Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Control

ASecurity

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.

1,800 stars
0 votes
0 copies
0 views
Added 8/31/2026
ai-agentsshellbashnodetesting

Works with

climcp

Security Analysis

A100/100

Scanned 8/31/2026

Install to Claude Code

$npx -y skills add Core-Mate/OpenGUI --skill control --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Control?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Control
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/core-mate-control/badge)](https://www.skillsdirectory.com/skills/core-mate-control)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: control
description: 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.
---

# 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

1. Call `opengui_list_devices`. Explain USB authorization or connection errors rather than guessing.
2. Call `opengui_open_session` with one to four selected device ids. Omit ids only when exactly one authorized phone is connected.
3. Call `opengui_observe` before the first mutation. Treat the returned screenshot pixels as the only valid coordinate space.
4. 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.
5. Open the returned `deviceWallUrl` in the native Codex Browser when the user asks to monitor devices or when a multi-device wall helps.
6. 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.

Attribution

Core-MateCore-Mate
View sourceMore from Core-Mate →
SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →