Google Search Browser Use
Runs Google searches through a real browser session instead of hitting the API, which means it can reuse your existing login cookies and dodge most CAPTCHA walls. The setup walks you through installing browser-use via pip, then launching searches in real browser mode, clicking results, and extracting content. If parsing fails, it falls back to piping URLs through Jina AI's reader endpoint. Honestly most useful when you're already logged into Google and need to scrape a few results without getting blocked. The manual CAPTCHA solving step is a bit clunky, but that's the tradeoff for avoiding headless detection. Closes the session when done.
- skills.sh installs
- 1.9K
- GitHub stars
- 3
- last updated
- Aug 21, 2026
Install
$ npx -y skills add grasseed/google-search-browser-use --skill google-search-browser-use --agent claude-codeInstalls into .claude/skills of the current project.
Files
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:
-
Check Installation: Verify if
browser-useis available in the current PATH.which browser-use -
Install if Missing: If not found, install it using pip.
python3 -m pip install --user browser-use -
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:
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
browser-use --browser real open "https://www.google.com/search?q=YOUR+QUERY"
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/grasseed/google-search-browser-use
- Category
- Automation & Workflows
Recommended
More Automation & Workflows
ansible-automationaj-geddes/useful-ai-promptsInfrastructure automation and configuration management using Ansible playbooks, roles, and inventory. Use for deploying applications, patching, and managing ser1.9Kskills.sh installs
xiaohongshu-cover-generatorfreestylefly/xiaohongshu-skillsGenerate Xiaohongshu (小红书) style cover images based on user topics. Use when the user wants to create a social media cover image in Xiaohongshu style, or mentio1.9Kskills.sh installs
nemo-mbridge-perf-expert-parallel-overlapnvidia/skillsValidate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlap_moe_expert_parallel_comm, delay_wgrad_compute, and flex dispatc1.8Kskills.sh installsnemo-mbridge-perf-hierarchical-context-parallelnvidia/skillsOperational guide for enabling hierarchical context parallelism in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.1.8Kskills.sh installs
safe-browserbrowserbase/skillsBuild local constrained-browser agents with a safe_browser tool that owns CDP, enforces a domain allowlist with Fetch interception, and lets a runtime Claude Ag1.8Kskills.sh installs
landing-page-generatorkostja94/marketing-skillsWhen the user wants to create, optimize, or audit campaign landing pages for paid ads, email, or other traffic. Also use when the user mentions "landing page," 1.8Kskills.sh installs