agent-browser

Automate browser tasks including web testing, form filling, and data extraction.

Updated May 25, 2025
One-click install
npx skills add https://github.com/temple-slope/dotfiles --skill agent-browser-temple-slope
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/temple-slope/dotfiles/tree/main/dot_claude/skills/agent-browser
Command: npx skills add https://github.com/temple-slope/dotfiles --skill agent-browser-temple-slope

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

ブラウザ操作の自動化が必要な場面で、テスト、フォーム入力、スクリーンショット取得、データ抽出を効率化します。

Core Features & Use Cases

  • ブラウザ操作の自動化: ページ遷移、要素のクリック・入力・スクロールを繰り返し実行可能にします。
  • スナップショットと参照: ref を使った要素操作とページの状態取得をサポートします。
  • データ収集と検証: ページ情報の取得、タイトル・URL・要素値の抽出をワークフローに組み込みます。

Quick Start

Open a URL and begin automating browser interactions with agent-browser commands.

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 web testing?

Automate browser tasks by leveraging the agent-browser CLI to execute page transitions, element clicks, input filling, and scroll actions across modern web applications. The Skill supports interactive element references and snapshot generation to drive repetitive workflows.

What is the best way to extract data and capture screenshots from web pages?

Data extraction and screenshot capture are handled by generating page snapshots and retrieving element values, titles, and URLs through the agent-browser CLI. This allows you to collect page information and verify page states within your automation workflows.

Does browser automation work with interactive element references and wait conditions?

Browser automation with agent-browser supports interactive element references, snapshot generation, and wait conditions to handle dynamic page states. This ensures your UI automation scenarios execute reliably across modern web applications without timing failures.

How do I run end-to-end UI testing for web applications?

Run end-to-end UI testing by automating browser-based interactions such as page transitions, form filling, and element validation using the agent-browser CLI. The Skill applies to UI automation scenarios across modern web applications to verify application behavior.

Can I use this for data collection across multiple web pages?

Data collection across multiple pages is supported by automating page transitions and extracting titles, URLs, and element values. The agent-browser CLI enables repetitive navigation and data gathering to build comprehensive datasets from web sources.

Do I need the agent-browser CLI to automate web testing and form filling?

The agent-browser CLI is required to automate web testing and form filling, providing the necessary commands for interactive element references, snapshot generation, and wait conditions. No additional dependencies are needed to run these browser automation workflows.