skills.rest
ytqh
ytqhCOMMUNITY
Explore all skills by this author →
GitHub

agent-browser

Drive web pages via CLI for navigation, form filling, and data extraction.

Updated Feb 4, 2026
Search Tags:#screenshots#CLI#forms#session-management#data-extraction#browser-automation#web-interaction
One-click install
npx skills add https://github.com/ytqh/agent-skills --skill agent-browser-ytqh
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/ytqh/agent-skills/tree/main/skills/agent-browser
Command: npx skills add https://github.com/ytqh/agent-skills --skill agent-browser-ytqh

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Browser automation for AI agents can be tedious to orchestrate manually. This Skill provides a CLI-driven approach to drive web pages, interact with elements, and collect results, reducing setup time and human error.

Core Features & Use Cases

  • Navigate to URLs, fill forms, click elements, take screenshots, and extract data using concise commands.
  • Support for parallel sessions, state persistence, and reusability of workflows via templates and references.
  • Use cases include automated login testing, data extraction from product pages, and end-to-end form automation across multiple sites.

Quick Start

Open a site and capture data with a minimal flow: agent-browser open https://example.com agent-browser snapshot -i agent-browser fill @e1 "sample" agent-browser click @e1 agent-browser wait --load networkidle 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 form filling and data extraction for multiple sites?▼

Automate browser tasks for AI agents by issuing CLI commands to navigate sites and interact with elements. It operates in a Unix-like environment, driving page loads, clicks, and form submissions while capturing screenshots and extracting data.

Does browser automation for AI agents support parallel sessions and state persistence?▼

Yes, browser automation for AI agents supports parallel sessions with state persistence. This allows you to run isolated browser instances simultaneously, maintaining state and reusing workflows across different automation tasks.

How do I take screenshots and capture interactive elements during web automation?▼

Take screenshots and capture interactive elements by using the snapshot command with interactive flags. This generates references for clickable elements, enabling precise targeting for subsequent fill and click commands.

Do I need a specific environment to run CLI-based browser automation for agents?▼

Yes, you need a Unix-like environment with the agent-browser CLI installed. This setup provides the necessary command-line interface to drive web pages, manage sessions, and execute automation commands without requiring manual browser orchestration.

What is the best way to reuse web interaction workflows across different tasks?▼

The best way to reuse web interaction workflows is by utilizing optional templates and references for guided automation. This approach standardizes navigation, clicking, and data extraction sequences across multiple recurring tasks.

Related Skills

Explore More Software Engineering Skills→
llm011llm011
9

agent-browser

Automates browser interactions for command-line web workflows.

Official
Advanced
lemonhalllemonhall
5

headless-web-viewer

Render web pages headlessly with Playwright and extract visible text.

Community
Intermediate
valkryhxvalkryhx
6

playwright-cli

Automate browser interactions via command-line for navigation, form submission, and screenshots.

Community
Intermediate
FunnelEnvyFunnelEnvy
1

playwright-browser

Automate browser navigation, element interactions, form filling, and screenshots with Playwright.

Official
Intermediate