claude-for-safari

Community

Control your real Safari browser with AI.

AuthorSDLLL
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill enables an AI agent to operate the user's real Safari browser on macOS using AppleScript and screencapture. It provides the ability to browse websites, read page content, automate browser tasks, take screenshots, and interact with live sessions without relying on extensions or proxies.

Core Features & Use Cases

  • Read and navigate pages by programmatically listing tabs, opening URLs, and switching between them.
  • Extract visible content and run JavaScript in page context to fetch dynamic data.
  • Take screenshots (foreground or background) for visual feedback and verification.
  • Automate common browser actions (clicks, typing, scrolling) to support workflows like data collection or form submission.

Quick Start

Instruct the AI to start controlling Safari to read pages, navigate, and take screenshots.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: claude-for-safari
Download link: https://github.com/SDLLL/claude-for-safari/archive/main.zip#claude-for-safari

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 510,000+ vetted skills library on demand.