How does BrowserX handle multi-step workflows like logins?

It uses session-based tools and a managed BrowserPool to maintain state (cookies, local storage, and history) across multiple steps, ensuring a persistent session.

Does BrowserX support capturing visual page data?

Yes, it includes specialized tools for capturing high-quality screenshots (PNG/JPEG) and generating formatted PDFs of web pages or specific elements.

What is BrowserX in the context of Claude Code?

BrowserX is a Claude Code skill that provides a suite of tools for browser automation, web scraping, and proxy management via the Model Context Protocol (MCP).

Can I use SQL to scrape websites with BrowserX?

Yes, the browserx_query tool allows you to use a familiar SQL-like syntax to SELECT data, NAVIGATE to URLs, and even INSERT values into forms.

Can I block tracking scripts using this skill?

Yes, the proxy tools allow you to add interceptors that can block, allow, or modify specific network requests based on URL patterns.

BrowserX Automation & Scraping

Name: BrowserX Automation & Scraping
Author: LayerDynamics

byLayerDynamics

0•

ブラウザ自動化

Automates browser interactions, web scraping, and network proxying using SQL-like queries and imperative session controls.

BrowserX is a specialized Claude Code skill that empowers AI agents to perform complex web automation and data extraction tasks through a composable Model Context Protocol (MCP) toolkit. It features a unique SQL-like query language for declarative scraping, imperative tools for multi-step session-based workflows such as form filling and PDF generation, and advanced proxy capabilities for request interception and caching. Designed for the Lore framework, it provides a deterministic approach to AI-assisted browser management, ensuring repeatable results for monitoring, testing, and data collection tasks.

主な機能

01High-fidelity output options including screenshots and PDF generation

02Session-based imperative automation for complex login and navigation flows

03SQL-like declarative query engine for simplified web data extraction

040 GitHub stars

05Advanced proxy management with request interception and TTL-based caching

06Resource-efficient BrowserPool for managing concurrent browser instances

ユースケース

01Automated web scraping and structured data extraction from dynamic sites

02End-to-end browser testing and automated form-filling workflows

03Network-level monitoring and performance optimization using proxy interceptors

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add layerdynamics/lore using-browserx

For use in Claude.ai and ChatGPT