agent-browser

Automate web and Electron app interactions with Playwright-based browser control.

Updated Jul 13, 2026
One-click install
npx skills add https://github.com/ElbertePlinio/dotfiles --skill agent-browser-elberteplinio
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/ElbertePlinio/dotfiles/tree/main/private_dot_factory/plugins/marketplaces/factory-plugins/plugins/droid-control/skills/agent-browser
Command: npx skills add https://github.com/ElbertePlinio/dotfiles --skill agent-browser-elberteplinio

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates the tedious manual effort of interacting with web pages and Electron desktop applications for automation, testing, and data extraction tasks, removing the need for repetitive clicks, form fills, and manual verification.

Core Features & Use Cases

  • Cross-Platform Browser Automation: Control any web application or Electron desktop app (including VS Code, Slack, Figma, and Notion) for login flows, form submissions, data scraping, and UI testing.
  • Visual Quality Assurance: Capture full-page or annotated screenshots with numbered element labels to validate layout, styling, and alignment, with support for pixel-perfect visual diffs.
  • DOM-Level Interaction: Interact with page elements via accessibility snapshots, handle dynamic single-page applications, and execute custom JavaScript for complex automation scenarios.

Quick Start

Use the agent-browser skill to automate the login flow for your target web application, capture an annotated screenshot of the post-login dashboard, and verify all key UI elements are present.

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 app login flows and extract data using Playwright?

Automate web app login flows and data extraction using Playwright-based browser control, which manages persistent sessions, tracks element references, and interacts with DOM elements via accessibility snapshots for reliable single-page application automation.

Can I use browser automation to control Electron desktop apps like VS Code or Slack?

Yes, you can use browser automation to control Electron desktop apps like VS Code, Slack, Figma, and Notion for login flows, form submissions, data scraping, and UI testing by applying web interaction techniques to the desktop application environment.

What is the best way to perform visual quality assurance on a single-page application?

Perform visual quality assurance on a single-page application by capturing full-page or annotated screenshots with numbered element labels to validate layout, styling, and alignment, utilizing pixel-perfect visual diffs to detect regressions.

Does browser automation support persistent session management for testing dynamic web pages?

Yes, browser automation supports persistent session management for testing dynamic web pages by maintaining session state across interactions, handling dynamic single-page applications, and tracking element references for reliable DOM-level assertions.

How do I capture annotated screenshots during web scraping to verify UI elements?

Capture annotated screenshots during web scraping by utilizing visual quality assurance features that apply numbered element labels to full-page captures, allowing you to verify all key UI elements are present and validate layout alignment.