Safari Browser Control for macOS
This skill enables an agent to operate the user's actual Safari browser session, allowing access to existing login states, cookies, and open tabs without requiring browser extensions.
Key Capabilities:
- DOM Interaction: Read page content, extract structured metadata (titles, headings), and execute arbitrary JavaScript via
osascript.
- Tab Management: List all open tabs, switch between them, and open new URLs in tabs or windows.
- Visual Feedback: Take screenshots of the Safari window (both background and foreground modes) to verify actions.
- Form Automation: Fill inputs using native JS setters and simulate real keyboard events via System Events for React/Vue compatibility.
- Navigation & Control: Scroll pages, click elements, and wait for page load completion.
Requirements: Requires macOS with specific permissions for Automation and JavaScript from Apple Events enabled in Safari.
Not yet audited
This skill has not been reviewed by our automated audit pipeline yet.