browser-skill

Community

Visually browse and interact with web pages

Authorcyzus
Version1.0.0
Installs0

System Documentation

What problem does it solve?

The Browser Skill lets the agent control a real headless Chrome instance to access pages that require JavaScript, inspect semantic structure, and perform element-level interactions that simple HTTP requests cannot handle.

Core Features & Use Cases

  • Navigate Dynamic Sites: Open pages, go back/forward, and reload to traverse complex web apps.
  • Semantic Snapshots: Produce semantic lists of interactive elements with ephemeral @e references for reliable targeting.
  • Element Interaction: Click, double-click, fill, type, press keys, hover, scroll, and click at coordinates to automate form submission, testing, and research tasks.

Quick Start

Open https://example.com, take a semantic snapshot to list interactive elements, and click the first referenced element.

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: browser-skill
Download link: https://github.com/cyzus/suzent/archive/main.zip#browser-skill

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 223,000+ vetted skills library on demand.