skills.rest
gannonh
gannonhCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

agent-browser

Automate browser tasks via snapshot-driven element ref interactions.

2|Updated Feb 18, 2026
Search Tags:#automation#cli#web-testing#browser#refs#ai-agents#data-extraction
One-click install
npx skills add https://github.com/gannonh/skills --skill agent-browser-gannonh
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/gannonh/skills/tree/main/agent-browser
Command: npx skills add https://github.com/gannonh/skills --skill agent-browser-gannonh

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Automates browser-based tasks for AI agents by providing a compact, ref-driven workflow that reduces manual browsing effort.

Core Features & Use Cases

  • Snapshot-driven interactions using element refs for reliable automation.
  • Supports navigation, form filling, data extraction, testing, and visual verification across desktop and mobile contexts.
  • Example use case: automate a login flow and extract page data for validation.

Quick Start

Open a target site, snapshot to capture element refs, and interact with those refs to complete a 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 for AI agents?▼

You can automate browser tasks for AI agents by using a ref-driven workflow that captures element references during a page snapshot, then executing interactions like navigation and form filling against those specific element refs.

What is a ref-driven workflow for web automation?▼

A ref-driven workflow for web automation captures element references during a page snapshot, allowing AI agents to reliably target and interact with specific page elements for data extraction and testing without manual browsing effort.

How do I extract data from web pages using AI agents?▼

To extract data from web pages using AI agents, you snapshot the target site to capture element refs, interact with those refs to navigate or fill forms, and extract the resulting page data for validation.

Can I use browser automation for web testing on both desktop and mobile?▼

Yes, this browser automation approach supports web testing, visual verification, and navigation across both desktop and mobile contexts, allowing AI agents to validate page elements using snapshot-driven refs.

Does AI agent browser automation work without external dependencies?▼

Yes, the browser automation workflow operates independently without external dependencies, relying solely on its internal SKILL.md frontmatter and optional directories like references/ and scripts/ to extend capabilities.

Why use snapshot-driven interactions for browser automation?▼

Snapshot-driven interactions provide reliable browser automation by capturing exact element refs on the page, ensuring AI agents accurately target elements for navigation, form filling, and visual checks across varying contexts.

Related Skills

Explore More Software Engineering Skills→
swongsuddeeswongsuddee
1

playwright-cli

Automate browser interactions and capture evidence using Playwright CLI.

Community
Intermediate
quanngynxquanngynx

agent-browser

Automate Chrome browser interactions via CDP with snapshot-based element refs.

Community
Advanced
hemoryhemory

agent-browser

Displays a list of available commands for the specified tool.

Community
Intermediate
zhouxiuminzhouxiumin

agent-browser

Automate browser workflows using accessibility-tree snapshots and ref-based element targeting.

Community
Advanced