Google Search Browser Use
Install this when you need live Google results through a real browser session—competitor lookups, current docs, or answers that static APIs block.
Overview
Google-search-browser-use is an agent skill most often used in Idea research (also Validate competitors and Launch SEO spot checks) that performs Google searches and page extraction via browser-use real-browser sessions.
Install
npx skills add https://github.com/grasseed/google-search-browser-use --skill google-search-browser-useWhat is this skill?
- Runs Google search via browser-use in real browser mode to reuse logged-in sessions and reduce CAPTCHAs
- Prerequisite checks: which browser-use, pip install --user browser-use, resolve user-base bin path
- Opens result URLs and extracts snippets or full page content from live pages
- Explicit open command pattern: browser-use --browser real open Google search URL
- Fallback explicit-path execution when standard PATH invocation fails
- 3 prerequisite steps: check which, pip install --user, locate user-base bin
Adoption & trust: 1.8k installs on skills.sh; 3 GitHub stars; 0/3 security scanners passed (skills.sh audits).
What problem does it solve?
You need current Google results and page text but API-only or headless flows get blocked or return stale summaries.
Who is it for?
Indie builders who already run Python locally and want the agent to mirror manual Google research without fighting CAPTCHAs.
Skip if: High-volume programmatic SEO scraping, air-gapped environments without browser-use, or teams that forbid shell and browser automation.
When should I use this skill?
User asks to search Google, look this up on Google, or needs current web results via a real browser session (often to avoid bot blocks).
What do I get? / Deliverables
After setup checks, the agent opens a real-browser Google search, follows results, and returns extracted snippets or page content from live URLs.
- Google SERP opened in real browser mode
- Extracted snippets or key content from selected result pages
- Documented install path when using explicit binary execution
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Idea research is the first place builders explicitly need open-web discovery before committing to a product direction. Research subphase covers competitive and factual lookups that browser-use on Google is optimized to satisfy.
Where it fits
Run a real-browser Google query to collect current pricing pages for adjacent tools before picking a niche.
Spot-check how your target keyword renders on Google today before publishing a positioning article.
Pull fresh statistics or announcement pages to cite in a newsletter draft the agent is helping write.
How it compares
Browser CLI workflow for human-like search—not a managed SERP API or Prism marketplace server.
Common Questions / FAQ
Who is google-search-browser-use for?
Solo builders and agent users who need trustworthy live web answers from Google using browser-use on their own machine.
When should I use google-search-browser-use?
In Idea research for market facts; in Validate for competitor pages; in Launch for quick SERP checks; whenever the user says search Google or needs current web results via a real browser.
Is google-search-browser-use safe to install?
It runs shell commands and drives a real browser with network access; review the Security Audits panel on this Prism page and treat logged-in session reuse as a trust decision.
SKILL.md
READMESKILL.md - Google Search Browser Use
# Google Search Browser Use ## Overview Run Google searches with `browser-use` (prefer real browser mode), open results, and extract the relevant snippets or page content. This skill leverages the user's existing browser session to reduce CAPTCHAs. ## Prerequisites Before running the search, ensure the environment is ready: 1. **Check Installation**: Verify if `browser-use` is available in the current PATH. ```bash which browser-use ``` 2. **Install if Missing**: If not found, install it using pip. ```bash python3 -m pip install --user browser-use ``` 3. **Locate Binary**: If the command is still not found after installation, it is likely in the user's local bin directory. Retrieve the path dynamically: ```bash python3 -m site --user-base # The binary is typically at <USER_BASE>/bin/browser-use ``` ## Workflow ### 1) Launch a Google search (Real Browser Mode) Use the real browser to reuse the user’s logged-in session. **Option A: Standard Execution** ```bash browser-use --browser real open "https://www.google.com/search?q=YOUR+QUERY" ``` **Option B: Explicit Path Execution** If Option A fails (command not found), use the full path found in Prerequisites: ```bash # Example (adjust based on 'python3 -m site --user-base' output): ${HOME}/Library/Python/3.14/bin/browser-use --browser real open "https://www.google.com/search?q=YOUR+QUERY" ``` *(Note: Replace `3.14` with your current Python version if different)* ### 2) Inspect results and parse Once the browser is open: ```bash # Check current page state browser-use --browser real state # Click on a search result (use index from state output) browser-use --browser real click <index> ``` ### 3) Extract or Summarize - **Goal**: Provide a short summary (3-6 bullets) with source citations. - **Fallback**: If `browser-use` struggles with parsing, use `curl` with Jina AI for a text-friendly version: ```bash curl -L "https://r.jina.ai/https://example.com" ``` ### 4) Close the Session ```bash browser-use close ``` ## Troubleshooting - **CAPTCHAs**: If encountered, solve them manually in the open browser window. - **Path Issues**: If `browser-use` cannot be called directly, always prefer finding the path via `python3 -m site --user-base` rather than guessing. - **Connection**: Ensure no VPN/Proxy is blocking Google results if timeouts occur.