web-pilot
Search the web and read page contents without API keys. Use when you need to search via DuckDuckGo/Brave/Google (multi-page), extract readable text from URLs, browse interactively with a persistent visible browser (with tabs, click, screenshot, text search), download files/PDFs, or dismiss cookie banners. Supports JSON/markdown/text output. Powered by Playwright + Chromium.
Why use this skill?
Learn how to use the OpenClaw web-pilot skill to perform web searches, extract page content, manage browser sessions, and download files without API keys.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/liranudi/web-pilotWhat This Skill Does
The web-pilot skill is a comprehensive browser automation suite designed for the OpenClaw AI agent. It allows the agent to interact with the live web using four distinct modular scripts, all powered by Playwright and Chromium. Unlike traditional AI tools that rely on expensive or rate-limited APIs, web-pilot provides a direct, low-level interface to the web, enabling search, page parsing, persistent browser sessions, and file downloading.
It features intelligent content extraction, allowing the agent to parse HTML into JSON, Markdown, or plain text. The persistent browser mode supports multi-tab management, screen capturing, element interaction (clicking/navigating), and text searching, making it an ideal choice for complex tasks that require authentication, multi-step navigation, or cookie banner management.
Installation
To install this skill, run the following command in your terminal:
clawhub install openclaw/skills/skills/liranudi/web-pilot
Ensure you have the required Python dependencies installed globally or in your agent's virtual environment:
pip install requests beautifulsoup4 playwright && playwright install chromium
Use Cases
- Research Automation: Aggregate search results from DuckDuckGo, Brave, or Google without needing an API key.
- Data Extraction: Scrape text, content, or specific data points from websites for processing by the AI agent.
- File Management: Automatically download and parse documents, including text extraction from PDFs using optional libraries like pdfplumber.
- Complex Web Workflows: Execute multi-step tasks such as logging into a portal, filling out forms, or navigating complex single-page applications using the persistent browser session.
- Testing: Perform visual verification of web pages via automated screenshots.
Example Prompts
- "Search for the latest documentation on OpenClaw features using Brave and list the top 3 URLs found."
- "Navigate to https://example.com, dismiss any cookie banners, extract the main content in Markdown format, and save a screenshot of the page."
- "Download the latest report from this URL (https://example.com/data.pdf) and summarize the extracted text for me."
Tips & Limitations
- Efficiency: Always prefer the one-shot
read_page.pyfor simple tasks to save resources. Reservebrowser_session.pyfor multi-step interactions. - Cookie Management: While the skill auto-dismisses most banners, some websites may require manual
dismiss-cookiescalls. - Performance: Ensure your environment has sufficient memory to handle multiple Chromium tabs, as overhead can increase with each open tab.
- Dependencies: If you frequently work with PDFs, installing
pdfplumberis highly recommended to enable built-in text parsing functionality.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-liranudi-web-pilot": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, file-write, file-read