skills.rest
sunzcdev
sunzcdevCOMMUNITY
Explore all skills by this author →
GitHub

agent-browser

Automate browser interactions to navigate websites and validate UI behavior.

Updated May 21, 2026
Search Tags:#data extraction#screenshots#browser automation#web testing#form filling#accessibility snapshot#network intercept
One-click install
npx skills add https://github.com/sunzcdev/archon-dev-team --skill agent-browser-sunzcdev
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/sunzcdev/archon-dev-team/tree/main/.claude/skills/agent-browser
Command: npx skills add https://github.com/sunzcdev/archon-dev-team --skill agent-browser-sunzcdev

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires node, chromium, and includes assets (resource) components.

What problem does it solve?

It removes the guesswork and repetition of manually clicking through websites for testing, data collection, and verification, so web-based work becomes faster and more consistent.

Core Features & Use Cases

  • Browser automation for QA: Open pages, navigate, interact with elements, and verify states like visibility, enabled/disabled, and checked/unchecked.
  • Deterministic element targeting: Take an accessibility snapshot to get stable element references, then click, fill, select, hover, scroll, and upload using those references.
  • Evidence capture & extraction: Take screenshots or full-page captures, and extract text, HTML, attributes, URLs, counts, and page titles for reporting and debugging.
  • Use Case: When you need to test a login + form submission flow on a web app, you can snapshot the interactive elements, fill inputs, click the submit button, wait for the next page to load, and then capture screenshots and extracted confirmation text.

Quick Start

Use agent-browser to open a page, snapshot interactive elements, then fill and submit a form using the returned element references.

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 testing to fill forms and capture screenshots?▼

You automate web testing by opening a page, taking an accessibility snapshot for stable element references, then using those references to fill inputs, click submit, wait for navigation, and capture confirmation screenshots.

What is an accessibility snapshot and how does it work for browser automation?▼

An accessibility snapshot provides deterministic element targeting for browser automation by returning stable references, which you then use to reliably click, fill, select, hover, and upload without fragile selectors.

Do I need Node and Chromium to run browser automation for web testing?▼

Yes, browser automation for web testing requires Node and Chromium installed to execute interactions, navigate pages, intercept network requests, and validate UI states.

Can I extract text, HTML, and attributes while scraping web pages?▼

Yes, you can extract text, HTML, attributes, URLs, counts, and page titles during web scraping by navigating sites and using accessibility snapshot references to reliably target and pull specific data.

How do I validate UI states like visibility or enabled and disabled elements?▼

You validate UI states by automating browser interactions to navigate the web app, interacting via snapshot references, and checking returned states for visibility, enabled or disabled, and checked or unchecked conditions.

What are the limitations of using accessibility snapshots for element targeting?▼

Accessibility snapshots require deterministic element selection, meaning dynamic content or elements lacking stable references might not be targeted reliably, so you should use wait commands to ensure page loads complete before snapshotting.

Related Skills

Explore More Software Engineering Skills→
HigorAlvesHigorAlves
4

agent-browser

Automate browser interactions for navigation, form filling, and data scraping via CDP.

Community
Intermediate
alibabaalibaba
10.5k

pdf-extractor

Extract text, tables, and metadata from PDF documents into JSON.

Official
Intermediate
serkan-ozalserkan-ozal
7

api-testing

Mock API responses and intercept HTTP requests in browser automation.

Community
Intermediate
spideynolovespideynolove
2

lightpanda

Fetch HTML content from web pages using a lightweight headless browser.

Community
Basic