agent-browser

Automate browser interactions for testing, form filling, and data extraction.

67.6k|5.5k|Updated Dec 3, 2025
One-click install
npx skills add https://github.com/code-yeongyu/oh-my-opencode --skill agent-browser-code-yeongyu
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/code-yeongyu/oh-my-opencode/tree/main/src/features/builtin-skills/agent-browser
Command: npx skills add https://github.com/code-yeongyu/oh-my-opencode --skill agent-browser-code-yeongyu

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when you need to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

Core Features & Use Cases

  • Browser automation: open URLs, navigate back/forward, capture screenshots, and inspect page elements.
  • Form interactions: fill inputs, click buttons, and validate results.
  • Data extraction & testing: run end-to-end workflows, validate results across sessions, and generate reproducible outputs.

Quick Start

Use the agent-browser CLI to open a page, snapshot elements, and interact with the page using element refs. Examples: agent-browser open https://example.com agent-browser snapshot -i agent-browser click @e1 agent-browser fill @e2 "text" agent-browser close

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 testing and form filling across multiple pages?

You can automate web testing and form filling by using a CLI tool that integrates with Playwright-backed browsers to open URLs, snapshot elements, and interact with page components using element refs.

What's the best way to extract data from web pages using browser automation?

Data extraction from web pages is handled by navigating to URLs, taking element snapshots, and executing standard interaction commands to gather information across multiple sites reproducibly.

Can I take screenshots during web QA automation workflows?

Screenshots can be captured during web QA automation by issuing a CLI command to open the target URL and capture the page state at any point during the interactive workflow.

How do I click buttons and fill inputs using a browser automation CLI?

You can click buttons and fill inputs by taking an element snapshot to get element refs, then executing commands like 'click @e1' or 'fill @e2' with the corresponding ref values.

Do I need Playwright installed to run browser automation tasks for web testing?

Yes, the solution requires a CLI tool that integrates with Playwright-backed browsers to support element refs, snapshots, and standard interaction commands for web testing.

Why does browser automation fail to locate elements during form submission workflows?

Form submission workflows can fail to locate elements if the page has not fully loaded or if the element snapshot is outdated, requiring a fresh snapshot to capture current element refs.