Best desktop control skills, page 3

Use OpenPocket MCP tools to inspect or control an Android emulator, physical Android phone, Android TV, or ADB-backed app.

pockebot/openpocket

Control native macOS, Windows, and Linux desktop apps through the open-computer-use MCP server.

QwenLM/qwen-code-examples

Automate native macOS apps and system interactions via osascript (AppleScript)

vellum-ai/vellum-assistant

Delegate tasks to OpenSpace — a full-stack autonomous worker for coding, DevOps, web research, and desktop automation, backed by an extensive MCP tool and skill library.

HKUDS/OpenSpace

Drive the desktop background-first; escalate on signal. An agent skill from Prismer-AI/PrismerCloud.

Prismer-AI/PrismerCloud

Drive Google Cloud through the connected gcloud CLI (the cligcloud tool) — billing/costs, projects, compute, storage, IAM — instead of opening the Cloud Console in a browser via Computer-Use (which…

PersonalJarvis/PersonalJarvis

Connects AI agents to remote Windows desktop applications on Amazon WorkSpaces Applications (AppStream 2.0) through the managed Agent Access MCP server, and guides reliable desktop automation.

aws/agent-toolkit-for-aws

Live-test any Electron desktop app with native-devtools-mcp, Chrome DevTools Protocol, screenshots, OCR, and accessibility tools.

instructa/agent-skills

Regenerate docs/nodeparamaudit.md: every node's on-screen controls and whether each is modulatable (registers a ParamRef).

n1m21n/Infinite

Execute cross-platform desktop tasks through a packaged desktop automation skill that guides the main agent to observe the screen, focus apps and windows, call helper scripts for screenshots and…

LeoYeAI/openclaw-master-skills

This skill should be used when the user asks to "build a computer-use agent", "automate a GUI with an AI agent", "when to use computer use vs an API", "make browser automation reliable", or "design…

borghei/Claude-Skills

Design, build, review, or extend a production YouTube channel operator that combines complete typed YouTube Data, Analytics, Reporting, and Live API access with guided Slack or chatbot workflows…

swyxio/skills

Automate YouTube Studio through tab-bound Chrome control when API access is unavailable, insufficient, or slower for Studio-only edits.

swyxio/skills

Continue a coding session on a paired always-on computer. An agent skill from BuilderIO/agent-native.

BuilderIO/agent-native

Operate CompozyOS. An agent skill from compozy/compozy.

compozy/compozy

Execute programs on a compiled transformer stack machine where every instruction fetch and memory read is a parabolic attention head.

oaustegard/claude-skills

Reference data, not a reviewer. An agent skill from Community-Access/accessibility-agents.

Community-Access/accessibility-agents

Walk a native Windows, macOS, or Linux app through a flow with Poracode's desktop control and verify each step from the window itself.

Porabuild/Poracode

Optimize TechSmith desktop automation cost through license assignment, workstation utilization, retention, and measured export capacity.

jeremylongshore/tons-of-skills-marketplace

Manage Snagit and Camtasia workstation capacity with explicit capture, recorder, export, disk, and queue limits.

jeremylongshore/tons-of-skills-marketplace

Session primer for ADE work: what ADE is, the dev loop, the tooling you can reach (the ade CLI control plane, app/browser/iOS-sim control, Linear, computer-use), and what's in flight on this branch.

arul28/ADE

Finds common violations of the Android accessibility API in the Clank App Java code and attempts to address them (e.g.

nwjs/chromium.src

Two scopes: (1) drives Kimi.app via computer-use for Work/Agent data-plugin queries (天眼查、同花顺 iFinD、SEC、IMF etc.) and Chat's built-in 深度研究 report; (2) kimi-cu macOS desktop-automation playbook — AX…

daymade/claude-code-skills

Use the public orca CLI to operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, skill sharing, worktree comments, and the browser embedded inside the Orca app.

aiskillstore/marketplace

Fill long web forms and applications through a computer-use agent — from a fact sheet you approve, field by field, with a full transcript and nothing submitted without your word.

mohitagw15856/pm-claude-skills

Control a connected desktop

vellum-ai/vellum-assistant

Apply natural mapping — the strongest form of mapping, in which the spatial position, motion, or shape of a control directly corresponds to what it affects.

hashgraph-online/awesome-codex-plugins

Visually validate an interactive CLI or terminal UI in Codex's in-app browser using a real local PTY, fixed rendering, keyboard interaction, screenshots, and session evidence.

hashgraph-online/awesome-codex-plugins

ALWAYS ACTIVE. An agent skill from flornkm/personal-site.

flornkm/personal-site

A skill your agent uses for any computer use — driving an app, a screen, a simulator or a web page; clicking, typing, screenshotting, recording, or proving a UI change works.

arul28/ADE

Control desktop software (GIMP, Blender, LibreOffice, etc.) through CLI-Anything generated command-line interfaces.

openakita/openakita

Full Computer Use for OpenClaw via kasmweb/chrome Docker sidecar.

LeoYeAI/openclaw-master-skills

Set up macOS automation access for Apple Notes via AppleScript, JXA, and Shortcuts.

jeremylongshore/tons-of-skills-marketplace

Automates desktop GUI workflows via computer use API with screenshot capture.

athola/claude-night-market

Assistant juridique expert en droit français. An agent skill from lawve-ai/awesome-legal-skills.

lawve-ai/awesome-legal-skills