agent-browser

Automate browser navigation, scraping, form submission, and element clicking with Puppeteer/Playwright.

Updated Mar 8, 2026
One-click install
npx skills add https://github.com/okenwa/claude-skills --skill agent-browser-okenwa
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/okenwa/claude-skills/tree/main/agent-browser
Command: npx skills add https://github.com/okenwa/claude-skills --skill agent-browser-okenwa

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates web browsing tasks, allowing you to navigate websites, extract content, fill forms, and interact with web elements without manual intervention.

Core Features & Use Cases

  • Website Navigation: Open and browse to any specified URL.
  • Content Scraping: Extract text and structured data from web pages.
  • Form Interaction: Fill out forms and click buttons or links.
  • Use Case: Automatically gather product pricing information from multiple e-commerce sites for a competitive analysis report.

Quick Start

Use the agent-browser skill to scrape the content from the website https://example.com.

Frequently Asked Questions about agent-browser

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

FAQPage Schema
How do I automate browser navigation and web scraping without manual intervention?

Automate browser navigation and web scraping by targeting specific URLs to extract structured data, fill forms, and click elements. This skill uses Puppeteer or Playwright to sequence interactions for automated data collection without manual input.

Can I use Puppeteer or Playwright for automated form filling and element clicking?

Yes, you can use Puppeteer or Playwright for automated form filling and element clicking. The skill automates these browser interactions by sequencing precise URL targeting and element interactions to simulate user interface actions.

What is the best way to extract text and structured data from web pages for competitive analysis?

The best way to extract text and structured data from web pages is through automated content scraping. This skill navigates to specified URLs like e-commerce sites and gathers product pricing information automatically for competitive analysis reports.

Does browser automation require precise URL targeting to execute interaction sequencing successfully?

Yes, browser automation requires precise URL targeting and interaction sequencing for successful execution. The skill relies on exact URL inputs to drive web navigation, form submission, and element clicking accurately without manual intervention.

Why does automated web data collection fail when interaction sequencing is not precise?

Automated web data collection fails without precise interaction sequencing because the browser automation cannot accurately target web elements. Successful content scraping, form submission, and element clicking depend on exact URL targeting and ordered interaction steps.