skills.rest
khoi
khoiCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

agent-browser

Automate browser tasks via CLI for AI agents.

16|2|Updated Mar 29, 2018
Search Tags:#cli#data-extraction#web-scraping#browser-automation#automation-testing#agent-browser
One-click install
npx skills add https://github.com/khoi/dotfiles --skill agent-browser-khoi
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/khoi/dotfiles/tree/main/chezmoi/dot_agents/skills/agent-browser
Command: npx skills add https://github.com/khoi/dotfiles --skill agent-browser-khoi

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Browser automation for AI agents to interact with websites, fill forms, click elements, take screenshots, extract data, and test web apps, enabling automated workflows without manual browser control.

Core Features & Use Cases

  • Automated browser control via a CLI, including open/navigate, snapshot with element refs, fill/click interactions, and data extraction.
  • Supports session management, authentication patterns, iframe handling, multi-tab control, and network activity inspection for robust automation pipelines.
  • Use cases include QA automation, data gathering, and reproducible web-task automation across environments.

Quick Start

Open a URL and begin interacting with the page to demonstrate automated browser tasks.

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 via a CLI?▼

Yes, browser automation supports multi-session orchestration, allowing you to manage authentication patterns, handle iframes, and control multiple tabs across different projects simultaneously.

Does this browser automation tool handle iframe interactions and multi-tab control?▼

Yes, browser automation supports multi-session orchestration, allowing you to manage authentication patterns, handle iframes, and control multiple tabs across different projects simultaneously.

What is the best way to automate QA testing for web applications?▼

You can extract data and inspect network activity by navigating to URLs and using snapshot features with element references. This allows robust data gathering and network inspection during automated browser pipelines.

What environment do I need to run reproducible browser automation pipelines?▼

You need an environment that supports CLI execution and defines a root entry point in SKILL.md, with optional directories like scripts and assets to extend capabilities for robust browser automation pipelines.

Why use a CLI for browser automation instead of manual browser control?▼

A CLI for browser automation enables AI agents to execute reproducible workflows, inspect network activity, and orchestrate multiple sessions, eliminating the inconsistencies and limitations of manual browser control.

Related Skills

Explore More Software Engineering Skills→
sigitpoerwosigitpoerwo

template-skill

Define a reusable Claude skill entry with YAML frontmatter in SKILL.md.

Community
Basic
JansenAnalyticsJansenAnalytics
5

data-pad

Load CSV, JSON, or NDJSON files and run SQL-like queries.

Community
Intermediate
CatsofsufferingCatsofsuffering
5

data-engineering

Manage and validate data pipelines and streaming workflows across orchestration and quality tools.

Community
Advanced
marktantongcomarktantongco

playwright-cli

Automate headless browser navigation, clicks, and form submissions for testing and scraping.

Community
Intermediate