skills.rest
TrendpilotAI
TrendpilotAICOMMUNITY
Explore all skills by this author →
𝕏@NathanStvnsnGitHub

agent-browser

Automate browser interactions like navigation, form filling, and data scraping via the agent-browser CLI.

Updated Aug 27, 2026
Search Tags:#AI agent#browser automation#web scraping#form filling#CLI tool#web interaction
One-click install
npx skills add https://github.com/TrendpilotAI/invesco-demo --skill agent-browser-trendpilotai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/TrendpilotAI/invesco-demo/tree/main/skills/compound-engineering/skills/agent-browser
Command: npx skills add https://github.com/TrendpilotAI/invesco-demo --skill agent-browser-trendpilotai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill automates interactions with web pages, including filling forms, clicking buttons, taking screenshots, and scraping data, directly from your command line.

Core Features & Use Cases

  • Web Navigation: Open, reload, and navigate back/forward through web pages.
  • Element Interaction: Click, type, fill, check, and scroll to specific elements using reference IDs or semantic locators.
  • Data Scraping & Screenshots: Capture page content, element details, screenshots, and save pages as PDFs.
  • Use Case: Automate the process of logging into a website, filling out a multi-step form, and taking a screenshot of the confirmation page.

Quick Start

Use the agent-browser skill to navigate to https://example.com and take a screenshot.

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 scraping and form filling directly from the command line?▼

You can automate web scraping and form filling from the command line by using an AI agent to control browser interactions. This Skill executes web navigation, element interaction, and data extraction tasks directly through the CLI.

What is the best way to automate multi-step web form submissions and capture screenshots?▼

The best way to automate multi-step web form submissions is by using reference IDs or semantic locators to interact with elements deterministically. You can fill out forms, click buttons, and take screenshots of the final confirmation pages.

Do I need to install Chromium and npm packages to run browser automation tasks?▼

Yes, you need to install the agent-browser npm package and Chromium to run browser automation tasks. These dependencies provide the underlying browser environment required for the CLI to execute web interactions.

How does an AI agent interact with web page elements for deterministic task execution?▼

An AI agent interacts with web page elements by using ref-based element selection and semantic locators. This approach ensures deterministic task execution by targeting specific page components for clicking, typing, and scrolling actions.

Can I capture web page content and save pages as PDFs using CLI browser automation?▼

Yes, you can capture web page content and save pages as PDFs using CLI browser automation. The Skill supports taking screenshots, capturing element details, and scraping data directly from your terminal interface.

Related Skills

Explore More Software Engineering Skills→
dsactivi-2dsactivi-2

Agent Browser

Automate headless browser navigation, form filling, and data extraction via CLI.

Community
Advanced
leonanpereirapintoleonanpereirapinto
1

docling

Convert PDFs, Word, HTML, and images into structured Markdown, JSON, or HTML output.

Community
Intermediate
code-yeongyucode-yeongyu
67.6k

agent-browser

Automate browser interactions for testing, form filling, and data extraction.

Community
Intermediate
JimmyChen-NXPJimmyChen-NXP

agent-browser

Automate headless browser tasks via command-line interface for web pages.

Community
Intermediate