skills.rest
mattjefferson
mattjeffersonCOMMUNITY
Explore all skills by this author →
Website𝕏@mjeffersonGitHub

agent-browser

Automate browser navigation, form interaction, and data extraction via CLI.

4|1|Updated Feb 14, 2026
Search Tags:#testing#AI agent#browser automation#web scraping#form filling#web interaction
One-click install
npx skills add https://github.com/mattjefferson/harness-engineering --skill agent-browser-mattjefferson
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/mattjefferson/harness-engineering/tree/main/skills/agent-browser
Command: npx skills add https://github.com/mattjefferson/harness-engineering --skill agent-browser-mattjefferson

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill enables AI agents to interact with web browsers programmatically, automating tasks that typically require human interaction, such as navigating websites, filling forms, and extracting data.

Core Features & Use Cases

  • Web Navigation: Open URLs, go back/forward, and reload pages.
  • Form Interaction: Fill text fields, select dropdown options, check/uncheck boxes, and submit forms.
  • Data Extraction: Scrape text content, element attributes, and structured data from web pages.
  • Screenshots & PDFs: Capture full-page screenshots or save entire pages as PDFs.
  • Use Case: An AI agent needs to sign up for a new service. It uses agent-browser to open the signup page, fill in the required fields (name, email, password), handle any CAPTCHAs if integrated, and submit the form.

Quick Start

Use agent-browser to open the website https://example.com and take a full page 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 form filling and submission for an AI agent?▼

Automate web form filling by using a command-line interface for programmatic browser automation to input text, select dropdowns, check boxes, and submit forms. This enables AI agents to interact with web elements without human intervention.

Can I use Playwright or Selenium for web scraping with an AI agent?▼

Yes, web scraping with an AI agent requires integration with browser automation tools like Playwright or Selenium. The Skill provides a command-line interface that extracts text content, element attributes, and structured data from web pages.

What is the best way to capture full-page screenshots during browser automation?▼

The best way to capture full-page screenshots during browser automation is through a command-line interface that programmatically navigates URLs and triggers screenshot captures. It also supports saving entire pages as PDFs.

Does browser automation support complex workflows like authentication on mobile environments?▼

Yes, programmatic browser automation supports complex workflows including authentication and data scraping across both desktop and mobile environments. It handles web navigation such as opening URLs, going back/forward, and reloading pages.

Why do I need a command-line interface for web interaction instead of manual browsing?▼

You need a command-line interface for web interaction to enable AI agents to navigate websites, interact with web elements, and extract data programmatically. This automates tasks that typically require human interaction, such as filling forms and data scraping.

Related Skills

Explore More Software Engineering Skills→
byeSystem32byeSystem32

agent-browser

Automate web interactions via command-line browser automation commands.

Community
Advanced
shreed27shreed27

history

Fetch, sync, and analyze trade history from Polymarket and Kalshi.

Community
Intermediate
vibewatchvibewatch

fetch-url

Fetch URLs and extract readable text from HTML pages and PDFs.

Official
Intermediate
spideynolovespideynolove
2

lightpanda

Fetch HTML content from web pages using a lightweight headless browser.

Community
Basic