skills.rest
mitsuhiko
mitsuhikoCOMMUNITY
Explore all skills by this author →
Website𝕏@mitsuhikoGitHub

web-browser

Control Chrome via DevTools Protocol to navigate, click, fill forms, and evaluate JavaScript.

2.8k|212|Updated Nov 2, 2025
Search Tags:#automation#navigation#web scraping#form filling#web browsing#puppeteer#chrome
One-click install
npx skills add https://github.com/mitsuhiko/agent-commands --skill web-browser-mitsuhiko
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: web-browser
Source: https://github.com/mitsuhiko/agent-commands/tree/main/skills/web-browser
Command: npx skills add https://github.com/mitsuhiko/agent-commands --skill web-browser-mitsuhiko

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires puppeteer-core, and includes scripts (resource) components.

What problem does it solve?

This Skill empowers Claude to interact with web pages far beyond simple browsing, overcoming the limitations of standard AI browser tools. It enables complex actions like filling out forms, clicking specific elements, and executing custom JavaScript, allowing for true web automation.

Core Features & Use Cases

  • Advanced Web Interaction: Perform intricate actions such as clicking buttons, filling out forms, and navigating links by remote controlling a Chrome or Chromium browser.
  • Dynamic Content Handling: Interact with dynamic web applications and authenticated sessions, making it ideal for tasks that require more than just static page analysis.
  • Use Case: Automatically log into a web portal, navigate to a specific report, extract data from tables, and then submit a form based on that data, all without manual intervention.

Quick Start

Using the web-browser skill, navigate to 'https://example.com' and take a screenshot of the page.

Frequently Asked Questions about web-browser

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

FAQPage Schema
How do I automate web browser interactions like clicking buttons and filling forms?▼

Web browser automation uses Chrome DevTools Protocol to remotely control a Chromium browser, enabling actions like clicking elements, filling form fields, and executing JavaScript. This requires a running Chrome/Chromium instance with remote debugging enabled on port 9222 and Puppeteer-core integration to orchestrate the interactions.

Can I use Puppeteer to scrape dynamic web content and extract data?▼

Yes. Puppeteer-core enables web scraping of dynamic content by navigating to URLs, waiting for elements to load, extracting links and text, and evaluating custom JavaScript. This handles authenticated sessions and single-page applications where static HTML parsing fails.

What setup is required to control a Chrome browser remotely for automation tasks?▼

Remote browser control requires a Chrome or Chromium instance running with the `--remote-debugging-port=9222` flag enabled. Puppeteer-core then connects via Chrome DevTools Protocol to perform navigation, element interaction, screenshot capture, and JavaScript evaluation without manual browser intervention.

How do I test web forms and user workflows programmatically?▼

Automate form testing by using remote browser control to navigate pages, fill input fields, click submit buttons, and capture results. This simulates human interaction patterns for end-to-end testing of login flows, multi-step forms, and conditional navigation.

Can I take screenshots and extract visual data from web pages during automation?▼

Yes. Remote browser control captures screenshots at any point in the automation workflow, enabling visual verification, data extraction from rendered content, and documentation of page states during navigation, form submission, and report generation.

What are the limitations of web browser automation with Chrome DevTools Protocol?▼

Browser automation requires a dedicated Chrome/Chromium process with remote debugging enabled and sufficient system resources. It cannot bypass authentication mechanisms outside the browser context and depends on stable network connectivity and page load performance for reliable interaction timing.

Related Skills

Explore More Software Engineering Skills→
eykdeykd

web-browser

Control Chrome/Chromium via Chrome DevTools Protocol for navigation, screenshots, JavaScript, and element inspection.

Community
Advanced
smarmen86smarmen86

scrape

Extract structured data and text content from web pages into JSON.

Community
Intermediate
pynbj1001pynbj1001
2

Smart Browser

Extract JavaScript-rendered web page agendas and session data to Markdown and JSON.

Community
Intermediate
josorio7122josorio7122

browser-tools

Automates web page interaction and data extraction through Chrome DevTools Protocol.

Community
Intermediate