skills.rest
XDCIndia
XDCIndiaOFFICIAL
Explore all skills by this author →
Website𝕏@AnilChinchawaleGitHub

browse

Maintain a persistent headless Chromium daemon for automated web interaction.

Updated Aug 23, 2026
Search Tags:#cli#playwright#browse#web-automation#headless-browser#automation-testing
One-click install
npx skills add https://github.com/XDCIndia/SkyNet --skill browse-xdcindia
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: browse
Source: https://github.com/XDCIndia/SkyNet/tree/main/.claude/skills/gstack/browse
Command: npx skills add https://github.com/XDCIndia/SkyNet --skill browse-xdcindia

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides a persistent, headless browser environment that enables Claude Code to rapidly explore and interact with live web pages, reducing manual testing time and enabling automated data extraction and verification.

Core Features & Use Cases

  • Navigation & Interaction: goto, back, forward, reload, click, fill, hover, type, and clipboard-like chain operations to automate multi-step flows.
  • Content & Structure Extraction: text, html, links, forms, accessibility snapshots, and DOM inspection to gather data from pages and SPA apps.
  • Observability & Debugging: console and network buffering, performance timings, cookies/storage inspection, and visual outputs (screenshot/pdf) for quick validation.
  • Ref-based Interaction: after a snapshot, operate on stable refs like @e1 to click, fill, or inspect elements, with automatic ref invalidation on navigation.
  • Multi-tab & Resilience: support for multiple tabs, tab switching, and automatic server restarts in case of crashes or timeouts.

Quick Start

Start a session by issuing a command to load a URL, then progressively issue commands to inspect, interact with, and validate page content.

Frequently Asked Questions about browse

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate web interaction with a headless browser for Claude Code?▼

Automated web interaction for Claude Code is enabled by maintaining a persistent headless Chromium daemon. This daemon supports navigation, content extraction, and DOM interaction across traditional pages and single-page applications.

How do I run multi-step web automation flows using Playwright?▼

Multi-step web automation flows are executed by chaining commands like goto, click, fill, and hover. The system supports ref-based element selection, allowing you to operate on stable references like @e1 after taking an accessibility snapshot.

Does this headless browser tool support single-page applications and multiple tabs?▼

Yes, the headless browser tool fully supports single-page applications and multi-tab browsing. You can switch between tabs, execute chain operations, and rely on automatic server restarts for resilience during crashes or timeouts.

What is the best way to extract page content and debug SPAs in headless mode?▼

The best way to extract content and debug SPAs is by using built-in observability features. You can capture text, html, accessibility snapshots, console and network buffering, performance timings, and visual outputs like screenshots or PDFs.

Do I need a local Playwright runtime to use automated web browsing?▼

Yes, a local Playwright-based runtime is required to enable the persistent headless browser environment. It provides the secure command interface with authentication and buffering safeguards necessary for reliable automated data extraction.

Why do element refs become invalid during headless browser automation?▼

Element refs become invalid during headless browser automation because references are automatically invalidated upon navigation. This safeguard ensures that DOM interactions operate on current elements after page transitions or reloads.

Related Skills

Explore More Software Engineering Skills→
XinheLIUXinheLIU

browse

Operate a persistent headless Chromium browser for QA testing and site dogfooding.

Community
Advanced
lucasloutayflucasloutayf

browser-testing-with-devtools

Diagnose browser-rendered issues by inspecting real-time DOM, console, and network data.

Community
Advanced
nrupalanrupala

agent-browser

Automate browser navigation, form interaction, and data extraction via CLI commands.

Community
Advanced
Jia-Hong-PengJia-Hong-Peng

gstack

Automate persistent headless browser QA testing with Playwright and Chromium.

Community
Advanced