Control

OrganizationPopular

Core-Mate

control

Automatically control locally connected Android phones with OpenGUI screenshots and allowlisted actions whenever a request targets a phone, Android app, mobile game, or multiple devices. The user does not need to name OpenGUI. Use the native Codex Browser instead for browser-only work.

Overview

Publisher	Core-Mate
Repository	`OpenGUI`
Skill name	`control`
Stars	1.8K
Forks	111
Bundled files	1
Links	Skill source Repository Homepage

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.
1 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by Core-Mate on GitHub. Read the source before you install it.

Installation

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
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.

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/Core-Mate/OpenGUI.git /tmp/OpenGUI
mkdir -p .claude/skills
cp -r /tmp/OpenGUI/deepseek-harness-plugin/skills/control .claude/skills/control

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Control 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 Control 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 Control 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.

OpenGUI Control

Use the OpenGUI MCP tools when they are available. In a public Skills-only installation, resolve the plugin root as two directories above this file and invoke node <plugin-root>/lib/codex-cli.js <interface> '<json>' instead. The CLI returns screenshot files under its private state directory; inspect those files with the available image viewer. Never bypass this adapter with raw adb shell commands.

Route the task

Route by intent, not invocation syntax. Ordinary requests such as opening an app, testing a phone UI, or claiming a game reward activate this Skill without $control, OpenGUI, or a special command.
Treat an explicit Android phone, mobile app, or mobile game target as an OpenGUI task.
If OpenGUI is unavailable, report its device, session, or adapter error. Do not silently fall back to Bash, shell, raw ADB, or another phone-control path.
Use the native Codex Browser for a website, URL, web app, or browser-only target.
Split a mixed phone-and-browser request into the smallest necessary phone actions and native Browser work.

Phone loop

Call opengui_list_devices. Explain USB authorization or connection errors rather than guessing.
Call opengui_open_session with one to four selected device ids. Omit ids only when exactly one authorized phone is connected.
Call opengui_observe before the first mutation. Treat the returned screenshot pixels as the only valid coordinate space.
Perform exactly one opengui_act at a time with the newest observationId, then inspect the returned observation. Use tight target bounds for taps. Use wait only for visible loading.
Open the returned deviceWallUrl in the native Codex Browser when the user asks to monitor devices or when a multi-device wall helps.
Always call opengui_close_session after success. Call opengui_cancel immediately when the user asks to stop or when continuing would be unsafe.

For a multi-device session, pass deviceId on every observation and action. Devices are frozen for the session; never substitute a newly connected phone after a disconnect. Stop on stale-observation, repeated-no-progress, operation-limit, authorization, or disconnection errors.

External side effects

Before the action that sends a message, publishes content, purchases anything, or deletes data, show the user the current target and intended effect and ask for immediate confirmation. Set externalSideEffect to send, publish, purchase, or delete on that action. The MCP transport performs a second local confirmation. For the Skills-only CLI fallback, set confirmedExternalSideEffect: true only after the user explicitly confirms in the current conversation. Never infer confirmation from the original task wording when the final target or content was not yet visible.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

agents/openai.yaml1 KB

Frequently asked questions

What does the Control AI skill do?

Why use Control on TypingMind?

Because you install it once and use it with any model. Control 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 Control in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Core-Mate/OpenGUI/tree/main/deepseek-harness-plugin/skills/control. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Control?

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 Control?

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

Is the Control AI skill free?

It is published on GitHub by Core-Mate. Check the repository for licensing terms. 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

Add App Clip

sickn33

CommunityPopular

Add an iOS App Clip target to an Expo app. Use when the user mentions App Clip, AASA, apple-app-site-association, appclips, smart app banner, or wants to ship a lightweight iOS Clip invoked from a URL…

Advogado Criminal

Advogado criminalista especializado em Maria da Penha, violencia domestica, feminicidio, direito penal brasileiro, medidas protetivas, inquerito policial e acao penal.

Advogado Especialista

sickn33

CommunityPopular

Advogado especialista em todas as areas do Direito brasileiro: familia, criminal, trabalhista, tributario, consumidor, imobiliario, empresarial, civil e constitucional.

Cqrs Implementation

Implement Command Query Responsibility Segregation for scalable architectures. Use when separating read and write models, optimizing query performance, or building event-sourced systems.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

OpenGUI Control

Route the task

Phone loop

External side effects

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now