Agent skill

Phone And Simulator GUI Control

by Core-Mate in Core-Mate/OpenGUI

Completes an already-authorized task on a real Android phone or a macOS iOS simulator one screenshot-driven action at a time.

Custom licenceAuto-check passedProductivity & Automation

Install Phone And Simulator GUI Control

skills CLI
$ npx skills add Core-Mate/OpenGUI --skill opengui -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Core-Mate/OpenGUI opengui --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Core-Mate/OpenGUI.git skills-src && mkdir -p .claude/skills && cp -r skills-src/workbuddy-plugin/connector/skills/control .claude/skills/opengui && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
opengui
GitHub stars
1.8k
Token cost
~7.2k tokens
SKILL.md length
3,993 words
Files
2
Skills in repo
7
Repo updated
First seen
Licence
Custom licence

At a glance

Completes an already-authorized task on a real Android phone or a macOS iOS simulator one screenshot-driven action at a time.

  • Works in 6 steps: Do not execute a new task immediately.… → Use WorkBuddy's BUILT-IN present_files… → Call opengui_viewer_status with viewerId… → …
  • Running a specific, already-authorized action on a connected Android phone
  • SKILL.md covers Unified account, models and…, Task entry and scenario guidance and Structured tests and retests
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

This skill drives a connected Android device or a supported macOS iOS simulator by reading real screenshots and issuing one action at a time, rather than guessing what a screen looks like. Every tap or swipe carries a declared side effect — none for plain navigation, or a specific marker for a final mutation — and the runtime blocks anything marked as a submit, send, publish, purchase, or delete action until that marker is explicitly set.

A bare or first-time invocation opens a home guide instead of acting right away, so login, model selection, and device or simulator connection happen before any task runs. The skill will not enter passwords or verification codes itself, leaving those to the person at the device, and it checks progress only through the phone screenshots it is given, not by inspecting a workbench page through a browser.

When your agent uses it

  • Running a specific, already-authorized action on a connected Android phone
  • Testing an app flow on a macOS iOS or Android simulator
  • Walking through a multi-step phone task that needs screenshot confirmation at each step

Example prompts

  • “Open phone settings, then return to the home screen and confirm you're there.”
  • “Test the checkout flow in the shopping app on the Android simulator.”
  • “Check my notification settings and report what's currently enabled.”

Requirements

  • A connected Android device or a supported macOS iOS simulator

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Do not execute a new task immediately. Call opengui_open_viewer with the original objective and successCriteria; supply deviceIds only for…
  2. Use WorkBuddy's BUILT-IN present_files with files: [returned workbenchUrl], cwd: current working directory, and one short sentence asking…
  3. Call opengui_viewer_status with viewerId and waitMs: 600000; it returns as soon as the user clicks 开始执行 and the first frame shows, so one…
  4. For pure viewing, finish now. No screenshot or continued model calls are needed. For control, first split the objective into outcome-based…
  5. Inspect returned executor.mode. If configured, call opengui_execute with sessionId and waitMs: 600000 to start the selected admin model on…
  6. Keep stepId unchanged for clicks and scrolling within a step. After verifying its successful result, select the returned…

What it can do on your machine

Read from SKILL.md and the folder at commit ad6d57f. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Phone And Simulator GUI Control loads about 7.2k tokens when it runs. Until then it costs about 42 tokens; SKILL.md has 3,993 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~42
When it runs · the whole SKILL.md, loaded when a task matches
~7.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 3,993 words (~7,186 tokens).

“Complete the user-authorized phone task using actual returned screenshots. Do not ask again for already authorized steps. Do not guess image ability from a model name; if you cannot read the image, report that blocker.”

— opening of SKILL.md by Core-Mate, Custom licence
name
opengui
display_name
opengui
display_name_en
opengui
description_zh
根据真实截图完成用户指定的 Android 手机任务和已支持的 macOS iOS 模拟器测试,自动恢复、核验结果并释放控制锁。
description_en
Complete authorized Android tasks and supported iOS simulator tests through a screenshot-action loop, local displays, bounded recovery and automatic task…
category
productivity
version
0.3.1
author
OpenGUI

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file in workbuddy-plugin/connector/skills/control of Core-Mate/OpenGUI.

  • SKILL.md
  • references.md

Open the folder on GitHubat commit ad6d57f

Compare with similar skills

Phone And Simulator GUI Control next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Phone And Simulator GUI Control compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Phone And Simulator GUI Control this skillCore-Mate/OpenGUI1.8k—~7.2kAutomated safety check: PassCustom licence
Phoneagentrounak/PhoneAgent798—~2.2kAutomated safety check: PassMIT
Maui AI DebuggingRedth/Maui.Gtk101—~4.1kAutomated safety check: PassMIT
Kuri iOSjustrach/kuri365—~1.7kAutomated safety check: PassCustom licence
Frb Dev Envfzyzcjy/flutter_rust_bridge5.4k—~5.5kAutomated safety check: PassMIT
Interceptor iOSHacker-Valley-Media/Interceptor514—~1.9kAutomated safety check: PassCustom licence

Similar skills

  • Phoneagent

    rounak/PhoneAgent

    Control a connected iPhone, iOS simulator, Android emulator, or Android device from macOS through PhoneAgent's JSON-RPC bridge.

    798 GitHub stars~2.2k tokensUpdated 1 mo ago
    MobileAuto-check passed
  • Maui AI Debugging

    Redth/Maui.Gtk

    End-to-end workflow for building, deploying, inspecting, and debugging .NET MAUI and MAUI Blazor Hybrid apps as an AI agent.

    101 GitHub stars~4.1k tokensUpdated 5 mo ago
    MobileAuto-check passed
  • Kuri iOS

    justrach/kuri

    Use kuri-ios to drive iOS Simulators from the CLI — list sims, boot/shutdown, navigate Safari to URLs (openurl), launch and terminate apps by bundle id, capture PNG screenshots, list installed apps…

    365 GitHub stars~1.7k tokensUpdated 2 mo ago
    MobileAuto-check passed
  • Frb Dev Env

    fzyzcjy/flutter_rust_bridge

    A skill your agent uses when the user wants Docker-based FRB development or Tart-based iOS Simulator validation.

    5.4k GitHub stars~5.5k tokensUpdated yesterday
    MobileAuto-check passed
  • Interceptor iOS

    Hacker-Valley-Media/Interceptor

    Drive any installed app on an owned, unlocked, Developer-Mode iPhone via interceptor ios : ref-tagged element trees, deterministic coordinate taps (click), reliable text entry (type/keys), scroll…

    514 GitHub stars~1.9k tokensUpdated 4 days ago
    Productivity & AutomationAuto-check passed
  • iOS Simulator control from inside Orca, with the live device view in Orca's emulator pane. Use when driving a booted Apple Simulator on macOS: taps, gestures…

    87k GitHub starsUsed in 1 repo~584 tokens
    MobileAuto-check passed

More from Core-Mate/OpenGUI

  • OpenGUI Bootstrap

    Core-Mate/OpenGUI

    Installs, configures and runs OpenGUI's backend and Android client from a plain-language request, running the repo's own setup scripts and asking the user only for physical phone steps or secrets.

    1.8k GitHub stars~1.7k tokensUpdated today
    Auto-check: notes
  • OpenGUI Installer for DSH

    Core-Mate/OpenGUI

    Installs and verifies the latest stable OpenGUI release in a DeepSeek Harness web profile on macOS without disturbing existing plugins or settings.

    1.8k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Lets a coding agent list, run, pause, resume or cancel natural-language tasks on an Android phone through the OpenGUI backend instead of raw ADB commands.

    1.8k GitHub stars~2.6k tokensUpdated today
    Auto-check: notes
  • Controls an authorized local Android phone, or shows its live read-only video feed, for phone app tasks and Android UI checks on macOS.

    1.8k GitHub stars~762 tokensUpdated today
    Auto-check passed
  • OpenGUI Plugin Installer

    Core-Mate/OpenGUI

    Installs or upgrades the standalone OpenGUI plugin for Codex or WorkBuddy on macOS from verified prebuilt GitHub releases, checking the SHA-256 before running anything.

    1.8k GitHub stars~1k tokensUpdated today
    Auto-check passed
  • OpenGUI Android Control

    Core-Mate/OpenGUI

    Drives locally connected Android phones through OpenGUI screenshots and allowlisted actions, one observed step at a time, for app, game and multi-device tasks.

    1.8k GitHub stars~788 tokensUpdated today
    Auto-check passed

Works with

Questions about Phone And Simulator GUI Control

What does Phone And Simulator GUI Control do?

Completes an already-authorized task on a real Android phone or a macOS iOS simulator one screenshot-driven action at a time. This skill drives a connected Android device or a supported macOS iOS simulator by reading real screenshots and issuing one action at a time, rather than guessing what a screen looks like. Every tap or swipe carries a declared side effect — none for plain navigation, or a specific marker for a final mutation — and the runtime blocks anything marked as a submit, send, publish, purchase, or delete action until that marker is explicitly set.

When should I use Phone And Simulator GUI Control?

Phone And Simulator GUI Control fits situations like: running a specific, already-authorized action on a connected Android phone; testing an app flow on a macOS iOS or Android simulator; walking through a multi-step phone task that needs screenshot confirmation at each step.

How do I install Phone And Simulator GUI Control in Claude Code?

Run `npx skills add Core-Mate/OpenGUI --skill opengui -a claude-code`. Or copy the skill folder (workbuddy-plugin/connector/skills/control in Core-Mate/OpenGUI) into .claude/skills/opengui in your project. Claude Code loads it when a task matches its description.

How do I install Phone And Simulator GUI Control in Codex?

Run `npx skills add Core-Mate/OpenGUI --skill opengui -a codex`. Or copy the skill folder (workbuddy-plugin/connector/skills/control in Core-Mate/OpenGUI) into .agents/skills/opengui in your project. Codex loads it when a task matches its description.

Can I use Phone And Simulator GUI Control in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Core-Mate/OpenGUI --skill opengui -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/opengui, .gemini/skills/opengui, .github/skills/opengui and .opencode/skills/opengui in your project.

What does Phone And Simulator GUI Control need to run?

SKILL.md names no scripts, command-line tools or credentials: Phone And Simulator GUI Control is instructions for the agent only. Our summary lists: A connected Android device or a supported macOS iOS simulator.

Does Phone And Simulator GUI Control access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Phone And Simulator GUI Control safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Phone And Simulator GUI Control use?

Phone And Simulator GUI Control has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Phone And Simulator GUI Control use?

About 7.2k tokens (SKILL.md is roughly 29k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Phone And Simulator GUI Control?

Skills that share tags, products or a category with Phone And Simulator GUI Control: Phoneagent (rounak/PhoneAgent, 798 stars), Maui AI Debugging (Redth/Maui.Gtk, 101 stars), Kuri iOS (justrach/kuri, 365 stars) and Frb Dev Env (fzyzcjy/flutter_rust_bridge, 5.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Phone And Simulator GUI Control?

Core-Mate (a GitHub organization) maintains it in Core-Mate/OpenGUI, which has 1,815 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 7, 2026.

Source: Core-Mate/OpenGUI on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.