown14.9 KB
references/media3-compose.mdmarkdown1.7 KB
references/ml-kit-agentic.mdmarkdown5.5 KB
references/modifiers.mdmarkdown13.6 KB
references/multiplatform.mdmarkdown21.1 KB
references/navigation-migration.mdmarkdown14.6 KB
references/navigation.mdmarkdown11.0 KB
references/official-android-skills.mdmarkdown2.7 KB
references/paging-mvi-testing.mdmarkdown6.4 KB
references/paging-offline.mdmarkdown6.4 KB
references/paging.mdmarkdown11.1 KB
references/performance.mdmarkdown22.7 KB
references/platform-specifics.mdmarkdown20.2 KB
references/pr-review.mdmarkdown14.1 KB
references/production-crash-playbook.mdmarkdown25.3 KB
references/remote-compose.mdmarkdown3.7 KB
references/side-effects.mdmarkdown13.0 KB
references/source-code/cmp-source.mdmarkdown17.8 KB
references/source-code/foundation-source.mdmarkdown560.9 KB
references/source-code/material3-source.mdmarkdown836.1 KB
references/source-code/navigation-source.mdmarkdown118.8 KB
references/source-code/runtime-source.mdmarkdown449.0 KB
references/source-code/ui-source.mdmarkdown313.1 KB
references/state-management.mdmarkdown17.6 KB
references/styles-experimental.mdmarkdown14.5 KB
references/text-editing.mdmarkdown3.8 KB
references/theming-material3.mdmarkdown13.0 KB
references/tv-compose.mdmarkdown30.2 KB
references/view-composition.mdmarkdown20.0 KB
references/wear-compose.mdmarkdown2.0 KB
references/xr-compose.mdmarkdown5.1 KB

references/ml-kit-agentic.md

View on GitHub
# ML Kit Agentic Workflows

> ML Kit Agentic API is alpha. It uses Gemini Nano through Android AICore;
> APIs, model availability, and device support can change. Keep network and
> consequential side effects under app control.

ML Kit's Android Agentic API orchestrates focused, multi-step, on-device
workflows. `AgentRunner` manages the loop over `GenerativeModel`: it observes
context, chooses typed tools, receives results, and continues until completion
or a turn limit. Use it for local commands, lookup, filtering, curation, and
validated data entry — not for an unconstrained general-purpose cloud agent.

## Dependency and runtime

```kotlin
dependencies {
    implementation("com.google.mlkit:genai-agent:<latest-alpha>")
}
```

The runtime uses Gemini Nano through Android's AICore service. Availability is
device- and rollout-dependent; treat model readiness as a runtime capability,
not a build-time guarantee. Keep a deterministic non-agent fallback for devices
without the required model or service.

## Choose the orchestration level

| Need | API |
|---|---|
| Automatic tool dispatch, managed history, multi-step loop | `AgentRunner` / `AgentSession` |
| Custom prompts, typed generation, app-managed history/tools | `GenerativeModel` |
| Stateless writing, vision, or rewriting | Task-specific ML Kit GenAI APIs |

`AgentSession` keeps in-memory conversation state across turns. Bound execution
with `maxTurns` (default 10) to limit runaway loops, battery use, and latency.
Release sessions with `session.close()`, `deleteSession(sessionId)`, or
`clearAllSessions()` when the owning workflow ends.

## Tools and AppFunctions

The agent can discover registered Android AppFunctions and select them as typed
tools. Keep tools narrow:

- one clear responsibility;
- explicit parameter and result types;
- short, concrete descriptions;
- validation before every mutation;
- no hidden network or payment side effects.

```text
user intent
    ▼
AgentSession / AgentRunner
    ├── Gemini Nano reasoning
    ├── typed AppFunction call
    ├── validated result
    └── next step or final response
```

See `appfunctions.md` for declarations, KDoc contracts, permission boundaries,
and typed failure exceptions. AppFunctions may still call network services, so
"on-device agent" does not mean every side effect is local or offline.

## Compose integration

The official overview does not publish imports or constructor signatures; follow
the ML Kit Get started guide for setup and treat the sketch below as structure,
not compilable code (`AssistantUiState`, `Idle`, `Running`, `Completed`, `Failed`,
and `runAgent` are app-defined).

Keep the agent session outside composition — typically in a ViewModel or a
state holder. Expose immutable progress, tool status, errors, and final data to
Compose through `StateFlow` or AppState `StateStore`; render loading, waiting for
confirmation, success, and failure explicitly.

```kotlin
class AssistantViewModel : ViewModel() {
    private val _uiState = MutableStateFlow<AssistantUiState>(Idle)
    val uiState: StateFlow<AssistantUiState> = _uiState.asStateFlow()

    suspend fun run(request: String) {
        _uiState.value = Running
        try {
            // Create/use AgentSession outside composition; collect events here.
            _uiState.value = Completed(runAgent(request))
        } catch (cancelled: CancellationException) {
            throw cancelled
        } catch (error: Exception) {
            _uiState.value = Failed(error)
        }
    }
}
```

Do not start an agent loop directly in a composable body. If composition owns
the lifetime, use `LaunchedEffect` with stable keys and close the session in the
corresponding lifecycle owner. Never let a recomposition accidentally create a
second session.

## Safety and product boundaries

- Require explicit confirmation before deletion, purchase, sharing,
authentication, messages, or other consequential actions.
- Show which tool/action is running when the workflow can surprise the user.
- Cap turns, input size, output size, tool latency, and total execution time.
- Keep prompts and local context on-device where possible; audit tools that
  access network data.
- Treat model output and tool arguments as untrusted input. Validate IDs,
  permissions, URLs, and amounts in app code.
- Cancel on screen/account scope loss and release sessions on logout.
- Design an offline/non-agent fallback for unsupported devices and model errors.

## Testing

- Unit-test tool implementations independently from model behavior.
- Test unavailable AICore/model, denied permission, malformed arguments,
  cancellation, max-turn termination, timeout, and typed tool failures.
- Run repeated workflows to detect nondeterministic state or duplicate side
  effects; make mutations idempotent where possible.
- Verify session cleanup and process-death recovery.
- Inspect AppFunction registration (see `appfunctions.md`) before testing agent
  selection; a tool that is not registered cannot be chosen.
- Test on physical devices with AICore and Gemini Nano available; emulators may
  not provide the model.

## Sources

- ML Kit Android agentic workflows: https://developers.google.com/ml-kit/genai/agent/android
- ML Kit GenAI overview: https://developers.google.com/ml-kit/genai
- AppFunctions: https://developer.android.com/ai/appfunctions
- Android AICore: https://developer.android.com/ai/aicore
- Android Dev Summit agentic announcement: https://developer.android.com/blog/posts/build-it-your-way-a-next-era-of-android-development
brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).Stars: 322kUpdated Claude CodeCodexVerifiedInstall
brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).Stars: 198kUpdated Claude CodeCodexVerifiedInstall