Best desktop control skills for Claude Code, Codex and other agents.

Automates Electron desktop apps such as VS Code, Slack or Discord by connecting agent-browser to their Chrome DevTools Protocol port.

vercel-labs/agent-browser

Local vision CLIs: glance (describe/ask/OCR an image), ground (locate a target, pixel box), detect (element inventory), trace (image to SVG geometry), crop (cut a pixel box to a file), and…

Anionex/agent-vision-toolkit

Platform-neutral guidance for using Open Computer Use, the open-source Computer Use MCP server and CLI for macOS, Linux, and Windows.

iFurySt/open-codex-computer-use

Drives the GUI of a visible local app window through `orca computer`: accessibility tree, clicks, typing, menus, dialogs, and screenshots in native…

stablyai/orca

Records an annotated screen recording of the agent testing an app hands-on, then posts the video and a results summary to the PR and tracker issue.

michaelshimeles/skills

操作 macOS 桌面应用，探测窗口和自动化接口、截图、读取或修改辅助功能元素、执行鼠标键盘动作，以及通过 CDP 操作内嵌 Chromium 页面。适用于桌面应用自动化与界面验收；普通网页任务优先使用已有浏览器工具。

To3akaRin/mac-computer-use

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

Controls the macOS desktop visually through the TuriX computer-use agent, for opening apps, clicking buttons and navigating interfaces that have no CLI or API.

TurixAI/TuriX-CUA

Uses a clean Parallels macOS VM to test GUI automation, TCC permission prompts and screenshot tools like Peekaboo, verifying results from outside the guest.

steipete/agent-scripts

Control local macOS, Windows, and Linux apps through Waku Computer Use.

egoist/waku

Controls macOS native apps that have no API, taking window-level screenshots as reproducible evidence without stealing focus and probing whether an app can be automated.

alchaincyf/huashu-mac-use

Lets an agent observe and operate a local Linux desktop through the computer-use-linux MCP server or Pi tools: accessibility trees, screenshots, windows and input.

agent-sh/computer-use-linux

Drive a signed-in Chrome / Brave / Safari session via the interceptor CLI: open/read pages, click, type, inspect DOM/text/network, automate rich browser editors and scene graphs, capture…

Hacker-Valley-Media/Interceptor

Drives desktop GUI apps and OS dialogs by letting Jev pick the next action from a menu of safe actions the agent built, with a Mac Co-Agent shortcut.

kerpopule/hermes-jev-skills

Use the built-in Computer sub-agent with agent-desktop for macOS desktop automation.

superagent-ai/grok-cli

A skill your agent uses when you need to visually interact with a GUI — test buttons, fill forms, verify visual layouts, fuzz web pages, automate user flows, take screenshots, or perform end-to-end…

am-will/gooey-pi

Create, inspect, edit, persist, and verify tldraw canvases through the tldraw Desktop local Canvas API without mouse-driven Computer Use.

hoangnb24/skills

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

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…

Hacker-Valley-Media/Interceptor

Drives a hidden, agent-owned Linux desktop and browser over MCP for GUI testing and web automation without touching the user's real desktop.

agent-sh/agent-workspace-linux

macOS automation skill for AppleScript actions and Chrome browser control via MCP CDP tools.

altic-dev/altic-mcp

Read verified Altium schematic connectivity from .PrjPcb projects or .SchDoc sheets through the bundled script-only Windows JSON runtime.

Chsier/ADReader

Record a user-demonstrated macOS workflow with the Open Record/Replay CLI, inspect the captured event stream, prepare a skill evidence package, and hand it to the host agent's native skill creator.

humblebanana/open-record-replay

Legacy Autonomous Buddy control for explicitly requested Buddy coding sessions.

autonomous-ai/Physical-AI-Operating-System

Takes a screenshot of a running Electron desktop app through playwright-cli over remote debugging, shrinks it and shows it so you can check the UI visually.

keybase/client

Review a PR from local annotated-diff artifacts and write validated review.json for the workflow to publish.

warpdotdev-demos/cloud-factory-demo

Use Orca's computer-use CLI to inspect and operate local desktop app windows through accessibility trees, screenshots, and safe UI actions.

bam-bam-2/solo-skills

Control, inspect, test, or automate a physical Android phone connected to OpenMausBot over authorized USB debugging.

milind-soni/OpenMausBot

Comprehensive guide to Uni-CLI — the open Agent-Computer Interface runtime for real software.

olo-dot-io/Uni-CLI

Invoke this automatically after completing any user-facing client change, ONLY in non-sandboxed environments and local environments.

Heartcoolman/warp-cn

Verify Reel, the macOS menu-bar screen recorder, by launching a disposable app bundle and driving its real UI with Computer Use.

rselbach/reel

See and control desktop apps on this Cloud sandbox’s virtual Linux screen with cloudroom computer-use: launch GUI apps you build or install, read their UI, click, type, and take screenshots.

davidondrej/cloudroom-core

Cleans a voice recording by driving Adobe Audition on a macOS host to reduce hiss, hum, background noise and sibilance, after asking for your consent.

THU-SAGE/syll

Use the steve CLI to automate macOS apps via Accessibility APIs.

mikker/steve

Route every Hancom/HWP document edit, analysis, and verification request to the GSGHWPBETA (gsg-hwp-beta-live) MCP.

innae1121-bit/gsghwp

Create and edit visual designs with Affinity or HTML, including computer-use editing, native-file saving, browser editing and export checks.

julilaoshi/julilaoshi-design

Create and maintain automated tests in Microsoft-native/.NET projects with a minimal stack — MSTest runner, System.Windows.Automation for Windows desktop, Playwright for real browser smoke.

JocysCom/FocusLogger

Use Orca orchestration for structured multi-agent coordination: threaded messages, blocking ask/reply flows, task dispatch, workerdone/escalation waits, task DAGs, decision gates, coordinator loops…

bam-bam-2/solo-skills

Take real control of the desktop - list and focus windows, type, paste, click, scroll, and screenshot - on Windows, macOS or Linux, and drive other coding-agent sessions running in terminals.

coleam00/skills

macOS GUI automation CLI. An agent skill from disler/mac-mini-agent.

disler/mac-mini-agent

Pick a browser or desktop agent's next action by choosing among the actions actually on screen instead of inventing one.

mrmps/classifier-dev

Drive a macOS app through the computer tool — read its accessibility tree, act on elements, and use real input only when the tree cannot reach the target.

kunpengtalk/PeakCode

Develop and verify HyperTTS GUI screens against a real, running Anki instance: launch Anki headlessly on a throwaway profile, inject notes with AnkiConnect, read the live Qt widget tree as text…

Vocab-Apps/anki-hyper-tts

Operates native desktop apps through DeepChat's built-in Computer Use tools, following a snapshot-then-act loop with session setup, app launch and window inspection.

ThinkInAIXYZ/deepchat

A skill your agent uses when testing or debugging Flet apps in maintainer/contributor development mode with local Python package sources and the local Flutter client, including web, desktop…

flet-dev/flet

A skill your agent uses when testing Windows 11 desktop apps (WinForms/WPF/UWP) via UFO UIA/Win32 automation MCP.

CodeAlive-AI/ai-driven-development

Operate web pages in Emperor's built-in browser with the browser tools, and macOS app windows with the desktop tools — open or bind a target, read it, fill, click or type, and verify the result.

TheSyart/emperor-agent

Triage an incoming GitHub, Jira, Linear, or other issue-tracker issue against the current codebase and related open issues, then return a structured decision with exactly one…

warpdotdev-demos/cloud-factory-demo