What problem does it solve? Android developers need to expose app features to system AI agents without forcing users to open the app UI, but implementing AppFunctions correctly requires coordinating Gradle/KSP setup, metadata XML, Kotlin annotations, KDoc optimization, and ADB testing across many steps. ## Core Features & Use Cases - Feature Discovery: Analyzes Android codebases (manifests, activities, services) to identify and recommend high-value AppFunctions with rationale for AI agent use. - Implementation & Configuration: Generates Kotlin code with correct @AppFunction annotations, KSP setup, app_metadata.xml, and optional Hilt dependency injection. - KDoc Refinement: Optimizes function and serializable documentation so LLM agents correctly understand workflows, parameters, and error recovery. - ADB Testing: Provides commands to list, invoke, enable, and disable AppFunctions on a connected device for verification. - Use Case: A notes app developer asks to expose note creation to the system assistant; the skill discovers candidate functions, generates the Kotlin implementation, refines the KDoc, and verifies registration via ADB. ## Quick Start Analyze my Android app and implement AppFunctions so system AI agents can create notes without opening the app UI.