skills.rest
acarmonag
acarmonagCOMMUNITY
Explore all skills by this author →
GitHub

browser

Automate web browser interactions and data extraction using accessibility snapshots.

2|Updated Apr 7, 2026
Search Tags:#automation#mcp#navigation#scraping#browser#web
One-click install
npx skills add https://github.com/acarmonag/ai-runbook-automation --skill browser-acarmonag
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: browser
Source: https://github.com/acarmonag/ai-runbook-automation/tree/main/.claude/skills/browser
Command: npx skills add https://github.com/acarmonag/ai-runbook-automation --skill browser-acarmonag

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill solves the complexity of web automation by reducing DOM overhead and providing a reliable, AI-optimized interface for interacting with web pages.

Core Features & Use Cases

  • AI-Optimized Snapshots: Uses accessibility trees and element references to reduce context size by 93% compared to raw HTML.
  • Multi-Session Swarm: Supports isolated browser sessions for parallel tasks like authentication and data scraping.
  • Use Case: Automate complex login flows and multi-page data extraction tasks by using element refs to ensure deterministic interactions across dynamic web applications.

Quick Start

Use the browser skill to navigate to the target URL and extract all interactive elements for further interaction.

Frequently Asked Questions about browser

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

FAQPage Schema
How do I automate web navigation and scraping without dealing with raw HTML overhead?▼

Automating web navigation is streamlined by using AI-optimized accessibility snapshots instead of raw HTML. This approach maps DOM elements to deterministic references, reducing context size by 93% and enabling reliable agentic control for complex interactions.

What is the best way to handle complex login flows and multi-page data extraction?▼

Handling complex login flows is best achieved through isolated browser sessions that support parallel tasks. By using element refs mapped from accessibility trees, you ensure deterministic interactions across dynamic web applications during multi-page extraction.

Can I run parallel browser sessions for simultaneous authentication and scraping tasks?▼

Yes, running parallel browser sessions is supported through a multi-session swarm feature. This allows you to maintain isolated browser instances for simultaneous tasks like authentication and data scraping without session interference.

How does mapping DOM elements to deterministic references improve web automation?▼

Mapping DOM elements to deterministic references improves web automation by providing a reliable, AI-optimized interface. This integration ensures consistent element targeting across dynamic web pages, preventing interaction failures caused by shifting DOM structures.

Does web scraping with accessibility snapshots reduce context size for AI agents?▼

Web scraping with accessibility snapshots reduces context size by 93% compared to raw HTML. This optimized data format provides AI agents with a cleaner representation of interactive elements, facilitating more efficient navigation and content extraction.

Related Skills

Explore More Software Engineering Skills→
mrsorbatemrsorbate

browser

Automate web browser interactions and data scraping via accessibility snapshots.

Community
Advanced
shynlee04shynlee04

web-search

Search the web and extract content via Tavily and Exa using the inference.sh CLI.

Community
Intermediate
ProyectoG007ProyectoG007

agent-browser

Automate headless browser workflows using accessibility tree snapshots for element selection.

Community
Advanced
libilibi
27

ko-browser

Automate browser navigation, form submission, and screenshot capture via a Go-based CLI.

Community
Advanced