agent-browser

Automate browser navigation, form filling, and data extraction via command line.

Updated Mar 15, 2026
One-click install
npx skills add https://github.com/i0switch/yoyaku-tosho --skill agent-browser-i0switch
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/i0switch/yoyaku-tosho/tree/main/.github/skills/agent-browser
Command: npx skills add https://github.com/i0switch/yoyaku-tosho --skill agent-browser-i0switch

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

The AI agent browser automation skill enables driving a local browser from the command line to automate common web tasks such as navigation, form filling, clicking, and data extraction, reducing manual repetitive work.

Core Features & Use Cases

  • Compact, snapshot-driven refs: generate minimal @e references from page snapshots to drive interactions.
  • End-to-end browser workflows: open URLs, fill forms, click buttons, take screenshots, and extract content or test apps.
  • Real-world scenarios: automate login flows, data capture, and QA checks across local or remote environments.

Quick Start

Open a website, snapshot the page to identify element refs, and perform clicks, fills, or extractions to complete a browser 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 browser tasks like form filling and navigation with an AI agent?

Automate browser tasks by driving a local browser from the command line using a snapshot-driven workflow. You generate minimal @e references from page snapshots to direct the AI agent to perform clicks, form fills, and data extraction.

What are snapshot-driven refs and how do they work for web testing?

Snapshot-driven refs are minimal @e references generated from page snapshots. They identify specific page elements so the AI agent can accurately target and interact with them for automated web testing.

Do I need a local browser driver to automate web interactions?

Yes, a local browser driver is required to automate web interactions. It acts as the bridge allowing the AI agent to execute navigation, form filling, and data extraction across local or remote environments.

Can I use this for automated testing and data extraction across remote environments?

Yes, this approach supports automated testing and data extraction across local or remote environments. It handles opening URLs, taking screenshots, and running QA checks to capture real-world data.

What is the best way to automate login flows and QA checks without manual repetitive work?

The best way to automate login flows and QA checks is using compact snapshot-driven refs to drive end-to-end browser workflows. This reduces manual repetitive work by letting the AI agent handle form filling and clicks.