agent-browser

Automate browser interactions for web testing, form handling, and content extraction.

4.3k|446|Updated Jan 25, 2026
One-click install
npx skills add https://github.com/m1heng/clawdbot-feishu --skill agent-browser-m1heng
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/m1heng/clawdbot-feishu/tree/main/.agents/skills/agent-browser
Command: npx skills add https://github.com/m1heng/clawdbot-feishu --skill agent-browser-m1heng

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill enables automated browser interactions for web testing, form filling, content extraction, and UI verification, reducing manual repetitive work and enabling repeatable, recordable demos.

Core Features & Use Cases

  • Snapshot-based automation:Capture compact element refs via snapshots and interact deterministically using @e identifiers.
  • End-to-end browser actions:Open pages, navigate, click, fill forms, type, and submit, with support for waiting and state checks.
  • Observability & data extraction:Get text, HTML, attributes, page title, and URL; take screenshots or PDFs for documentation and verification.
  • Advanced workflows:Record sessions, proxy and network controls, and multi-session management for concurrent testing and demos.

Quick Start

  • agent-browser open https://example.com
  • agent-browser snapshot -i
  • agent-browser click @e1
  • agent-browser fill @e2 "sample text"
  • agent-browser screenshot

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 without writing complex scripts?

Automate web testing and form filling by using compact CLI commands to open pages, capture snapshots, and interact with elements via deterministic @e identifiers, reducing repetitive work without complex scripting.

What is snapshot-based browser automation and how does it work?

Snapshot-based browser automation captures compact element references from a page snapshot, allowing you to click or fill forms deterministically using @e identifiers instead of fragile CSS selectors.

How do I extract text and take screenshots during automated web navigation?

Extract text and take screenshots during web navigation by issuing CLI commands to get page title, URL, HTML, and attributes, or capture visual outputs like screenshots and PDFs for verification.

Can I manage multiple browser sessions and use proxies for concurrent web testing?

Manage multiple browser sessions and configure proxy and network controls to enable concurrent web testing, session recording, and repeatable automated demos across different network environments.

Does this browser automation tool require any external dependencies?

No external dependencies are required. It functions as a Bash-based CLI tool, providing open, snapshot, click, fill, get, screenshot, wait, and recording capabilities natively.

What is the best way to handle waiting for page states during automated content extraction?

Handle waiting for page states during content extraction by using built-in wait and state check commands before executing snapshot or get operations, ensuring elements are fully loaded for deterministic extraction.