Topic · Productivity & Automation
Best desktop control skills, page 2
Desktop control skills, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 49 | 49.Triage 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/ | 325 | — | ~2.2k | Automated safety check: Pass | MIT | 1 mo ago |
| 50 | Guides visual testing of Warp UI changes by launching the app with an API key and driving it through the computer use tool, with optional mocked state. | warpdotdev/ | 65k | 1 repo | ~1k | Automated safety check: Pass | AGPL-3.0 | yesterday |
| 51 | 51.Computer Use Operate apps/websites on the paired Mac via Buddy: Calendar, Notes, forms, screenshots, files. | autonomous-ai/ | 381 | — | ~2k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 52 | 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/ | 4.3k | — | ~3.8k | Automated safety check: Pass | Unknown | 4 days ago |
| 53 | GUI desktop app only. An agent skill from warpdotdev/warp. | warpdotdev/ | 65k | 1 repo | ~6.2k | Automated safety check: Pass | AGPL-3.0 | yesterday |
| 54 | 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/ | 325 | — | ~2.2k | Automated safety check: Pass | MIT | 1 mo ago |
| 55 | 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/ | 165 | — | ~4.5k | Automated safety check: Pass | MIT | 4 mo ago |
| 56 | Guidance for reliable, token-efficient Windows automation through MCP. | sbroenne/ | 106 | — | ~1.5k | Automated safety check: Pass | MIT | yesterday |
| 57 | 57.Computer Use Drive the Agent's graphical desktop with the desktop helper — look at the screen, point, type, and control native applications. | Altinn/ | 169 | — | ~2k | Automated safety check: Pass | MIT | yesterday |
| 58 | Desktop automation through the real Rust agent-desktop CLI, published in Printing Press through a small bridge. | mvanhorn/ | 2.1k | — | ~2.3k | Automated safety check: Notes | Apache-2.0 | yesterday |
| 59 | 59.Computer Use Control local desktop applications through Computer Use for tasks that require reading or operating app UI. | QwenLM/ | 28k | — | ~3.6k | Automated safety check: Pass | Apache-2.0 | today |
| 60 | 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/ | 28k | 1 repo | ~16k | Automated safety check: Pass | Apache-2.0 | today |
| 61 | 61.Windows CLI Guidance for driving Windows desktop automation from the wincli command-line tool - the token-efficient entry point that mirrors the Windows MCP server. | sbroenne/ | 106 | — | ~1.8k | Automated safety check: Pass | MIT | yesterday |
| 62 | 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/ | 65k | — | ~1.2k | Automated safety check: Pass | AGPL-3.0 | yesterday |
| 63 | Controls desktop applications through screenshots: a vision model reads the screen and returns click, type and scroll actions that pyautogui then performs. | THU-SAGE/ | 303 | — | ~662 | Automated safety check: Pass | MIT | 4 mo ago |
| 64 | 64.Cua Driver 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/ | 4.1k | — | ~821 | Automated safety check: Pass | MIT | yesterday |
| 65 | 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/ | 325 | — | ~6.8k | Automated safety check: Pass | MIT | 1 mo ago |
| 66 | 66.Computer Use 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/ | 336 | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 67 | 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/ | 41k | — | ~1.4k | Automated safety check: Pass | MIT | yesterday |
| 68 | 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/ | 933 | — | ~3.3k | Automated safety check: Pass | No licence | 3 mo ago |
| 69 | 69.QA Systematically QA test any application — web apps, native macOS apps, Electron apps, CLI tools, interactive REPLs, or anything on screen. | team-attention/ | 173 | — | ~2.6k | Automated safety check: Notes | MIT | 4 mo ago |
| 70 | 70.Unicli Usage Command reference for Uni-CLI — the open Agent-Computer Interface runtime for real software. | olo-dot-io/ | 274 | — | ~1.5k | Automated safety check: Pass | Apache-2.0 | 4 days ago |
| 71 | Build AI agents that interact with computers like humans do - viewing screens, moving cursors, clicking buttons, and typing text. | davila7/ | 32k | 6 repos | ~2.4k | Automated safety check: Pass | MIT | yesterday |
| 72 | 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/ | 325 | — | ~3.8k | Automated safety check: Pass | MIT | 1 mo ago |
| 73 | 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/ | 707 | — | ~3.6k | Automated safety check: Pass | MIT | yesterday |
| 74 | Batch YouTube Studio upload workflow for videos sourced from Airtable, Google Drive, Loom, YouTube, or local files. | swyxio/ | 175 | — | ~1.5k | Automated safety check: Warn | MIT | 4 days ago |
| 75 | Transform Claude Code into a fully autonomous agent system with persistent memory, scheduled operations, computer use, and task queuing. | affaan-m/ | 275k | 2 repos | ~2.9k | Automated safety check: Pass | MIT | 3 days ago |
| 76 | Drive native applications on macOS, Windows, or Linux through the separately installed TryCUA driver CLI. | am-will/ | 941 | — | ~370 | Automated safety check: Pass | MIT | 29 days ago |
| 77 | Debug and validate OpenBridge on a real macOS desktop through mini-machine plus full VNC computer-use. | AFK-surf/ | 430 | — | ~2.2k | Automated safety check: Pass | MIT | 4 mo ago |
| 78 | 78.Computer Use Drive the user's desktop in the background — clicking, typing, scrolling, dragging — without stealing the cursor, keyboard focus, or switching virtual desktops / Spaces. | johnson7788/ | 327 | 1 repo | ~2.8k | Automated safety check: Warn | MIT | 1 mo ago |
| 79 | 79.Cmux Cua 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/ | 28k | — | ~4.5k | Automated safety check: Pass | Unknown | today |
| 80 | 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/ | 108 | — | ~2.4k | Automated safety check: Pass | AGPL-3.0 | 4 mo ago |
| 81 | 81.Computer Use Use Cua Driver through MCP to inspect and operate the user's native desktop apps on Windows, macOS, or Linux. | xuzhougeng/ | 1k | — | ~2.9k | Automated safety check: Pass | AGPL-3.0 | yesterday |
| 82 | 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/ | 4.3k | — | ~3.4k | Automated safety check: Pass | Unknown | 4 days ago |
| 83 | 83.Computer Use Inspect and operate native Windows, macOS, or Linux applications through Poracode's desktop-control tools. | Porabuild/ | 114 | — | ~718 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 84 | Control terminal TUIs, browsers, and native desktop apps for testing, demos, QA, and computer-use tasks. | Factory-AI/ | 110 | — | ~3.6k | Automated safety check: Notes | No licence | yesterday |
| 85 | 85.Control API Change Jarvis's own configuration through the local Control API instead of clicking the desktop UI or driving Computer-Use. | PersonalJarvis/ | 141 | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | today |
| 86 | 86.Desktop Act Cross-OS computer-use MCP: multi-agent exclusive desktop leases, Xvnc pool on Linux, single-session macOS/Windows. | Lifecycle-Innovations-Limited/ | 540 | — | ~560 | Automated safety check: Pass | MIT | yesterday |
| 87 | Operate desktop applications and browsers reliably through Computer Use, with proactive state tracking and recovery from common automation failures. | swyxio/ | 175 | — | ~4k | Automated safety check: Pass | MIT | 4 days ago |
| 88 | Build AI agents that interact with computers like humans do - viewing screens, moving cursors, clicking buttons, and typing text. | sickn33/ | 47k | 2 repos | ~450 | Automated safety check: Pass | MIT | yesterday |
| 89 | 89.Computer Use Control the local desktop using the computer MCP tool from computer-use-mcp. | QwenLM/ | 143 | — | ~632 | Automated safety check: Pass | No licence | 4 mo ago |
| 90 | Automate native Windows apps and system interactions with PowerShell, documented COM APIs, and Microsoft UI Automation through the Windows host executor. | vellum-ai/ | 1.4k | — | ~1.5k | Automated safety check: Pass | MIT | yesterday |
| 91 | 91.Computer Use 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/ | 1.2k | — | ~1.7k | Automated safety check: Pass | MIT | yesterday |
| 92 | 92.LLM Security 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/ | 104 | — | ~2.8k | Automated safety check: Pass | No licence | 5 mo ago |
| 93 | 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/ | 608 | — | ~3.2k | Automated safety check: Pass | MIT | yesterday |
| 94 | 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/ | 114 | — | ~2.5k | Automated safety check: Pass | AGPL-3.0 | today |
| 95 | Build and run Gemini 2.5 Computer Use browser-control agents with Playwright. | aiskillstore/ | 430 | 2 repos | ~519 | Automated safety check: Pass | No licence | yesterday |
| 96 | 96.QA A skill your agent uses to verify that code works correctly — browser-based testing with Playwright, native app testing with computer use, CLI testing, API testing, or root-cause debugging. | garagon/ | 207 | — | ~3.4k | Automated safety check: Pass | Apache-2.0 | 28 days ago |
Explore related skills
Category
More topics in Productivity & Automation
- App automation through connectors735
- Messaging and chat bots597
- Browser automation540
- Web search506
- Email management428
- Scheduled and recurring tasks393
- Workflow automation262
- Meeting notes and agendas258
- Task management215
- Health and fitness tracking129
- File organization112
- Focus and ADHD support60
- Time tracking and reporting46
- Calendar and scheduling42