agent-browser

Automate browser tasks via CLI for navigation, interaction, and data capture.

1|Updated Nov 20, 2025
One-click install
npx skills add https://github.com/sejoalfaro/paperly --skill agent-browser-sejoalfaro
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/sejoalfaro/paperly/tree/main/.agents/skills/agent-browser
Command: npx skills add https://github.com/sejoalfaro/paperly --skill agent-browser-sejoalfaro

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Automate browser-based tasks for AI agents by providing a robust CLI to open URLs, interact with elements, fill forms, take screenshots, and extract data from web pages.

Core Features & Use Cases

  • Open and navigate pages with deterministic steps, fill inputs, click controls, and capture screenshots for QA and demos.
  • Support for session management, authentication flows, and multi-session orchestration to reuse login states across runs.
  • Data extraction and automated testing workflows, including form submission, validation, and visual checks.

Quick Start

Use the agent-browser CLI to perform a sample interaction like opening a page, snapshotting the UI, and performing a click.

Frequently Asked Questions about agent-browser

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate browser tasks like form filling and data extraction with an AI agent?

Automate browser tasks using a CLI to open URLs, interact with elements, fill forms, take screenshots, and extract data. The agent-browser skill manages web automation for AI agents across testing, data extraction, and form workflows.

Can I maintain authentication states across multiple web automation sessions?

Web automation supports session management, authentication flows, and multi-session orchestration to reuse login states across runs. This allows deterministic navigation while maintaining persistent contexts for repeated tasks.

How do I capture and validate web pages during automated testing?

Automated testing captures data and validates pages by opening URLs, interacting with elements, and taking screenshots. The snapshot and reference system minimizes prompt payloads while performing visual checks and form validation.

Do I need a specific browser engine for CLI-based web automation?

CLI-based web automation requires a local Chromium-based engine to operate. This supports modular components through scripts and references, enabling deterministic page interaction and data extraction.

What's the best way to reduce prompt payload size when automating web interactions?

Minimize prompt payloads during web automation using a snapshot and reference system. This approach captures UI states efficiently, allowing AI agents to interact with page elements without sending excessive context data.