skills.rest
SLEEPYBQ
SLEEPYBQCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

agent-browser

Automate headless browser operations for web data retrieval and interaction.

Updated Aug 23, 2026
Search Tags:#browser automation#session management#web scraping#AI workflows#headless browsing#ref-based interaction
One-click install
npx skills add https://github.com/SLEEPYBQ/adaptive-rehearsal --skill agent-browser-sleepybq
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/SLEEPYBQ/adaptive-rehearsal/tree/main/WildClawBench/skills/agent-browser
Command: npx skills add https://github.com/SLEEPYBQ/adaptive-rehearsal --skill agent-browser-sleepybq

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill enables automated, headless web browser interactions, streamlining repetitive navigation and data extraction tasks for AI agents.

Core Features & Use Cases

  • Web Automation: Navigate, interact, and extract information from websites programmatically.
  • Complex Workflows: Automate multi-step processes such as form submissions, searches, and data gathering.
  • Use Case: An AI agent needs to scrape product prices from multiple e-commerce pages; this Skill performs navigation, captures snapshots, and retrieves structured data seamlessly.

Quick Start

Use the agent-browser to open a URL, take a snapshot, and extract page title for analysis.

Frequently Asked Questions about agent-browser

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

FAQPage Schema
How do I automate web scraping for an AI workflow using a headless browser?▼

Automating headless browser operations for web scraping involves programmatically navigating URLs, taking snapshots, and extracting structured data to feed directly into AI workflows. This Skill manages multi-step navigation and captures page elements seamlessly for analysis.

Can I manage browser sessions and control network requests during web automation?▼

Yes, session management and network control are supported during web automation. You can maintain browser states across multiple interactions, allowing AI agents to execute complex, multi-step workflows like form submissions without losing context.

How does ref-based element interaction work for automated browser tasks?▼

Ref-based interaction targets specific page elements by their references during automated browser tasks. This mechanism allows AI agents to programmatically click buttons, fill forms, and extract data from precise DOM components without relying on brittle CSS selectors.

What is the best way to scrape product prices from multiple e-commerce pages programmatically?▼

The best way to scrape product prices programmatically is using headless browsing to navigate multiple e-commerce pages sequentially. This Skill performs automated navigation, captures page snapshots, and retrieves structured pricing data for immediate AI analysis.

Do I need Puppeteer or similar libraries to use this browser automation Skill?▼

Yes, you need Puppeteer or similar libraries to utilize this browser automation Skill. It requires these underlying dependencies to execute headless browser operations, manage sessions, and perform ref-based element interactions for web data retrieval.

What are the limitations of using headless browsing for web data extraction?▼

Limitations of headless browsing for web data extraction include potential detection by anti-bot systems and inability to process dynamic content requiring complex rendering. This Skill is suited for testing and scraping but may face constraints with heavily protected sites.

Related Skills

Explore More Content & Communication Skills→
AIDotNetAIDotNet
84

puppeteer

Automate headless Chrome tasks for PDF generation, screenshots, and web scraping.

Official
Intermediate
lvhuanidlvhuanid

web-reader

Extract text, HTML, and metadata from web pages using z-ai-web-dev-sdk.

Community
Intermediate
serkan-ozalserkan-ozal
7

api-testing

Mock API responses and intercept HTTP requests in browser automation.

Community
Intermediate
marktantongcomarktantongco

fetch

Fetch HTML or JSON from static web pages with redirect and proxy control.

Community
Basic