agent-browser

Automate browser interactions for navigation, form filling, screenshots, and data extraction.

Updated Feb 27, 2024
One-click install
npx skills add https://github.com/MaxStrootmann/lumen-yoga --skill agent-browser-maxstrootmann
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/MaxStrootmann/lumen-yoga/tree/main/.agents/skills/agent-browser
Command: npx skills add https://github.com/MaxStrootmann/lumen-yoga --skill agent-browser-maxstrootmann

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

agent-browser removes manual browser work by letting agents and scripts programmatically navigate websites, interact with forms and controls, capture visual evidence, and extract structured content so tasks like login automation, scraping, and UI testing can run reliably and repeatably.

Core Features & Use Cases

  • Interactive snapshot refs (@e1, @e2, ...) that reduce context and enable precise element targeting for clicks, fills, and selections.
  • Persistent named sessions, state save/load, and encrypted auth vault to reuse authenticated contexts for CI, monitoring, or long-running agents.
  • Visual capture and diffing: full-page screenshots, annotated images, PDF export, video recording, and pixel diffs for visual regression testing.
  • Robust wait strategies, CDP connection, proxy support, and profiling tools for debugging and performance analysis.
  • Use cases include automated form submissions, authenticated scraping, end-to-end web testing, scheduled monitoring, and demo recording.

Quick Start

Open the page with agent-browser, take an interactive snapshot to capture refs, then perform fills, clicks, waits, and screenshots in sequence to complete the task.

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 tasks like filling forms and taking screenshots?

Browser automation lets you programmatically navigate pages, fill forms, click elements, and take screenshots. You can use interactive snapshot refs to target elements precisely and execute actions in sequence to complete tasks reliably.

What is session persistence in web scraping and how does it help with authenticated pages?

Session persistence in web scraping saves and reloads authenticated browser states, allowing you to reuse login contexts across runs. This enables reliable authenticated scraping and monitoring without repeatedly performing manual logins.

Can I use Playwright for visual regression testing with full-page screenshots?

Yes, you can use Playwright for visual regression testing by capturing full-page screenshots and performing pixel diffs. You can also export PDFs and record videos to capture visual evidence for UI automation tasks.

Does browser automation work with single-page and multi-page web apps?

Browser automation works with both single-page and multi-page web apps. It provides configurable wait strategies to handle dynamic content, along with CDP connectivity and proxy support for debugging complex web interactions.

What's the best way to extract structured page data from dynamic web pages?

The best way to extract structured page data is using interactive snapshot refs that compactly capture page elements. This reduces context overhead while enabling precise data extraction from dynamic web pages during scraping tasks.