skills/desktop/SKILL.md
Windows desktop automation. Take full-screen or window screenshots, list/focus/minimize/maximize windows, send keystrokes, launch applications. Use when needing to capture the Windows screen, manage windows, send keyboard input, or start programs.
npx skillsauth add felipemsilva/powerskills powerskills-desktopInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Desktop automation: screenshots, window management, keystrokes, app launching.
.\powerskills.ps1 desktop <action> [--params]
| Action | Params | Description |
|--------|--------|-------------|
| screenshot | --out-file path.png [--window "title"] | Full screen or window capture |
| windows | | List all visible windows with title, PID, process name |
| focus | --window "title" | Bring window to foreground |
| minimize | --window "title" | Minimize window |
| maximize | --window "title" | Maximize window |
| keys | --keys "{ENTER}" [--window "title"] | Send keystrokes (SendKeys syntax) |
| launch | --app notepad [--app-args "file.txt"] [--wait-ms 3000] | Launch application |
# Full screen screenshot
.\powerskills.ps1 desktop screenshot --out-file screen.png
# Capture a specific window
.\powerskills.ps1 desktop screenshot --out-file outlook.png --window "Outlook"
# List all windows
.\powerskills.ps1 desktop windows
# Focus and type into Notepad
.\powerskills.ps1 desktop focus --window "Notepad"
.\powerskills.ps1 desktop keys --keys "Hello world{ENTER}" --window "Notepad"
# Launch an app
.\powerskills.ps1 desktop launch --app "notepad.exe" --app-args "C:\temp\notes.txt"
| Key | Syntax |
|-----|--------|
| Enter | {ENTER} |
| Tab | {TAB} |
| Escape | {ESC} |
| Ctrl+C | ^c |
| Alt+F4 | %{F4} |
| Shift+Tab | +{TAB} |
See Microsoft SendKeys docs for full syntax.
title, pid, process, hwnd
saved, width, height, window (if window capture)
testing
Windows system commands and info via PowerShell. Execute shell commands, get system info (hostname, OS, uptime), list top processes, read environment variables. Use when needing to run commands, check system status, or inspect the Windows environment.
tools
Outlook email and calendar automation via COM. Read inbox, unread, sent items. Search emails. Send, reply, draft. List calendar events and mail folders. Use when needing to check work email, read/send Outlook messages, search mail, or view calendar. Requires Outlook desktop app on Windows.
tools
Edge browser automation via Chrome DevTools Protocol (CDP). List tabs, navigate, take screenshots, extract page content/HTML, execute JavaScript, click elements, type text, fill forms, scroll. Use when needing to control Edge browser, scrape web content, automate web forms, or take browser screenshots on Windows. Requires Edge with --remote-debugging-port=9222.
tools
Windows automation toolkit for AI agents. Provides Outlook email/calendar, Edge browser (CDP), desktop screenshots/window management, and shell commands via PowerShell. Install this for the full suite, or install individual sub-skills (powerskills-outlook, powerskills-browser, powerskills-desktop, powerskills-system) separately.