skills.rest
antgroup
antgroupOFFICIAL
Explore all skills by this author →
Website𝕏@antgroupGitHub

web-pilot

Automate web searches and extract page content via Playwright and Chromium.

16|1|Updated May 21, 2026
Search Tags:#data extraction#browser automation#search#web scraping#web browsing#playwright
One-click install
npx skills add https://github.com/antgroup/Agent3Sigma-Stage --skill web-pilot-antgroup
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: web-pilot
Source: https://github.com/antgroup/Agent3Sigma-Stage/tree/main/data/advance/skill_templates/Web_Browsing/benign_skills/liranudi_web-pilot
Command: npx skills add https://github.com/antgroup/Agent3Sigma-Stage --skill web-pilot-antgroup

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, beautifulsoup4, playwright, Pillow, pdfplumber, and includes scripts (resource) components.

What problem does it solve?

This skill solves the challenge of gathering information from the web and interacting with sites without needing complex API keys or manual browser navigation.

Core Features & Use Cases

  • Multi-Engine Search: Perform searches across DuckDuckGo, Brave, and Google to aggregate results.
  • Persistent Browser Sessions: Maintain stateful browsing sessions to handle multi-step interactions like logging in, filling forms, or clicking through tabs.
  • Content Extraction: Convert complex web pages into clean JSON, markdown, or plain text, including automated cookie banner dismissal.

Quick Start

Use the web-pilot skill to search for the latest documentation on a topic and extract the content from the top result into a markdown file.

Frequently Asked Questions about web-pilot

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate web scraping and extract page content without API keys?▼

Automated web scraping without API keys is achieved by driving headless or visible Chromium sessions via Playwright, extracting page content into clean JSON, markdown, or plain text.

Can I maintain stateful browser sessions for multi-step interactions like logging in?▼

Persistent browser sessions support multi-step interactions like logging in, filling forms, or clicking through tabs by maintaining stateful web navigation across diverse platforms.

What is the best way to perform multi-engine searches and aggregate web results locally?▼

Multi-engine search aggregation is performed locally across DuckDuckGo, Brave, and Google to gather and extract web data without relying on external search APIs.

Does browser automation with Playwright handle cookie banner dismissal during content extraction?▼

Browser automation with Playwright includes automated cookie banner dismissal during content extraction to ensure clean, structured data retrieval from complex web pages.

How do I convert complex web pages into markdown or plain text?▼

Complex web pages are converted into markdown or plain text through local content extraction processes that transform raw HTML into structured, readable formats.

Do I need external API keys to extract web data and perform automated web searching?▼

No external API keys are required to extract web data and perform automated searching, as the process facilitates local data gathering and task automation directly through browser sessions.

Related Skills

Explore More Data & Analytics Skills→
26mitch2626mitch26

setup-browser-cookies

Import cookies from a Chromium browser into Playwright headless sessions.

Community
Basic
disusereddisusered

jq

Parse, filter, and transform JSON data with jq queries.

Community
Intermediate
cici

pdf

Extract text and tables from PDFs using pypdf, pdfplumber, and reportlab.

Community
Intermediate
otrebuotrebu
4

web-to-markdown

Batch-convert JavaScript-rendered web pages to a timestamped Markdown file.

Community
Advanced