skills.rest
HHU3637kr
HHU3637krCOMMUNITY
Explore all skills by this author →
GitHub

agent-browser

Automate browser tasks via a Playwright-powered CLI with JSON snapshots.

140|20|Updated Jan 8, 2026
Search Tags:#automation#ai#playwright#session-management#browser#data-extraction#semantic-locators
One-click install
npx skills add https://github.com/HHU3637kr/skills --skill agent-browser-hhu3637kr
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/HHU3637kr/skills/tree/main/agent-browser
Command: npx skills add https://github.com/HHU3637kr/skills --skill agent-browser-hhu3637kr

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Headless browser automation for AI agents reduces manual, repetitive web tasks by providing a CLI-driven interface to control a browser, interact with pages, fill forms, and capture results.

Core Features & Use Cases

  • Refs-based element targeting: Interact with page elements using stable references or semantic locators for robust automation.
  • Session management & multi-domain workflows: Run isolated tasks in named sessions with independent cookies, storage, and navigation states.
  • Data extraction, form automation & verification: Snapshot JSON, fill forms, click controls, and verify results across dynamic pages.
  • Usage scenario: An AI agent opens a product page, snapshots the DOM structure, fills a form, and saves a screenshot for verification.

Quick Start

Open a URL, capture a JSON snapshot, and let the AI drive interactions using refs or semantic locators.

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 tasks using Playwright for AI agents?▼

You automate web browsing for AI agents via a CLI-driven workflow using Playwright. It opens URLs, captures JSON snapshots, and executes interactions using stable refs or semantic locators, enabling agents to drive dynamic page interactions robustly.

What is headless browser automation and how does it work with AI?▼

Headless browser automation for AI agents uses a CLI-driven interface to control a browser without a UI. It captures DOM structures as JSON snapshots, allowing AI to analyze page elements and execute interactions like form filling and verification.

Can I manage isolated browser sessions with independent cookies and storage?▼

Yes, you can run isolated tasks in named sessions. This Skill manages session state by maintaining independent cookies, storage, and navigation states, enabling secure multi-domain workflows without cross-session interference.

How do I extract data and fill forms on dynamic web pages?▼

You extract data and fill forms on dynamic pages by capturing a JSON snapshot of the DOM, then using stable references or semantic locators. The AI agent uses these refs to click controls, fill inputs, and verify results.

Does browser automation require any external dependencies or scripts?▼

No external dependencies are required to use this Skill. It optionally extends behavior using script and reference assets, providing a self-contained CLI workflow for debugging, network interception, and session management.

Related Skills

Explore More Software Engineering Skills→
namninhndnamninhnd

Playwright Browser Automation

Automate web browser interactions with Playwright via MCP server or Node.js API.

Community
Advanced
mbastakismbastakis
5

crawl4ai

Crawl web pages with Python and extract structured data as Markdown or JSON.

Community
Intermediate
Wanli-LeeWanli-Lee
1

agent-browser

Automate browser workflows using accessibility tree snapshots and stable reference IDs.

Community
Intermediate
Z43LZ43L

scrapling

Extract web content from static, dynamic, and Cloudflare-protected pages.

Community
Advanced