skills.rest
han-so1omon
han-so1omonCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

agent-browser

Automate browser interactions for AI agents to navigate pages and fill forms.

1|Updated Apr 7, 2026
Search Tags:#authentication#cli#session-management#web-testing#data-extraction#browser-automation#form-filling
One-click install
npx skills add https://github.com/han-so1omon/ikam --skill agent-browser-han-so1omon
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/han-so1omon/ikam/tree/main/skills/agent-browser
Command: npx skills add https://github.com/han-so1omon/ikam --skill agent-browser-han-so1omon

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Browser automation tasks for AI agents are repetitive and error-prone; this Skill provides a CLI to drive web pages, fill forms, click controls, take screenshots, extract data, and test web apps in a deterministic, scriptable way.

Core Features & Use Cases

  • Open and navigate to websites with a stable, snapshot-derived ref system for interaction
  • Fill forms, click buttons, capture screenshots, extract text, and run automated checks across single or multiple sessions
  • Use cases include automation of data extraction, login/auth flows, onboarding forms, and UI testing with reproducible steps across environments.

Quick Start

Open a URL, snapshot the page to obtain element refs, then perform actions using those refs.

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 AI agents?▼

Automate web form filling and data extraction by using a CLI to navigate pages, snapshot elements for stable refs, and execute actions like clicking and text extraction deterministically across sessions.

How does browser automation handle authentication and login flows for web testing?▼

Browser automation handles authentication by supporting multi-session workflows, allowing AI agents to manage login states, execute auth flows, and maintain session access controls during web testing.

Can I run automated UI testing across single-page applications with this tool?▼

Yes, you can run automated UI testing across single-page applications and standard websites by capturing screenshots, interacting with snapshot-derived refs, and executing reproducible steps with enforced timeouts.

What is the best way to interact with web page elements during browser automation?▼

The best way to interact with web page elements is to snapshot the page to obtain stable element refs, then use those refs to perform actions like clicking buttons, filling forms, and extracting data.

How do I manage multiple browser sessions for concurrent web automation tasks?▼

Manage multiple browser sessions by utilizing built-in session management and access controls, enabling concurrent web automation workflows like parallel data extraction or isolated testing environments.

Related Skills

Explore More Software Engineering Skills→
C0ntr0lledCha0sC0ntr0lledCha0s
3

managing-docs

Automate project documentation structure and governance with configurable tooling.

Community
Advanced
profmikegreeneprofmikegreene
1

plan-ingestion

Parses pilot plans and hypotheses into structured JSON or tabular data for downstream analysis.

Community
Intermediate
dpalferydpalfery

browser-testing

Automate web UI testing and end-to-end validation with Playwright MCP.

Community
Advanced
jonathanmalkinjonathanmalkin
61

agent-browser

Automate web browser interactions via command-line interface for navigation, form filling, and data extraction.

Community
Advanced