skills.rest
pynbj1001
pynbj1001COMMUNITY
Explore all skills by this author →
GitHub

Agent Browser

Automate web interactions and extract structured data via CLI.

2|2|Updated Mar 1, 2026
Search Tags:#automation#screenshots#cli#browser#headless#web-scraping#form-filling
One-click install
npx skills add https://github.com/pynbj1001/agent-workspace --skill agent-browser-pynbj1001
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Agent Browser
Source: https://github.com/pynbj1001/agent-workspace/tree/main/skills/agent-browser
Command: npx skills add https://github.com/pynbj1001/agent-workspace --skill agent-browser-pynbj1001

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill enables programmatic browser control so agents and scripts can navigate pages, interact with elements, and extract structured data without manual browsing, reducing repetitive UI work and speeding automated testing or scraping tasks.

Core Features & Use Cases

  • Navigation & Interaction: Navigate, back, forward, reload, open/close tabs and windows, and interact with elements using stable refs for click, fill, type, hover, drag, and keyboard events.
  • Page Analysis & Data Extraction: Snapshot full accessibility trees or interactive elements to extract text, HTML, attributes, counts, bounding boxes, and other structured information for scraping or validation.
  • Media, Sessions & Network Control: Capture screenshots, PDF exports, video recordings, save/load session state, intercept and mock network requests, and configure viewport, device emulation, geolocation, and headers for robust testing and demos.
  • Use Case Example: Automate login and form submission across multiple sessions, record a demo of user flows, or run headless UI checks that produce JSON snapshots for downstream parsing.

Quick Start

Use Agent Browser to open https://example.com, snapshot interactive elements, fill the email and password fields using refs, click the submit button, and return the resulting page title.

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 extract structured data from web pages?▼

Automate web scraping by using headless browser automation to navigate pages, snapshot the accessibility tree or interactive elements, and extract text, HTML, and attributes into structured JSON output for downstream parsing.

How do I automate form filling and element interaction for UI testing?▼

Automate form filling by taking a snapshot of interactive elements to get stable refs, then use those refs to programmatically click, fill, type, hover, drag, and trigger keyboard events for UI validation.

Can I capture screenshots and PDF exports during headless browser automation?▼

Yes, headless browser automation supports capturing screenshots, exporting PDFs, and recording video of user flows, alongside configuring viewport, device emulation, and geolocation for robust testing and demos.

Do I need node and npm to run headless browser automation scripts?▼

Yes, you need node and npm installed, along with the agent-browser binary, to execute CLI-based browser control, manage session isolation, and output structured JSON from your automation tasks.

Does headless browser automation support session isolation and network mocking?▼

Yes, headless browser automation provides session isolation by saving and loading session state, and allows you to intercept and mock network requests for controlled testing and scraping environments.

What is the best way to automate login and form submission across multiple sessions?▼

Automate logins by opening the target URL, snapshotting interactive elements, filling credentials using stable refs, clicking submit, and leveraging save/load session state to persist authentication across multiple sessions.

Related Skills

Explore More Software Engineering Skills→
Wike-CHIWike-CHI
2

acquisition-dependencies

Install and configure Python, npm, and Playwright dependencies across Linux, macOS, WSL2, and Windows.

Community
Intermediate
disusereddisusered

jq

Parse, filter, and transform JSON data with jq queries.

Community
Intermediate
pleaseaipleaseai

chrome-devtools-cli-usage

Automate Chrome browser tasks using Chrome DevTools CLI commands.

Official
Intermediate
alangebalangeb

agent-browser

Automate web browser navigation, form submission, and DOM manipulation via Playwright.

Community
Advanced