Appfunctions

by android42dc2270e960Complete terms in LICENSE.txt7.7K starsListed Oct 8, 2026Updated Oct 8, 2026Repository updated 13 days ago

Analyzes Android apps to identify key user workflows for AppFunctions such as creating a note, playing media, or sending an automated or AI agent triggered message, voice commands, or system shortcuts, without needing to open the app UI. Generates Kotlin code to expose these workflows to the Android system, allowing agents to discover and execute them on-device. Also refines KDoc documentation to ensure AI agents correctly understand and use the provided functionality.

AI-generated overview

Guides Android developers through discovering, implementing, documenting and testing AppFunctions that expose app workflows to on-device AI agents.

What it does
This skill walks through a four-step AppFunctions development flow for Android apps: discovering candidate user workflows, generating Kotlin implementations with build and system configuration, refining KDoc so AI agents and MCP clients understand the functions, and testing or debugging them with ADB commands. It also covers architecture terminology and migrating legacy AppFunctionConfiguration.Provider code to the AppFunctionServiceEntryPoint architecture. It produces Kotlin code, configuration guidance, refined KDoc, and ADB test commands.
When to use it
Use it when working on an Android app that targets Android 16 or later and you want to expose app features such as creating a note or playing media to system agents without opening the UI. It fits requests to discover AppFunctions, implement or configure the framework, optimize tool descriptions for LLMs or MCP, or verify function registration on a device. It also applies when upgrading existing AppFunctions code from versions 1.0.0-alpha09 and lower.
Requirements
The target Android app must use targetSdk 36 or newer and compileSdk 37 or newer, and should use the Jetpack AppFunctions library for backward compatibility. Testing steps require ADB access to a device. The skill is instructions only and ships no scripts; it relies on bundled reference documents.

Analyzes Android apps to identify key user workflows for AppFunctions such as creating a note, playing media, or sending an automated or AI agent triggered message, voice commands, or system shortcuts, without needing to open the app UI.

Generates Kotlin code to expose these workflows to the Android system, allowing agents to discover and execute them on-device.

Also refines KDoc documentation to ensure AI agents correctly understand and use the provided functionality.

Prerequisites

The app must targetSdk 36 or newer and use compileSdk 37 or newer as AppFunctions, part of the Android platform API, are available from Android 16 onwards. Always use the Jetpack library because it handles backward compatibility.

Workflows

This skill enables the caller to discover features that will be provided to system agents, implement these with AppFunctions, improve function description for agents, and use ADB commands for local evaluation and testing.

The full AppFunction development flow consists of these four steps:

  • Step 1: Discovery [blocked]: Analyze Android codebases to identify and recommend potential AppFunctions. Use this step when a user asks to "discover AppFunctions," "find features for AI," or "analyze my app for agentic tools."
  • Step 2: Implementation and configuration [blocked]: Generate Kotlin implementations of AppFunctions, manage system-wide configuration, and configure build dependencies. Use this step when a user asks to "implement AppFunctions," "set up the AppFunctions framework," or "configure Hilt for AppFunctions."
  • Step 3: KDoc refinement [blocked]: Optimize AppFunction KDoc for AI agents and Model Context Protocol. If a user asks to "write KDoc", "optimize for MCP", or "refactor tool descriptions for LLMs", use this step.
  • Step 4: Testing and debugging [blocked]: Provide commands to interact with AppFunctions using ADB for testing and debugging. If a user wants to "list app functions", "invoke an app function", or "verify app function registration" on a device, use this step.

If users request a subset of steps, you must encourage them to use all steps.

If they apply, you must load the following references:

  • Context and terminology [blocked]: Defines the ubiquitous language, architecture definitions, and design patterns across the AppFunctions skill suite. Load when you need to understand core architecture terminology or check the distinctions between modern and legacy AppFunctions APIs.
  • Migration to service entry point [blocked] : Documents the systematic procedure for migrating Android applications using AppFunctions versions 1.0.0-alpha09 and lower to AppFunctionServiceEntryPoint architecture introduced in version 1.0.0-alpha10. Load when a user asks to migrate or upgrade existing AppFunctions code, or when you encounter legacy AppFunctionConfiguration.Provider implementations.

Critical constraints

  • Modular consistency: You must refine KDocs immediately after you generate AppFunction implementations.
  • Security: Don't expose sensitive data or run destructive actions without user confirmation.

Troubleshooting

  • If you encounter build-time errors such as Kotlin Symbol Processing (KSP) issues, see Implementation and configuration [blocked].
  • If you encounter runtime errors such as missing services or execution failures, see Testing and debugging [blocked].
  • If you need architecture definitions and vocabulary, see Context and terminology [blocked].
  • If you encounter issues when upgrading legacy configurations, see Migration to service entry point [blocked].

Source and attribution

Source:android/skillsindevice-ai/appfunctionsat commit42dc227

License: Complete terms in LICENSE.txt

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal

More from android/skills

Wear Compose M3

android

Guides building, updating and migrating Wear OS Compose Material3 apps, with canonical component samples and version rules.

Software Development7.7Kupdated 13 days ago

Display Glasses With Jetpack Compose Glimmer

android

Provides guidelines for developing projected Android XR apps for display glasses using the Jetpack Compose Glimmer UI toolkit. This skill covers foundational Glimmer design principles, workflows for implementing Jetpack Compose Glimmer, and interaction models for the glasses form factor. Use this skill to build an Android XR Augmented Experience app with Jetpack Compose Glimmer that adheres to the Glimmer design system for optimized glasses styling.

Awaiting classification7.7Kupdated 13 days ago

Play Billing Library Version Upgrade

android

Guides upgrading an Android project from a legacy Google Play Billing Library version to the latest stable release.

Software Development7.7Kupdated 13 days ago

Leanback To Compose Tv Migration

android

Provides instructions and architectural patterns for migrating Android TV applications from legacy Leanback UI Toolkit, Android Views, or Support Fragments to Jetpack Compose for TV (androidx.tv). Use this skill for Leanback to Compose migrations, including browse screen, settings screen, authentication screen, login screen, or video playback screen migrations, or when replacing BrowseSupportFragment, LeanbackSettingsFragment, PreferenceFragment, BaseLeanbackPreferenceFragmentCompat, VideoSupportFragment, GuidedStepSupportFragment, SearchSupportFragment, VerticalGridSupportFragment, Presenter, ArrayObjectAdapter, or CursorMapper with modern Compose equivalents, implementing immersive carousels with focus memory, Media3 video playback with PlayerSurface, or custom 10-foot hero layouts.

Awaiting classification7.7Kupdated 13 days ago

Testing Setup

android

Analyzes an Android project's testing setup and installs testing frameworks, harnesses and tests for unit, UI, screenshot and end-to-end coverage.

Software Development7.7Kupdated 13 days ago

Android Profiler

android

Guides Android performance profiling: recording system traces, heap dumps and method recordings, and analyzing them with Perfetto SQL.

Software Development7.7Kupdated 13 days ago