skills.rest
wayne930242
wayne930242COMMUNITY
Explore all skills by this author →
WebsiteGitHub

agent-browser

Automate browser tasks and extract data via CLI with ref-based element targeting.

Updated Aug 23, 2026
Search Tags:#automation#web-testing#browser#screenshot#form-filling#element-ref
One-click install
npx skills add https://github.com/wayne930242/Merlin-My-Pai --skill agent-browser-wayne930242
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/wayne930242/Merlin-My-Pai/tree/main/pai-claude/workspace/.claude/skills/agent-browser
Command: npx skills add https://github.com/wayne930242/Merlin-My-Pai --skill agent-browser-wayne930242

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates browser interactions to streamline testing, form filling, screenshot capture, and data extraction when you need to navigate websites, interact with pages, fill forms, take screenshots, test web applications, or extract information from web pages.

Core Features & Use Cases

  • Navigate pages, interact with elements via refs from snapshots, and perform deterministic actions.
  • Take screenshots, record interactions, and extract text or data for validation.
  • Use semantic locators and a wide range of browser controls (waits, frames, dialogs, network, etc.) to automate complex workflows.

Quick Start

Open a URL, snapshot the page to obtain element refs, and then automate interactions using those refs.

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 and form filling without flaky element selectors?▼

Automate web testing and form filling by taking a page snapshot to obtain element refs, then use those refs for deterministic browser interactions. This snapshot-based targeting ensures reliable execution without fragile CSS selectors.

Can I capture screenshots and extract data from web pages using CLI browser automation?▼

Yes, CLI browser automation supports capturing screenshots and extracting text or data from web pages. You navigate to a URL, snapshot the page, and perform interactions to gather information for validation.

What is the best way to handle complex UI automation workflows involving waits and frames?▼

Handle complex UI automation workflows by using semantic locators and a wide range of browser controls. The tool supports waits, frames, dialogs, and network interactions to automate deterministic actions across web pages.

Does browser automation via Bash tooling support assertions for web application testing?▼

Yes, browser automation via Bash tooling includes assertion support for web application testing. You can extract text or data from pages and validate it directly within your automated workflows to ensure deterministic task execution.

How do I start automating browser tasks to extract information across websites?▼

Start automating browser tasks by opening a URL and snapshotting the page to obtain element refs. Then use those refs to interact with elements, navigate pages, and extract information across websites deterministically.

Related Skills

Explore More Software Engineering Skills→
liuaibin001liuaibin001

automating-browsers

Automate browser interactions for AI agents using the agent-browser CLI.

Community
Advanced
u9401066u9401066

pdf-reader

Extract text, figures, and citations from PDFs into Markdown.

Community
Intermediate
NguyenvanleNguyenvanle

agent-browser

Drive browser automation for AI agents via CLI commands.

Community
Advanced
Casper-StudiosCasper-Studios
11

agent-browser

Automate browser interactions for web testing and data scraping.

Official
Advanced