skills.rest
sylvanding
sylvandingCOMMUNITY
Explore all skills by this author →
Website𝕏@sylvandingGitHub

agent-browser

Automate web navigation, form filling, scraping, and screenshots via headless browser CLI.

9|Updated Mar 9, 2026
Search Tags:#data extraction#cli#browser automation#web scraping#form filling#screenshot capture#headless browser
One-click install
npx skills add https://github.com/sylvanding/omelette --skill agent-browser-sylvanding
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/sylvanding/omelette/tree/main/.claude/skills/agent-browser
Command: npx skills add https://github.com/sylvanding/omelette --skill agent-browser-sylvanding

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Manually browsing websites to complete repetitive tasks like form filling, data scraping, screenshot capture, or login flows is time-consuming, error-prone, and impossible to scale for large volumes of work.

Core Features & Use Cases

  • Ref-Based Element Selection: Uses accessibility snapshot refs (@e1, @e2) for stable, reliable element targeting that avoids broken selectors from dynamic page content changes.
  • Comprehensive Browser Actions: Supports navigation, form filling, clicking, scrolling, text/HTML extraction, full page or viewport screenshots, and PDF generation for any web page.
  • Use Case: For example, you can use this skill to automatically log into a research database, search for papers matching your keywords, and export all result titles and URLs to a CSV file without manual clicking or copying.

Quick Start

Use the agent-browser skill to navigate to your target job board, fill the search bar with "remote software engineer", and scrape all matching job titles, companies, and application links into a structured list.

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 and form filling without writing complex scripts?▼

You can automate web scraping and form filling using simple CLI commands to control a headless browser. This handles repetitive navigation, clicking, and data extraction reliably without complex scripting, outputting structured JSON.

How does a headless browser handle dynamic page content during web automation?▼

A headless browser handles dynamic content using accessibility snapshot refs like @e1 or @e2 for element targeting. This ref-based selection ensures stable interactions and avoids broken selectors when page content changes dynamically.

Can I run parallel browsing sessions for concurrent web scraping tasks?▼

Yes, you can run parallel browsing sessions to handle concurrent web scraping tasks. This feature supports executing multiple automated browsing workflows simultaneously, increasing throughput for bulk data extraction or testing.

What is the best way to extract public website data into a structured format?▼

The best way to extract public website data is using a CLI headless browser that outputs structured JSON. It automates navigation and text or HTML extraction, allowing you to easily parse and integrate scraped data.

Does this browser automation tool support visual page verification and screenshots?▼

Yes, this browser automation tool supports visual page verification by capturing full page or viewport screenshots and generating PDFs. This allows you to visually inspect and verify web pages during automated testing workflows.

Related Skills

Explore More Software Engineering Skills→
hemoryhemory

agent-browser

Displays a list of available commands for the specified tool.

Community
Intermediate
maxvaegamaxvaega
146

json-parser

Parse and validate JSON data against schemas and JSONPath queries.

Community
Intermediate
CatsofsufferingCatsofsuffering
5

data-engineering

Manage and validate data pipelines and streaming workflows across orchestration and quality tools.

Community
Advanced
olostepolostep

batch

Scrape up to 10,000 URLs in parallel with configurable output formats.

Community
Intermediate