agent-browser

Automate web browsing, UI interaction, and structured data extraction.

Updated Mar 15, 2026
One-click install
npx skills add https://github.com/spyqs/nanoclaw-email-imap --skill agent-browser-spyqs
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/spyqs/nanoclaw-email-imap/tree/main/container/skills/agent-browser
Command: npx skills add https://github.com/spyqs/nanoclaw-email-imap --skill agent-browser-spyqs

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It solves the problem of manually browsing websites, interacting with UI elements, and extracting information by automating these steps inside a controlled browser workflow.

Core Features & Use Cases

  • Web navigation & UI interaction: Open pages, click, fill, select, scroll, upload files, and wait for page readiness using interactive element references.
  • Structured page analysis: Capture accessibility trees via snapshots to reliably locate elements and extract text, HTML, attributes, titles, URLs, and counts.
  • Screenshots and PDF output: Produce visual evidence (screenshots) and document exports (PDF) for verification and reporting.
  • Use Case: Turn a messy “manual research + copy/paste” task into an automated workflow by browsing a product listing, snapshotting elements, extracting fields, and saving screenshots for audit.

Quick Start

Tell the agent to open https://example.com, snapshot the page for interactive refs, extract the main headings, and capture a full-page screenshot.

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 browsing and UI interaction for dynamic pages?

Extract structured data from web pages by capturing accessibility trees via snapshots to reliably locate elements. The Skill extracts text, HTML, attributes, titles, URLs, and counts from dynamic pages, turning manual copy/paste research into automated structured data extraction workflows.

Can I capture screenshots and generate PDFs during web automation?

Use snapshot-driven element referencing to reliably locate interactive elements on dynamic pages. The Skill captures accessibility trees, providing deterministic references for clicking, filling, and extracting data from dynamically loaded web content without relying on fragile selectors.

How do I extract structured data from web pages without manual copy and paste?

Extract structured data from web pages by capturing accessibility trees via snapshots to reliably locate elements. The Skill extracts text, HTML, attributes, titles, URLs, and counts from dynamic pages, turning manual copy/paste research into automated structured data extraction workflows.

Can I capture screenshots and generate PDFs during web automation?

Yes, you can capture screenshots and generate PDFs during web automation. The Skill produces visual evidence through full-page screenshots and document exports for verification, audit reporting, and rendering outputs across dynamic web pages.

How do I fill forms and upload files automatically in browser testing workflows?

Use this Skill for web automation tasks requiring snapshot-driven element referencing, deterministic navigation, and structured data extraction. It suits research workflows, form completion, web app testing, and screenshot generation across dynamic pages where interactive element references are needed.