web-search

Execute live web searches via Playwright-controlled Chrome and return Markdown result summaries.

1|Updated May 13, 2026
One-click install
npx skills add https://github.com/wtgoku-create/PopiStudio --skill web-search-wtgoku-create
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: web-search
Source: https://github.com/wtgoku-create/PopiStudio/tree/main/SKILLs/web-search
Command: npx skills add https://github.com/wtgoku-create/PopiStudio --skill web-search-wtgoku-create

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill solves the problem of outdated or cutoff knowledge by enabling real-time web searches and summarizing current information from the live web.

Core Features & Use Cases

  • Real-time web search: Retrieve current results (Google with Bing fallback) for questions about recent events, latest docs, and fast-moving topics.
  • Transparent browser automation: Uses a visible Playwright-controlled Chrome instance so actions are observable.
  • Markdown-ready outputs: Returns search results formatted for fast extraction and synthesis, with optional API access for deeper workflows.

Quick Start

Run the web-search skill by asking it to search a current topic and return a concise, cited summary based on the latest results, for example: bash "$SKILLS_ROOT/web-search/scripts/search.sh" "React 19 new features" 5

Frequently Asked Questions about web-search

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

FAQPage Schema
How do I get current information for technical troubleshooting when my knowledge base is outdated?

Real-time web search resolves outdated knowledge by executing live web searches and returning structured Markdown summaries with titles, URLs, and snippets for technical troubleshooting discovery. It uses a Playwright-controlled Chrome browser to retrieve current information.

Can I use Playwright browser automation to extract live search results with source citations?

Yes, Playwright browser automation controls a visible Chrome instance to execute live web searches and extract results. It returns Markdown-formatted outputs containing titles, URLs, snippets, and timing metadata with source citations for research transparency.

Does the web search skill support engine fallback logic for research tasks?

Yes, the web search skill implements engine fallback logic by defaulting to Google and falling back to Bing. This ensures consistent research results for tasks like latest documentation lookup, recent news research, and comparison research across versions.

What is the best way to research fast-moving topics and latest documentation across different ecosystems?

Executing live web searches via a bash CLI orchestration script is the best way to research fast-moving topics. It queries current information and returns concise, cited summaries based on the latest results extracted from the live web.

Do I need a localhost HTTP bridge server to run web searches for real-time research?

Yes, you need a Playwright-controlled Chrome browser, an HTTP bridge server on localhost, and bash CLI orchestration to execute live web searches. These components work together to return structured Markdown summaries of current information.

Why are my web search results not returning current information for recent events?

Without a live web search mechanism, knowledge bases remain cutoff and outdated. Executing live web searches with engine fallback logic via a Playwright-controlled browser ensures you retrieve current results for recent events and fast-moving topics.