How do I install the Appfunctions skill?

Run npx skillmds add thedixitjain/appfunctions in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Appfunctions safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Appfunctions?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Appfunctions free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Appfunctions?

thedixitjain (@thedixitjain) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Appfunctions by thedixitjain — Agent Skill

Name: Appfunctions
Rating: 4.666666666666667 (3 reviews)
Author: thedixitjain

Appfunctions

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.

thedixitjain f05d2fd 5 files · 18.9 KB Updated Sep 9, 2026 2 repo stars

File contents

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, as it handles backwards 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: Analyzes Android codebases to identify and recommend high-value AppFunctions. Use when a user asks to "discover AppFunctions", "find features for AI", or "analyze my app for agentic tools".
Step 2: Implementation & Configuration: Specialized for generating Kotlin implementations of AppFunctions, handling system-wide configuration, and managing build dependencies. Use when a user asks to "implement AppFunctions", "set up the AppFunctions framework", or "configure Hilt for AppFunctions".
Step 3: KDoc Refinement: Optimizes AppFunction KDoc for AI agents and Model Context Protocol. Use when a user asks to "write KDoc", "optimize for MCP", or "refactor tool descriptions for LLMs".
Step 4: Testing & Debugging: Provides commands to interact with AppFunctions using ADB for testing and debugging. Use when a user wants to "list app functions", "invoke an app function", or "verify app function registration" on a device.

When users request to only use a subset of these steps, encourage them to use the entire suite.

Critical Constraints

Modular Consistency : Always ensure that implementations generated using Implementation & Configuration are immediately followed by KDoc refinement using KDoc Refinement to ensure maximum agent compatibility.
Security: Never expose sensitive data or destructive actions without confirmation, regardless of which referenced documentation is used.

Troubleshooting

For build-time errors (KSP, Metadata), refer to Implementation & Configuration.
For runtime errors (Service not found, Execution failed), refer to Testing & Debugging.

Source: android/skills → device-ai/appfunctions/SKILL.md

---name: appfunctionsdescription: 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.--- 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, as it handles backwards 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](references/feature-discovery-analysis.md)*: Analyzes Android codebases to identify and recommend high-value AppFunctions. Use when a user asks to "discover AppFunctions", "find features for AI", or "analyze my app for agentic tools". - *[Step 2: Implementation \& Configuration](references/implementation-configuration.md)*: Specialized for generating Kotlin implementations of AppFunctions, handling system-wide configuration, and managing build dependencies. Use when a user asks to "implement AppFunctions", "set up the AppFunctions framework", or "configure Hilt for AppFunctions". - *[Step 3: KDoc Refinement](references/kdoc-refinement-optimization.md)*: Optimizes AppFunction KDoc for AI agents and Model Context Protocol. Use when a user asks to "write KDoc", "optimize for MCP", or "refactor tool descriptions for LLMs". - *[Step 4: Testing \& Debugging](references/adb-interaction-testing.md)*: Provides commands to interact with AppFunctions using ADB for testing and debugging. Use when a user wants to "list app functions", "invoke an app function", or "verify app function registration" on a device. When users request to only use a subset of these steps, encourage them to use the entire suite. ## Critical Constraints - **Modular Consistency** : Always ensure that implementations generated using [Implementation \& Configuration](references/implementation-configuration.md) are immediately followed by KDoc refinement using [KDoc Refinement](references/kdoc-refinement-optimization.md) to ensure maximum agent compatibility. - **Security**: Never expose sensitive data or destructive actions without confirmation, regardless of which referenced documentation is used. ## Troubleshooting - For build-time errors (KSP, Metadata), refer to [Implementation \& Configuration](references/implementation-configuration.md). - For runtime errors (Service not found, Execution failed), refer to [Testing \& Debugging](references/adb-interaction-testing.md). --- **Source:** [`android/skills`](https://github.com/android/skills) → `device-ai/appfunctions/SKILL.md`

Frequently asked questions