skills.rest
hollandkevint
hollandkevintCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

agent-browser

Automate web browser interactions via CLI for navigation, form filling, and screenshots.

5|1|Updated Aug 26, 2025
Search Tags:#screenshots#cli#form filling#web automation#scraping#browser
One-click install
npx skills add https://github.com/hollandkevint/thinkhaven --skill agent-browser-hollandkevint
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/hollandkevint/thinkhaven/tree/main/.gemini/skills/agent-browser
Command: npx skills add https://github.com/hollandkevint/thinkhaven --skill agent-browser-hollandkevint

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill automates web browser interactions, allowing for tasks like filling forms, clicking buttons, taking screenshots, and scraping data directly from web pages via a command-line interface.

Core Features & Use Cases

  • Web Navigation: Open and navigate to specified URLs.
  • Element Interaction: Click, type, fill, check, and select elements using reference IDs or semantic locators.
  • Data Scraping & Screenshots: Extract text, HTML, attributes, and capture screenshots of web pages.
  • Use Case: Automate the process of logging into a web application, filling out a registration form, and submitting it, then taking a screenshot of the confirmation page.

Quick Start

Use the agent-browser skill to open the website https://example.com and take a full page screenshot named output.png.

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 browser interactions to fill forms and take screenshots?▼

Automate web browser interactions by using a CLI tool to navigate URLs, fill forms, click buttons, and take screenshots. It leverages accessibility snapshots and semantic locators to execute tasks deterministically. You can capture full-page screenshots or extract text and HTML directly.

How does web scraping work with accessibility snapshots and semantic locators?▼

Web scraping via CLI uses accessibility snapshots to generate reference IDs for elements on the page. Semantic locators and these ref IDs target specific elements, allowing automated agents to extract text, HTML, and attributes deterministically without relying on brittle CSS selectors.

Do I need to install Chromium to use a CLI for web automation?▼

Yes, you need to install the agent-browser CLI tool and Chromium to use this web automation Skill. These dependencies provide the environment required to navigate websites, fill forms, click buttons, and scrape data through the command-line interface.

What's the best way to automate logging into a website and scraping the confirmation page?▼

The best way is using a CLI web automation tool that navigates to the login URL, fills the registration form, clicks submit, and takes a screenshot of the confirmation page. This is achieved by utilizing reference IDs from accessibility snapshots for element selection.

Can I extract HTML attributes and capture screenshots using command-line web automation?▼

Yes, CLI web automation supports extracting text, HTML, and attributes from web pages. It also captures screenshots of web pages, enabling you to save visual outputs like a full-page PNG while automating interactions like clicking and typing.

Why use reference IDs from accessibility snapshots instead of CSS selectors for web automation?▼

Using reference IDs from accessibility snapshots ensures deterministic task execution. This approach allows automated agents to reliably click, type, and select elements, avoiding the fragility of CSS selectors when navigating websites and filling forms via a CLI.

Related Skills

Explore More Software Engineering Skills→
MisLinkMisLink

agent-browser

Automate web page navigation, interaction, and data extraction via Chromium CDP.

Community
Advanced
Blake-JohnBlake-John

pymupdf

Convert PDF documents into Markdown, JSON, and text for LLM workflows.

Community
Intermediate
michaelvolzmichaelvolz

agent-browser

Automate browser navigation and DOM interactions via CLI workflows.

Community
Advanced
limzivectorlimzivector

scrape

Extract text, tables, and images from web pages via browser automation.

Community
Intermediate