Desktop control

Operate apps/websites on the paired Mac via Buddy: Calendar, Notes, forms, screenshots, files.

autonomous-ai/Physical-AI-Operating-System

Use the signed-in ChatGPT website in Chat UI Pro mode, never Work mode, to research, architect, and review one local project through a configured Secure Tunnel and read-only MCP, while Codex alone…

mcncarl/yichen-skills

GUI desktop app only. An agent skill from warpdotdev/warp.

warpdotdev/warp

Verify or reproduce visible product behavior by delegating to Oz's dedicated computer-use capability, requiring a native Oz video artifact for meaningful UI flows and durable Oz run/artifact links.

warpdotdev-demos/cloud-factory-demo

Goal-driven E2E testing where a browser agent (Playwright MCP / computer-use) reads a natural-language goal and explores the app via the accessibility tree to assert outcomes — no pre-written script.

petrkindlmann/qa-skills

Use the user's already signed-in official ChatGPT website account, especially GPT-5.5 Pro / ChatGPT Pro, to perform product research, market research, competitor research, second-opinion research…

bear2u/my-skills

Guidance for reliable, token-efficient Windows automation through MCP.

sbroenne/mcp-windows

A skill your agent uses when a task needs a native desktop app's own UI or the OS.

zai-org/ZCode

Drive the Agent's graphical desktop with the desktop helper — look at the screen, point, type, and control native applications.

Altinn/altinn-studio

Desktop automation through the real Rust agent-desktop CLI, published in Printing Press through a small bridge.

mvanhorn/printing-press-library

Control local desktop applications through Computer Use for tasks that require reading or operating app UI.

QwenLM/qwen-code

Guidance for driving Windows desktop automation from the wincli command-line tool - the token-efficient entry point that mirrors the Windows MCP server.

sbroenne/mcp-windows

Controls desktop applications through screenshots: a vision model reads the screen and returns click, type and scroll actions that pyautogui then performs.

THU-SAGE/syll

Verifies a Warp client change by pushing it to a branch and spawning a cloud agent with computer use that follows the test-warp-ui skill, only when you ask for it.

warpdotdev/warp

Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling…

davidondrej/skills

A skill your agent uses when opening, navigating, inspecting, testing, clicking, typing, filling, screenshotting, or verifying web pages and local HTTP targets (localhost, 127.0.0.1, ::1) inside…

zai-org/ZCode

Sets up a beginner-friendly Oz cloud software factory that automatically triages new GitHub issues, specs issues labeled ready-to-spec, implements issues labeled ready-to-implement, reviews PRs, and…

warpdotdev-demos/cloud-factory-demo

Use before operating an app on the user's computer, such as clicking, filling a field, reading a window or moving through a website in their browser.

katipally/openlive

Operates desktop apps and isolated or disposable browsers on registered computers through an observe, act, verify loop, separate from driving the user's own signed-in Chrome.

codewhale-hq/Codewhale

Give an AI agent its own real browser over MCP tool calls - launch, navigate, click, fill, screenshot, extract text, run JS - with a kernel-level real-device fingerprint and a persistent profile, so…

antibrow/anti-detect-browser-skills

Systematically QA test any application — web apps, native macOS apps, Electron apps, CLI tools, interactive REPLs, or anything on screen.

team-attention/hoyeon

Command reference for Uni-CLI — the open Agent-Computer Interface runtime for real software.

olo-dot-io/Uni-CLI

Implement a fix or feature from a GitHub, Jira, Linear, or other issue-tracker issue by fetching issue context, inspecting the current codebase, making code changes, validating them, verifying…

warpdotdev-demos/cloud-factory-demo

Drive any UI surface like a real user - a web app, a Chromium-backed desktop app (Electron / WebView2, reached over CDP), or a genuinely native app (macOS AppKit/SwiftUI, or a non-CDP webview)…

gmickel/flow-next

Batch YouTube Studio upload workflow for videos sourced from Airtable, Google Drive, Loom, YouTube, or local files.

swyxio/skills

Build AI agents that interact with computers like humans do - viewing screens, moving cursors, clicking buttons, and typing text.

davila7/claude-code-templates

Drives native desktop apps on macOS, Windows and Linux through the Qwen Cua Driver CLI or MCP server, snapshotting accessibility trees and verifying each action.

QwenLM/qwen-code

Transform Claude Code into a fully autonomous agent system with persistent memory, scheduled operations, computer use, and task queuing.

affaan-m/ECC

Drive native applications on macOS, Windows, or Linux through the separately installed TryCUA driver CLI.

am-will/gooey-pi

Debug and validate OpenBridge on a real macOS desktop through mini-machine plus full VNC computer-use.

AFK-surf/OpenBridge

Use only after the user explicitly asks for cmux Computer Use through the cmux-cua skill: drive real macOS apps from a cmux agent session via the bundled engine (accessibility tree + screenshots…

manaflow-ai/cmux

Guides an agent to operate native macOS apps by surveying an app first, acting through intents, menus or keystrokes, and verifying each step, in OpenLoaf Desktop only.

OpenLoaf/OpenLoaf

Record the App Store review demo video for lpm Link: the lpm desktop app and lpm Link on a physical iPhone (live through iPhone Mirroring) side by side, pairing and then controlling the Mac from the…

gug007/lpm

Drive the user's desktop in the background — clicking, typing, scrolling, dragging — without stealing the cursor, keyboard focus, or switching virtual desktops / Spaces.

johnson7788/MultiUserClaw

Use Cua Driver through MCP to inspect and operate the user's native desktop apps on Windows, macOS, or Linux.

xuzhougeng/wisp-science

Use the user's already signed-in official ChatGPT website account, especially GPT-5.5 Pro / ChatGPT Pro, to perform product research, market research, competitor research, second-opinion analysis…

mcncarl/yichen-skills

Inspect and operate native Windows, macOS, or Linux applications through Poracode's desktop-control tools.

Porabuild/Poracode

Control terminal TUIs, browsers, and native desktop apps for testing, demos, QA, and computer-use tasks.

Factory-AI/factory-plugins

Change Jarvis's own configuration through the local Control API instead of clicking the desktop UI or driving Computer-Use.

PersonalJarvis/PersonalJarvis

Cross-OS computer-use MCP: multi-agent exclusive desktop leases, Xvnc pool on Linux, single-session macOS/Windows.

Lifecycle-Innovations-Limited/claude-ops

Operate desktop applications and browsers reliably through Computer Use, with proactive state tracking and recovery from common automation failures.

swyxio/skills

Control the local desktop using the computer MCP tool from computer-use-mcp.

QwenLM/qwen-code-examples

Build AI agents that interact with computers like humans do - viewing screens, moving cursors, clicking buttons, and typing text.

sickn33/agentic-awesome-skills

Automate native Windows apps and system interactions with PowerShell, documented COM APIs, and Microsoft UI Automation through the Windows host executor.

vellum-ai/vellum-assistant

Drive the desktop — macOS, or the Windows desktop through WSL — when a task needs a native app, dialog, menu bar, file picker or anything the terminal and browser tools cannot reach.

clacky-ai/openclacky

LLM and AI application security testing skill for prompt injection (direct, indirect, multimodal), system-prompt extraction, RAG poisoning, memory poisoning, MCP server injection, skill-file…

hardw00t/ai-security-arsenal

Launch Oz cloud agents with computer use to reproduce UI-focused bug reports, capture visual evidence (a screen recording by default), and report reproduction findings.

warpdotdev/common-skills

A skill your agent uses when the user asks for proof, screenshots, video, artifacts, test evidence, computer-use capture, or when work should appear in ADE's proof drawer.

arul28/ADE