Setup & Installation
openclaw skills install @itzsubhadip/stealthy-google-search
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
npx clawhub install stealthy-google-search
What This Skill Does
Runs Google searches using Scrapling's stealth browser fetcher and returns the top result titles and URLs. Ships a self-contained install script that sets up a local Python venv with Scrapling and Playwright browsers. Output can be plain text or JSON.
Uses a stealth browser fetcher to reduce the chance of blocks that affect standard HTTP-based scrapers.
When to use it
- Scraping Google search results from a script or agent
- Fetching top links for a keyword without using the official Search API
- Automating research queries that return structured URL lists
- Comparing search results across regions using --gl and --hl flags
- Feeding search results into a downstream pipeline as JSON
Example Workflow
Here's how your AI assistant might use this skill in practice.
INPUT
User asks: find the top 5 links for 'open source LLM frameworks' in English
AGENT
- 1Run install.sh to set up the venv and Playwright browsers if not already done
- 2Execute google_search.py with --query 'open source LLM frameworks' --top 5 --hl en
- 3Parse the printed output or capture JSON with --json flag
- 4Return the list of titles and URLs to the user
OUTPUT
A list of 5 result titles and their corresponding Google search URLs
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.
Python 3.10 or higherDisk space for Playwright browser binaries (downloaded during install)