skills.rest
papachong
papachongCOMMUNITY
Explore all skills by this author →
GitHub

Agent Browser

Automate headless browser interactions and extract structured data from web pages.

2|Updated Apr 4, 2026
Search Tags:#automation#testing#browser#headless#web-scraping#form-filling#agent-browser
One-click install
npx skills add https://github.com/papachong/RHClaw --skill agent-browser-papachong
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Agent Browser
Source: https://github.com/papachong/RHClaw/tree/main/RHClaw-Desktop/src-tauri/skills/agent-browser
Command: npx skills add https://github.com/papachong/RHClaw --skill agent-browser-papachong

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill lets developers and automation engineers programmatically navigate pages, interact with UI elements, and extract structured information from websites, eliminating manual clicking and fragile ad-hoc scraping.

Core Features & Use Cases

  • Headless Browser Automation: Navigate pages, snapshot DOM/accessibility elements, and perform clicks, typing, uploads, and mouse actions using stable refs.
  • Structured Extraction & Testing: Extract text, HTML, attributes, and counts; capture screenshots and videos; and run UI checks or form submissions for QA and scraping tasks.
  • Session & Network Control: Manage isolated sessions, save and load session state, intercept and mock network requests, and emulate devices or viewport settings.
  • Use Case: Automate a login flow, extract dashboard data into JSON, and record a demonstration video for debugging or QA verification.

Quick Start

Use Agent Browser to open a URL, snapshot interactive refs, fill the login fields, click the submit button, and save the session state.

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?▼

Headless browser automation allows you to navigate web pages, snapshot interactive elements, and perform actions like form filling and clicks. You can extract structured data into JSON and capture screenshots while running entirely without a graphical interface.

What do I need to run headless browser automation tasks for UI testing?▼

To run headless browser automation tasks, you need the agent-browser CLI installed alongside Node.js and npm. This environment supports taking DOM snapshots, executing UI checks, and recording demonstration videos for QA verification.

Can I manage isolated sessions and intercept network requests during web scraping?▼

Yes, you can manage isolated sessions to save and load session state for continuous interactions. The automation supports intercepting and mocking network requests while emulating specific devices or viewport settings.

How do I extract structured data from web pages into JSON?▼

You extract structured data from web pages by navigating to the URL, snapshotting the DOM or accessibility elements, and pulling specific text, HTML attributes, or element counts. The output is formatted as structured JSON for immediate downstream use.

Does headless browser automation support recording videos for debugging?▼

Headless browser automation supports recording interactions and capturing screenshots. You can record a demonstration video of your automated login flow or UI testing sequence for direct debugging and QA verification.

When should I use snapshot refs instead of direct selectors for web automation?▼

Use snapshot refs when you need to interact with UI elements like clicks, typing, or uploads using stable references. This approach prevents fragile ad-hoc scraping by relying on structured accessibility snapshots rather than hardcoded selectors.

Related Skills

Explore More Software Engineering Skills→
letitbkletitbk

playwright

Automate browser navigation, interaction, and data capture via command-line scripts.

Community
Intermediate
profmikegreeneprofmikegreene
1

plan-ingestion

Parses pilot plans and hypotheses into structured JSON or tabular data for downstream analysis.

Community
Intermediate
aresbitaresbit
46

agent-browser

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

Community
Intermediate
Mathews-TomMathews-Tom
310

lightpanda-browser

Automate DOM interactions and data extraction via Lightpanda CDP.

Community
Intermediate