agent-browser

Automate web tasks via CLI for navigation, form filling, and data extraction.

Updated Jan 2, 2026
One-click install
npx skills add https://github.com/tanaka-mambinge/dotfiles --skill agent-browser-tanaka-mambinge
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/tanaka-mambinge/dotfiles/tree/main/ai-configs/skills/agent-browser
Command: npx skills add https://github.com/tanaka-mambinge/dotfiles --skill agent-browser-tanaka-mambinge

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automate repetitive web interactions by providing a unified CLI to control a browser, enabling AI agents to navigate pages, fill forms, click controls, take screenshots, and extract data without manual steps.

Core Features & Use Cases

  • Deterministic browser automation with snapshot-based refs, multi-session isolation, and batch execution for scalable workflows.
  • Built-in authentication patterns, session persistence, and form/test automation across dashboards, portals, and apps.
  • Data extraction, visual validation, and testing workflows for web apps, forms, and content-heavy sites.

Quick Start

Open a target URL, snapshot the page to generate element refs, then perform actions like filling fields or clicking buttons to complete a task.

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 tasks like form filling and data extraction without manual steps?

Browser automation lets you automate web tasks by using a CLI to navigate pages, fill forms, click controls, take screenshots, and extract data. This enables AI agents to handle repetitive web interactions without manual intervention.

How does snapshot-based browser automation work for identifying page elements?

Snapshot-based browser automation works by taking a snapshot of the target URL to generate compact element refs. You then use these refs in the CLI to deterministically fill fields, click buttons, and extract data from the web page.

Can I use browser automation CLI for multi-session isolation and batch execution?

Yes, browser automation CLI supports multi-session isolation and batch execution. This allows you to run scalable workflows across multiple isolated sessions simultaneously, covering complex multi-step workflows and authentication flows.

What is the best way to automate authentication flows and session persistence for web scraping?

Automating authentication flows and session persistence is best handled through a browser automation CLI with built-in authentication patterns. It maintains login states across multi-step workflows for web scraping and testing.

Does browser automation support visual validation and testing for web apps?

Yes, browser automation supports visual validation and testing for web apps. The CLI can take screenshots during multi-step workflows across dashboards and portals, enabling deterministic testing and visual validation of content-heavy sites.

Do I need any specific dependencies to run web automation scripts?

No specific dependencies are required to run web automation scripts. The skill operates independently with optional extensibility through custom directories for scripts, references, and assets, requiring only a YAML frontmatter for setup.