Zum Inhalt springen

Skills / claude for safari

claude for safari

Give your AI Agent the power to control Safari on macOS. No extensions, no separate browser.

21von @SDLLLvor 39d aktualisiertMITGitHub →

Installation

Kompatibilitaet

Claude CodeCursor

Beschreibung


Why This?

You want your AI Agent to help with browser tasks — then you discover:

  • 🔒 Playwright → Separate browser instance, hijacks your session
  • 🧩 Claude for Chrome → Requires Chrome extension, doesn't work with Safari
  • 📝 Copy & paste → Manually feeding page content to AI every time

You just want AI to use your Safari, as if you were doing it yourself.

Claude for Safari makes it one command:

npx skills add SDLLL/claude-for-safari

After installing, tell Claude "check what's open in my Safari" — it reads and controls your real browser directly.

If this saves you time, give it a ⭐ — it helps other developers discover the project!


Quick Start

Run this in your terminal:

npx skills add SDLLL/claude-for-safari

Then launch Claude Code:

claude

Say "show me what tabs are open in Safari". The agent will guide you through permission setup automatically.

Compatible with any AI Agent that supports Skills: Claude Code, Cursor, Windsurf, etc.

First-Time Setup

The agent auto-detects and guides you, but you can configure ahead of time:

  1. System Settings > Privacy & Security > Automation → Allow terminal to control Safari
  2. Safari > Settings > Advanced → Enable "Show features for web developers"
  3. Safari > Develop menu → Check "Allow JavaScript from Apple Events"
  4. (Optional) System Settings > Privacy & Security > Screen Recording → Allow terminal (enables background screenshots)

Features

Zero install. Pure macOS native capabilities. One Skill covers all browser operations:

| Capability | What the Agent Does | How | |---|---|---| | List tabs | List all windows and tabs with title & URL | AppleScript | | Read pages | Extract text, structured data, simplified DOM | AppleScript + JavaScript | | Execute JS | Run arbitrary JavaScript in page context | AppleScript do JavaScript | | Screenshot | Capture Safari window — AI can "see" the page | screencapture | | Navigate | Open URLs, new tabs, new windows | AppleScript | | Click | Click elements (React/Vue/Angular compatible) | JavaScript dispatchEvent | | Type | Fill forms, simulate keyboard input | JavaScript + System Events | | Scroll | Scroll up/down, scroll to element | JavaScript scrollBy/scrollTo | | Switch tabs | Switch by index or URL keyword | AppleScript | | Wait for load | Wait until page is fully loaded | JavaScript readyState |

Screenshot Modes

| Mode | Permission Required | Window Switch | Best For | |---|---|---|---| | Background | Screen Recording | No switch | Recommended, seamless | | Foreground | None | Brief (~0.3s) | Default, auto-switches back |


How It Works

Claude Code ──osascript──► Safari (reads/controls your real browser)
     │
     └──screencapture──► screenshot ──► Claude sees the page

No extensions. No proxy servers. No extra processes.

Everything runs through macOS native AppleScript and screencapture. Websites see a real user — no automation fingerprints.


FAQ

No. This Skill relies entirely on macOS built-in AppleScript and screencapture. Just grant a few system permissions on first use.

Safari only. For other browsers, use Playwright MCP or Chrome ACP. Safari is the only macOS browser with full AppleScript automation support.

Claude Code's permission system asks for your confirmation before every sensitive action. You can approve individually or in bulk. All operations are visible in your terminal.

Without Screen Recording permission, Safari briefly activates (~0.3s) then switches back. Grant Screen Recording permission for fully background screenshots with zero window switching.

Any agent supporting Claude Code Skills: Claude Code, Cursor, Windsurf, etc.


License

MIT

Aehnliche Skills