browser

Automate interactive and one-shot web browsing with CAPTCHA solving and email verification.

Updated Jan 29, 2026
One-click install
npx skills add https://github.com/benjgrad/clawdbot --skill browser-benjgrad
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: browser
Source: https://github.com/benjgrad/clawdbot/tree/main/skills/browser
Command: npx skills add https://github.com/benjgrad/clawdbot --skill browser-benjgrad

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python3, anthropic, playwright, python-dotenv, browser-_use, browser-utils, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates web browsing tasks, including complex interactions, CAPTCHA solving, and email verification, reducing the need for manual navigation and data entry.

Core Features & Use Cases

  • Interactive Browsing: Engage in multi-step web interactions with an AI agent that maintains context across messages.
  • One-Shot Tasks: Execute single, defined web actions like fetching specific data or navigating to a URL.
  • CAPTCHA Solving: Automatically handles various CAPTCHA challenges (reCAPTCHA, hCaptcha, Turnstile).
  • Email Verification: Polls Gmail for verification codes or accepts manually entered codes.
  • Use Case: Automatically log into a web portal, fill out a form, and submit it, even if it requires solving a CAPTCHA.

Quick Start

Use the browser skill to go to example.com and return the page title.

Frequently Asked Questions about browser

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

FAQPage Schema
How do I automate web browsing tasks with an AI agent?

AI agent web automation is executed through an interactive browser that maintains context across multi-step interactions or runs single, defined one-shot commands to fetch data and navigate URLs.

Can I automatically solve CAPTCHAs during web automation?

CAPTCHA solving is fully supported during web automation, automatically handling various challenges including reCAPTCHA, hCaptcha, and Turnstile without requiring manual user intervention.

How does email verification work for automated web interactions?

Email verification is handled by polling Gmail for verification codes automatically, or by accepting manually entered codes, enabling automated login and form submission workflows.

Do I need Python and an Anthropic API key to run interactive browsing?

Interactive browsing requires Python 3 and the ANTHROPIC_API_KEY environment variable to facilitate LLM interaction, alongside specific dependencies like Playwright and browser-use.

What is the difference between persistent sessions and one-shot web browsing?

Persistent sessions allow an AI agent to engage in multi-step interactive web browsing while maintaining context, whereas one-shot tasks execute a single defined web action like fetching specific data.

What are the limitations of using an AI agent for web automation?

Web automation limitations include dependency on external environment variables like ANTHROPIC_API_KEY for LLM interaction, and the necessity of Python 3 with specific dependencies for execution.