agent-browser

Automate browser navigation, DOM interaction, and content extraction via a CLI daemon.

1|Updated Apr 12, 2026
One-click install
npx skills add https://github.com/cryptopafi/nexusos-skills --skill agent-browser-cryptopafi
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/cryptopafi/nexusos-skills/tree/main/agent-browser
Command: npx skills add https://github.com/cryptopafi/nexusos-skills --skill agent-browser-cryptopafi

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Provides a reliable CLI-driven browser automation workflow to eliminate manual web interactions such as logging in, filling forms, taking screenshots, extracting dynamic content, and end-to-end UI testing that require a real browser environment.

Core Features & Use Cases

  • Navigate and interact: Open pages, snapshot interactive refs, click, fill, select, and type to drive complex UI flows.
  • Capture and extract: Take screenshots, full-page captures, PDFs, and extract text or element data including downloads and recordings.
  • Session and security controls: Named sessions, state save/load, domain allowlists, proxy support, timeouts, and action policies for safe automated runs.
  • Use Case: Automate logging into a web app, perform form submissions, capture evidence as screenshots/video, and save authenticated session state for repeated runs.

Quick Start

Open the target URL, run an interactive snapshot to obtain element refs, then fill, click, or extract elements and capture screenshots or downloads as needed.

Frequently Asked Questions about agent-browser

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate browser interactions on JavaScript-driven pages?

Browser automation handles JavaScript-driven pages by navigating websites, interacting with DOM elements, and extracting visual or textual content through a CLI daemon that fully renders pages before executing actions.

Can I save and reuse authenticated session state for repeated web scraping runs?

Session management supports saving and loading authenticated state for repeated runs, utilizing named sessions, domain allowlists, and credential handling to maintain persistent login contexts across scraping tasks.

How do I capture screenshots and PDFs during web form submission automation?

Screenshot and PDF capture occurs during form submission by navigating pages, filling interactive elements, and recording visual evidence of the UI flows directly through the CLI daemon.

Does headless browser automation support proxy configuration and file downloads?

Headless browser automation supports proxy configuration, file downloads, and video recording, applying wait/load policies and action controls for safe automated execution.

What is the best way to extract dynamic content from web pages without manual interaction?

Extracting dynamic content without manual interaction relies on programmatic browser automation to snapshot interactive element refs, extract text or element data, and capture full page renders.

Can I use this browser automation approach for end-to-end UI testing?

End-to-end UI testing is supported by automating complex UI flows, applying timeouts and action policies, and capturing video or screenshot evidence to verify interface behavior.