Search Google via Chrome and extract full-page content as text or JSON.
npx skills add https://github.com/sr-ai-dev/sr-harness --skill google-search-sr-ai-dev
Please help me install this Agent Skill. Skill: google-search Source: https://github.com/sr-ai-dev/sr-harness/tree/main/skills/google-search Command: npx skills add https://github.com/sr-ai-dev/sr-harness --skill google-search-sr-ai-dev
It solves the problem of getting reliable web results with complete, readable page content instead of short snippets, especially when sites require JavaScript rendering.
site: filtering, time filtering (day/week/month/year), and limiting results to control runtime.Use the google-search skill to search Google for "react server components best practices" and return enriched results for the top 5 pages.
High-intent search queries and answers about installing and using this skill.
To extract full page content instead of short snippets, this skill uses a real Chrome browser to visit result pages and pull structured data including title, author, tags, and body text, ensuring complete readable content even from JavaScript-rendered sites.
Yes, you can get JSON output from a Google web search. The tool can produce raw JSON or enriched human-readable text, allowing you to extract the body and comments from result pages for structured data processing.
Browser-based web search uses a real Chrome instance to mirror what a human sees, which reduces bot-detection issues. If the browser environment is unavailable, it automatically falls back to the built-in WebSearch tool.
You can filter Google search results by time and specific sites using built-in controls. The search supports site scoping with site: filtering, time filtering by day, week, month, or year, and result limits to match your query intent.
A key limitation of using Chromium automation for web content extraction is performance overhead, as visiting pages takes time. You can control runtime by limiting results, and if the browser is inaccessible, it falls back to standard WebSearch.
XinheLIUOperate a persistent headless Chromium browser for QA testing and site dogfooding.
profmikegreeneParses pilot plans and hypotheses into structured JSON or tabular data for downstream analysis.
InverterNetworkScrape data from anti-bot-protected websites using browser impersonation.
djnsty23Automates browser tasks via a Rust CLI with a Node.js daemon and Playwright backend.