skills.rest
sammyjoyce
sammyjoyceCOMMUNITY
Explore all skills by this author →
GitHub

agent-browser

Automate web browser interactions via the agent-browser CLI for AI agents.

Updated Feb 10, 2026
Search Tags:#screenshots#browser automation#web scraping#form filling#web automation#headless browser
One-click install
npx skills add https://github.com/sammyjoyce/pi-compound-engineering --skill agent-browser-sammyjoyce
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/sammyjoyce/pi-compound-engineering/tree/main/skills/agent-browser
Command: npx skills add https://github.com/sammyjoyce/pi-compound-engineering --skill agent-browser-sammyjoyce

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates interactions with web pages, allowing AI agents to navigate, fill forms, take screenshots, and scrape data without manual intervention.

Core Features & Use Cases

  • Web Navigation: Open, close, and navigate between web pages.
  • Form Interaction: Fill input fields, click buttons, select dropdowns, and check/uncheck boxes.
  • Data Scraping & Screenshots: Extract text, HTML, attributes, and capture full-page or viewport screenshots.
  • Use Case: Automatically log into a web application, fill out a complex form, and then take a screenshot of the confirmation page.

Quick Start

Use the agent-browser skill to open the website at 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 browser interactions like form filling and navigation with an AI agent?▼

You can automate web browser interactions by using the agent-browser CLI to handle navigation, fill forms, and interact with elements via accessibility refs. It supports both headless and headed modes, allowing AI agents to control web pages without manual intervention.

Can I use headless browser automation to scrape data and take screenshots?▼

Yes, headless browser automation supports scraping data and taking screenshots. The agent-browser CLI extracts text, HTML, and attributes from web pages, and captures full-page or viewport screenshots while outputting structured JSON data for AI processing.

What is the best way to automate logging into a web application and capturing a confirmation screenshot?▼

The best way to automate web logins and capture confirmation screenshots is using a browser automation CLI that handles navigation, form filling, and element interaction. The agent-browser skill fills input fields, clicks buttons, and takes viewport or full-page screenshots upon completion.

Does browser automation support parallel sessions for scraping multiple web pages simultaneously?▼

Yes, browser automation supports parallel sessions for interacting with multiple web pages simultaneously. The agent-browser CLI enables AI agents to manage concurrent browser sessions, extracting structured JSON data and screenshots from different pages at the same time.

How do I extract structured data from web pages during web automation tasks?▼

To extract structured data during web automation, the agent-browser CLI outputs JSON formatted results containing text, HTML, and element attributes. This structured data extraction allows AI agents to process scraped information from web pages programmatically.

Do I need to install external dependencies to run web automation scripts with an AI agent?▼

No external dependencies are required to run web automation scripts with this skill. The agent-browser CLI operates independently to handle browser navigation, form filling, and data scraping, providing JSON output for structured data extraction without additional package installations.

Related Skills

Explore More Software Engineering Skills→
wodehwodeh

pair-agent

Generate a setup key for remote agents to connect to a browser session.

Community
Advanced
juricamigac-from-hrjuricamigac-from-hr

identify-page-structure

Identify sections and content sequences in scraped webpages for structured import.

Official
Intermediate
AllBeingsFutureAllBeingsFuture
9

browser-get-content

Extract page or element text from a webpage using an optional CSS selector.

Community
Basic
optionioptioni

playwright-cli

Automate browser interactions, testing, and development with Playwright.

Official
Advanced