Android Phone Skill logo

Android Phone Skill

Community
zeenie-ai
android-phone-skill

Use the shared local Android phone through the Android tool, with visible progress and safe manual handoff.

Overview

Publisherzeenie-ai
RepositoryOpenCompany
Skill nameandroid-phone-skill
Stars
995
Forks
151
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by zeenie-ai on GitHub. Read the source before you install it.

Installation

Install the Android Phone Skill AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/zeenie-ai/OpenCompany/tree/main/server/skills/android_agent/android-phone-skill
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/zeenie-ai/OpenCompany.git /tmp/OpenCompany
mkdir -p .claude/skills
cp -r /tmp/OpenCompany/server/skills/android_agent/android-phone-skill .claude/skills/android-phone-skill
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Android Phone Skill in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Android Phone Skill on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Android Phone Skill is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Shared Android phone

Call android with a single prompt describing one clear goal, the relevant app, and what result to verify. The tool controls the phone visible in Workspace > Mobile. It returns the result after its internal phone steps finish.

  • Use one call for a coherent task; avoid one model-driven call per tap. Each call starts a phone agent and has model latency.
  • Do not invent low-level operations or pass model, credential, timeout, or step-budget arguments. These come from the saved phone settings.
  • Global model selection is the default. An optional connected model overrides it. OpenAI, Claude and Gemini are supported; Gemini Express credentials automatically route to Vertex.
  • A phone task is one tool call in the parent agent's turn. Its internal steps appear on the Android node and in Workspace; they are not extra parent-agent turns. Do not claim completion while the tool is still running.
  • If the owner takes control, wait for them to resume the task. Ask them to enter passwords and handle interactive login themselves. Never request passwords in chat.
  • If the phone is off, direct the owner to Workspace > Mobile > Start phone. Do not install another emulator or attempt raw ADB access.
  • Read returned errors. Authentication, quota, unsupported-model, and connection failures need their stated remedy; do not repeat failed calls in a loop or treat an error payload as success.
  • Terminal source mobile shows the execution ID, provider, model backend, model wait, and device timing. Report the error and relevant phase without asking the owner to reveal API keys.

Example: {"prompt":"Open Settings, find the Android version, and report it without changing settings."}

Live Android activity

Workspace shows the active phone task's model/provider, step budget, total elapsed time, current phase duration, and time since the last reported activity. The expandable activity panel retains the latest 40 events: model requests/responses and actual device operations (screen plus accessibility-tree reads, taps, scrolling, typing, navigation, and app actions). Completed operations include duration. The last task remains visible after completion, failure, or cancellation until another task runs; history is in memory and clears on restart. A 30-second quiet period shows a notice, not a claim that the engine is stuck. Use the last phase to distinguish a model wait from device I/O; take manual control using Use phone if needed. The panel is outside the phone canvas and hidden in full-screen mode. Activity contains operational summaries, never private model reasoning, typed text, URLs, or prompt content.

Frequently asked questions

What does the Android Phone Skill AI skill do?

Use the shared local Android phone through the Android tool, with visible progress and safe manual handoff.

Why use Android Phone Skill on TypingMind?

Because you install it once and use it with any model. Android Phone Skill is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Android Phone Skill in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/zeenie-ai/OpenCompany/tree/main/server/skills/android_agent/android-phone-skill. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Android Phone Skill?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Android Phone Skill?

As many as you like. As long as a model supports skills, you can use Android Phone Skill with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Android Phone Skill AI skill free?

Yes. It is published on GitHub by zeenie-ai under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇