skills.rest
harshaldhaduk
harshaldhadukCOMMUNITY
Explore all skills by this author →
GitHub

browser

Automate web browser tasks using accessibility tree snapshots with element references.

1|1|Updated Apr 11, 2026
Search Tags:#browser automation#ai agents#web scraping#form filling#ui testing#element refs
One-click install
npx skills add https://github.com/harshaldhaduk/Lattice --skill browser-harshaldhaduk
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: browser
Source: https://github.com/harshaldhaduk/Lattice/tree/main/.claude/skills/browser
Command: npx skills add https://github.com/harshaldhaduk/Lattice --skill browser-harshaldhaduk

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Traditional web automation tools output full DOM content, which wastes valuable AI agent context and slows down tasks like scraping, testing, and form filling. This Skill eliminates that inefficiency with AI-optimized snapshots.

Core Features & Use Cases

  • Low-Context Snapshots: Uses accessibility trees with element references (@e1, @e2) instead of full DOM, cutting AI context usage by 93% for faster, more efficient automation.
  • Full Browser Control: Supports navigation, element interaction, data extraction, screenshots, and multi-session parallel work for swarm agent workflows.
  • Use Case: Automate repetitive web tasks like logging into accounts, scraping product listings, or running parallel cross-browser tests without manual intervention.

Quick Start

Use the browser skill to navigate to any webpage, capture an interactive snapshot of its elements, and automate tasks like form filling, button clicking, or data extraction using the provided element references.

Frequently Asked Questions about browser

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

FAQPage Schema
How do I reduce context usage during AI web scraping and browser automation?▼

You can reduce AI context usage in browser automation by replacing verbose full DOM outputs with compact accessibility tree snapshots that use element references like @e1 to cut context overhead by 93%.

Can I run parallel multi-session browser operations for agent swarm workflows?▼

Yes, you can run parallel multi-session browser operations for agent swarm workflows by using multi-session management commands to execute concurrent navigation, element interaction, and data extraction across isolated browser instances.

How do I automate form filling and login flows using an accessibility tree?▼

Automate form filling and login flows by capturing an interactive accessibility tree snapshot, then executing interaction commands against specific element references or CSS selectors to input data and click buttons without parsing raw HTML.

What is the best way to perform UI testing without consuming excessive AI context?▼

The best way to perform UI testing without excessive AI context is using accessibility tree snapshots with element references instead of full DOM content, enabling faster automated test execution and lower token consumption.

Do I need a specific CLI tool to execute web navigation and element interaction?▼

Yes, you need the agent-browser CLI to execute web navigation, element interaction, data extraction, and session management commands using element references, CSS selectors, or semantic locators for automation tasks.

How does replacing full DOM content with element references improve web scraping?▼

Replacing full DOM content with element references improves web scraping by generating compact accessibility tree snapshots that eliminate verbose HTML, reducing context waste and accelerating AI-driven data extraction.

Related Skills

Explore More Software Engineering Skills→
Valor-mmmValor-mmm

sentry-browser-sdk

Install and initialize @sentry/browser for error monitoring and tracing.

Community
Advanced
liuaibin001liuaibin001

automating-browsers

Automate browser interactions for AI agents using the agent-browser CLI.

Community
Advanced
91fapiao-cn91fapiao-cn
71

playwright-browser

Automate browser tasks across Chromium, Firefox, and WebKit via MCP.

Community
Advanced
chiruu12chiruu12
1

browse

Automates web page navigation, form submissions, screenshot diffs, and state verification via headless browser technology in Python.

Community
Advanced