skills.rest
cribclaw
cribclawCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

agent-browser

Automate web browsing, element interaction, and data extraction via CLI.

Updated Feb 26, 2026
Search Tags:#testing#data extraction#form filling#web automation#scraping#browser
One-click install
npx skills add https://github.com/cribclaw/cribclaw --skill agent-browser-cribclaw
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/cribclaw/cribclaw/tree/main/container/skills/agent-browser
Command: npx skills add https://github.com/cribclaw/cribclaw --skill agent-browser-cribclaw

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill automates web browsing tasks, allowing for research, interaction with web applications, form filling, and data extraction without manual intervention.

Core Features & Use Cases

  • Web Navigation: Open URLs, go back/forward, reload pages.
  • Element Interaction: Click, fill forms, type, hover, check/uncheck, select dropdowns.
  • Data Extraction: Get text, HTML, attributes, titles, URLs, and count elements.
  • Screenshots & PDF: Capture screenshots of full pages or specific areas, and save pages as PDFs.
  • Authentication: Save and load browser states for seamless login persistence.

Quick Start

Use the agent-browser skill to open the URL 'https://www.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 web form filling and data extraction without manual intervention?▼

Web automation allows you to automate web form filling and data extraction through a command-line interface, enabling navigation and element manipulation without manual intervention. You can fill forms, click elements, and extract text or HTML attributes directly.

Can I save browser authentication states for web automation to avoid manual logins?▼

Yes, you can save and load browser authentication states for seamless login persistence. This enables you to maintain authenticated sessions for web application testing and data scraping tasks without repeatedly logging in manually.

How do I capture screenshots or save web pages as PDFs during web scraping?▼

To capture screenshots or save web pages as PDFs during web scraping, use automation commands to generate full page or specific area screenshots. You can also save the web pages directly as PDF files for later review.

What is the best way to interact with web page elements like dropdowns and checkboxes programmatically?▼

The best way to interact with web page elements programmatically is using semantic locators to target dropdowns, checkboxes, and buttons. This enables precise clicking, hovering, typing, and selecting within automated web browsing tasks.

Does web automation support extracting specific text and HTML attributes from web pages?▼

Yes, web automation supports extracting specific text and HTML attributes from web pages. You can get text, HTML, attributes, titles, URLs, and count elements directly through command-line interface instructions for efficient data scraping.

Related Skills

Explore More Software Engineering Skills→
rafaelcallejarafaelcalleja
2

gemini-cli

Interact with Gemini AI models through a command-line interface.

Community
Intermediate
marcoamumarcoamu
1

data_exporter

Export data from databases or files into CSV, JSON, Markdown, or HTML formats.

Community
Intermediate
secondskysecondsky
204

firecrawl-scraper

Fetch web page content and transform it into Markdown using the Firecrawl v2.5 API.

Community
Advanced
phanijappsphanijapps
1

light-panda-browser

Automate web scraping and data extraction with the Lightpanda headless browser.

Community
Intermediate