AI SummaryThis booster enables OS-level desktop and window screenshot capture when users explicitly request it or when tool-specific capabilities are unavailable. Developers and AI assistants benefit from having a fallback capture mechanism for debugging, documentation, and UI inspection tasks.
Install
Copy this and paste it into Claude Code, Cursor, or any AI assistant:
I want to install the "screenshot" skill in my project. Please run this command in my terminal: # Install skill into your project (11 files) mkdir -p .claude/skills/screenshot && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/screenshot/SKILL.md "https://raw.githubusercontent.com/openai/skills/main/skills/.curated/screenshot/SKILL.md" && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/screenshot/LICENSE.txt "https://raw.githubusercontent.com/openai/skills/main/skills/.curated/screenshot/LICENSE.txt" && mkdir -p .claude/skills/screenshot/agents && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/screenshot/agents/openai.yaml "https://raw.githubusercontent.com/openai/skills/main/skills/.curated/screenshot/agents/openai.yaml" && mkdir -p .claude/skills/screenshot/assets && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/screenshot/assets/screenshot-small.svg "https://raw.githubusercontent.com/openai/skills/main/skills/.curated/screenshot/assets/screenshot-small.svg" && mkdir -p .claude/skills/screenshot/assets && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/screenshot/assets/screenshot.png "https://raw.githubusercontent.com/openai/skills/main/skills/.curated/screenshot/assets/screenshot.png" && mkdir -p .claude/skills/screenshot/scripts && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/screenshot/scripts/ensure_macos_permissions.sh "https://raw.githubusercontent.com/openai/skills/main/skills/.curated/screenshot/scripts/ensure_macos_permissions.sh" && mkdir -p .claude/skills/screenshot/scripts && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/screenshot/scripts/macos_display_info.swift "https://raw.githubusercontent.com/openai/skills/main/skills/.curated/screenshot/scripts/macos_display_info.swift" && mkdir -p .claude/skills/screenshot/scripts && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/screenshot/scripts/macos_permissions.swift "https://raw.githubusercontent.com/openai/skills/main/skills/.curated/screenshot/scripts/macos_permissions.swift" && mkdir -p .claude/skills/screenshot/scripts && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/screenshot/scripts/macos_window_info.swift "https://raw.githubusercontent.com/openai/skills/main/skills/.curated/screenshot/scripts/macos_window_info.swift" && mkdir -p .claude/skills/screenshot/scripts && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/screenshot/scripts/take_screenshot.ps1 "https://raw.githubusercontent.com/openai/skills/main/skills/.curated/screenshot/scripts/take_screenshot.ps1" && mkdir -p .claude/skills/screenshot/scripts && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/screenshot/scripts/take_screenshot.py "https://raw.githubusercontent.com/openai/skills/main/skills/.curated/screenshot/scripts/take_screenshot.py" Then restart Claude Code (or reload the window in Cursor) so the skill is picked up.
Description
Use when the user explicitly asks for a desktop or system screenshot (full screen, specific app or window, or a pixel region), or when tool-specific capture capabilities are unavailable and an OS-level capture is needed.
Workflow examples
• "Take a look at <App> and tell me what you see": capture to temp, then view each printed path in order. `bash bash <path-to-skill>/scripts/ensure_macos_permissions.sh && \ python3 <path-to-skill>/scripts/take_screenshot.py --app "<App>" --mode temp ` • "The design from Figma is not matching what is implemented": use a Figma MCP/skill to capture the design first, then capture the running app with this skill (typically to temp) and compare the raw screenshots before any manipulation.
Linux prerequisites and selection logic
The helper automatically selects the first available tool: 1) scrot 2) gnome-screenshot 3) ImageMagick import If none are available, ask the user to install one of them and retry. Coordinate regions require scrot or ImageMagick import. --app, --window-name, and --list-windows are macOS-only. On Linux, use --active-window or provide --window-id when available.
Screenshot Capture
Follow these save-location rules every time: 1) If the user specifies a path, save there. 2) If the user asks for a screenshot without a path, save to the OS default screenshot location. 3) If Codex needs a screenshot for its own inspection, save to the temp directory.
Tool priority
• Prefer tool-specific screenshot capabilities when available (for example: a Figma MCP/skill for Figma files, or Playwright/agent-browser tools for browsers and Electron apps). • Use this skill when explicitly asked, for whole-system desktop captures, or when a tool-specific capture cannot get what you need. • Otherwise, treat this skill as the default for desktop apps without a better-integrated capture tool.
Discussion
Health Signals
My Fox Den
Community Rating
Sign in to rate this booster