skills.rest
SangIlMo
SangIlMoCOMMUNITY
Explore all skills by this author →
GitHub

agent-browser

Automate browser navigation, interaction, testing, and extraction across web pages.

1|Updated Nov 14, 2024
Search Tags:#automation#screenshots#web-testing#browser#data-extraction#form-filling#element-refs
One-click install
npx skills add https://github.com/SangIlMo/.dotfiles --skill agent-browser-sangilmo
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/SangIlMo/.dotfiles/tree/main/.config/claude/skills/agent-browser
Command: npx skills add https://github.com/SangIlMo/.dotfiles --skill agent-browser-sangilmo

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automating repetitive browser tasks such as testing, form filling, screenshot capture, and data extraction reduces manual effort and human error, speeds up validation, and improves reliability.

Core Features & Use Cases

  • Navigate to pages and manage browsing sessions
  • Snapshot the page to identify interactive elements and work with refs
  • Interact with elements (click, fill, type, hover, select) and perform validations
  • Capture screenshots and extract information for reporting

Quick Start

Open a page, snapshot the interactive elements, then perform actions using the element refs to complete a workflow.

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 testing and form filling across multiple web pages?▼

Automate web testing by navigating to pages, snapshotting interactive elements, and performing actions like form filling and clicking using element refs to validate UI flows. This reduces manual effort and human error during repetitive browser tasks.

What is the best way to capture screenshots and extract data from web pages for reporting?▼

Capture screenshots and extract data by opening a page, taking a snapshot of interactive elements, then performing actions using element refs to complete a workflow. This approach improves reliability and speeds up validation for reporting tasks.

How do I identify and interact with interactive elements during browser automation?▼

Identify interactive elements by snapshotting the page, which generates element refs. Use these refs to perform interactions like click, fill, type, hover, and select actions to complete your browser automation workflow accurately.

Do I need a browser automation runtime to manage browsing sessions and navigate sites?▼

Yes, a browser automation runtime is required to manage browsing sessions, navigate to pages, and perform element interactions. This runtime supports session management, element snapshots, and a broad set of interactions for web testing.

Can I use browser automation for validating UI flows and navigating sites?▼

Yes, browser automation applies to scenarios such as navigating sites, validating UI flows, capturing screenshots, and extracting content or data from pages. It supports a broad set of interactions and session management for these tasks.

Related Skills

Explore More Software Engineering Skills→
kolodachkolodach

agent-browser

Automate browser interactions and extract page data via ref-based snapshots.

Community
Advanced
Arry8Arry8
1

tavily

Automate web search, content extraction, and research discovery with configurable depth.

Community
Intermediate
temple-slopetemple-slope

agent-browser

Automate browser tasks including web testing, form filling, and data extraction.

Community
Intermediate
fajshahfajshah
1

browsing-with-playwright

Automate browser navigation, form interactions, and data extraction via Playwright MCP.

Community
Intermediate