screenshot

Capture desktop, window, and region screenshots on macOS, Linux, and Windows.

Updated Feb 4, 2026
One-click install
npx skills add https://github.com/pchemguy/AISandbox --skill screenshot-pchemguy
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: screenshot
Source: https://github.com/pchemguy/AISandbox/tree/main/docs/AgentSkills/openai/skills/skills/.curated/screenshot
Command: npx skills add https://github.com/pchemguy/AISandbox --skill screenshot-pchemguy

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve? Taking screenshots programmatically differs across operating systems, and agents often need OS-level captures when tool-specific options (like browser or Figma capture) are unavailable. This Skill provides unified scripts and instructions for capturing full screens, specific app windows, pixel regions, and active windows across macOS, Linux, and Windows. ## Core Features & Use Cases - Cross-platform capture helpers: A Python script for macOS/Linux and a PowerShell script for Windows handle full-screen, region, window, and active-window captures. - macOS window targeting: Capture windows by app name, window title, or window id, with a listing mode to discover ids and a permission preflight helper for Screen Recording. - Smart save locations: Saves to a user-specified path, the OS default screenshot location, or the temp directory for agent self-inspection. - Use Case: An agent asked to visually verify a running desktop app captures all its windows to the temp directory, views each image, and compares the result against a design mockup. ## Quick Start Take a screenshot of the currently active window and save it to the temp directory so you can inspect what is on screen.

Frequently Asked Questions about screenshot

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I take a screenshot of a specific app window on macOS?▼

Run the take_screenshot.py helper with the --app flag followed by the application name, which captures all matching on-screen windows. You can narrow results with --window-name or list candidates first using --list-windows to find a specific window id.

How to capture a specific screen region from the command line?▼

Pass a region as x,y,w,h pixel coordinates using the --region flag on macOS and Linux, or -Region in the PowerShell script on Windows. On Linux, region capture requires scrot or ImageMagick import to be installed.

Does this screenshot tool work on Linux and Windows?▼

Yes, Linux captures use scrot, gnome-screenshot, or ImageMagick import selected automatically, while Windows uses a dedicated PowerShell script. App-name and window-title capture are macOS-only; other platforms use active-window or window-id options.

Why does macOS screen capture fail with permission errors?▼

macOS requires Screen Recording permission before any capture can succeed. Run the ensure_macos_permissions.sh preflight script once to check and request permission, and rerun with escalated permissions if sandbox restrictions block the check.

Where are screenshots saved by default?▼

Captures save to the OS default screenshot location, such as the macOS Desktop or the Pictures/Screenshots folder on Windows and Linux. Use --mode temp to save to the temp directory or --path to specify an exact output file.