skills.rest
ximing
ximingCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

agent-browser

Automate browser navigation, form filling, and data extraction via CDP.

Updated Mar 14, 2026
Search Tags:#data extraction#browser automation#web testing#web scraping#form filling#headless browser
One-click install
npx skills add https://github.com/ximing/echoe --skill agent-browser-ximing
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/ximing/echoe/tree/main/.claude/skills/vercel.agent-browser
Command: npx skills add https://github.com/ximing/echoe --skill agent-browser-ximing

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates browser interactions, allowing you to navigate websites, fill forms, extract data, and perform complex web-based tasks programmatically, eliminating manual browsing.

Core Features & Use Cases

  • Web Navigation: Open any URL, navigate through pages, and handle redirects.
  • Form Interaction: Fill text fields, select dropdowns, check boxes, and submit forms.
  • Data Extraction: Scrape text content, element attributes, and structured data from web pages.
  • Screenshots & PDFs: Capture full-page screenshots or save pages as PDFs for documentation or analysis.
  • Authentication: Handle logins, manage sessions, and reuse authentication states across runs.
  • Use Case: Automate the process of logging into a web application, filling out a multi-step form, and then extracting the final confirmation details into a report.

Quick Start

Use the agent-browser skill to open the website 'https://example.com' and take a full-page screenshot.

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 with a headless browser?▼

You can automate web scraping and form filling by using the command-line interface to drive a headless Chrome/Chromium browser via CDP. This enables programmatic navigation, text extraction, and automated form submission for deterministic task execution.

Can I reuse authenticated sessions for browser automation across multiple runs?▼

Yes, you can manage authenticated browsing by handling logins and reusing session states across multiple runs. This allows the browser automation to maintain authenticated access without needing to repeat the login process for every task execution.

Does this browser automation tool support screenshots and PDF generation?▼

Yes, the browser automation tool supports capturing full-page screenshots and saving web pages as PDFs. This allows you to generate visual documentation or archive web content directly during your automated navigation tasks.

What is the best way to extract structured data from web pages programmatically?▼

The best way to extract structured data is by using the command-line interface to scrape text content and element attributes from web pages. It integrates with headless Chrome to provide deterministic data extraction results without manual browsing.

Do I need to install specific browser dependencies to run headless web testing tasks?▼

You need a compatible headless Chrome or Chromium environment to execute web testing tasks. The skill connects to the browser via the Chrome DevTools Protocol (CDP) to enable deterministic task execution, navigation, and interaction.

Related Skills

Explore More Software Engineering Skills→
apollostreetcompanyapollostreetcompany

agent-browser

Automate browser navigation, form interaction, screenshots, and data scraping via CDP.

Community
Advanced
K-Dense-AIK-Dense-AI
33.0k

flowio

Parse FCS files and extract event data as NumPy arrays.

Official
Intermediate
TTT1231TTT1231

agent-browser

Automate browser navigation, form filling, and data extraction for web tasks.

Community
Advanced
richardnguyen0715richardnguyen0715

scrapling

Scrape static and JavaScript-rendered web content with stealth and Cloudflare bypass.

Community
Advanced