skills.rest
fengzhizi319
fengzhizi319COMMUNITY
Explore all skills by this author →
GitHub

web-search

Performs real-time web searches via Playwright-controlled Chrome browser and returns Markdown-formatted results.

Updated Aug 27, 2026
Search Tags:#integration#real-time#playwright#web-search#browser-automation#markdown-output
One-click install
npx skills add https://github.com/fengzhizi319/LobsterAI --skill web-search-fengzhizi319
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: web-search
Source: https://github.com/fengzhizi319/LobsterAI/tree/main/SKILLs/web-search
Command: npx skills add https://github.com/fengzhizi319/LobsterAI --skill web-search-fengzhizi319

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires express, playwright-core, uuid, and includes scripts (resource) components.

What problem does it solve?

Real-time web search capability to retrieve current information beyond the knowledge cutoff by driving a real browser to search and gather results with visible, transparent operations.

Core Features & Use Cases

  • Real-time web searches with Google/Bing fallback to obtain current docs, news, and product information.
  • Transparent browser actions through a Playwright-controlled Chrome window for traceability.
  • Developer-friendly integration via CLI (scripts) and an HTTP API bridge for Claude workflows.

Quick Start

Start the bridge server, then run the CLI search script to perform a live web search.

Frequently Asked Questions about web-search

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

FAQPage Schema
How do I perform real-time web searches to retrieve current information beyond my knowledge cutoff?▼

Real-time web searches are performed by driving a Playwright-controlled Chrome instance to fetch current information, retrieving up-to-date documentation, recent news, and product comparisons with results rendered in Markdown.

Do I need a local Chrome instance and Playwright to automate web searches?▼

Yes, this web search approach requires a Playwright-backed bridge server, a local Chrome instance, and Electron-driven service management to coordinate searches and render results in Markdown.

Can I integrate real-time browser search results into my Claude workflows?▼

You can integrate real-time browser search results into Claude workflows via a developer-friendly HTTP API bridge and CLI scripts, enabling automated retrieval of current web data.

What is the best way to fetch up-to-date documentation and recent news using browser automation?▼

The best way to fetch up-to-date documentation and recent news is using transparent browser automation with Google and Bing fallbacks, ensuring visible operations and traceable search results.

Why does this browser automation approach render web search results in Markdown?▼

Rendering web search results in Markdown provides a developer-friendly output format that integrates seamlessly into Claude workflows and CLI scripts for current information retrieval.

What are the limitations of using a local Chrome instance for real-time web searches?▼

Limitations include requiring a local Chrome instance, a running Playwright bridge server, and Electron-driven service management, making this approach dependent on local browser availability and active service coordination.

Related Skills

Explore More Software Engineering Skills→
rhpdsrhpds

06-playwright-mcp

Configure and validate the Playwright MCP server for Claude Code browser automation.

Official
Advanced
ActiveInferenceInstituteActiveInferenceInstitute
30

gnn-parsing

Parse GNN Markdown files and serialize structured model data to JSON, YAML, and XML.

Community
Advanced
AradotsoAradotso
4

native-devtools-mcp-automation

Automate desktop apps, Chrome/Electron browsers, and Android devices via MCP server.

Official
Advanced
WhampWhamp
3

browser-tools

Control Chrome/Chromium instances via the DevTools protocol with six scripts.

Community
Advanced