skills.rest
msichterman
msichtermanCOMMUNITY
Explore all skills by this author →
Website𝕏@mattsichtermanGitHub

agent-browser

Automate browser navigation, form filling, clicks, screenshots, and data extraction.

Updated Feb 3, 2026
Search Tags:#automation#data extraction#state management#AI agents#web testing#CLI#browser
One-click install
npx skills add https://github.com/msichterman/templatesick --skill agent-browser-msichterman
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/msichterman/templatesick/tree/main/.agents/skills/agent-browser
Command: npx skills add https://github.com/msichterman/templatesick --skill agent-browser-msichterman

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides a programmable way to control a browser for AI agents, enabling automated web interactions such as navigation, form filling, clicks, screenshots, data extraction, and automated testing without manual GUI intervention.

Core Features & Use Cases

  • End-to-end browser automation: drive a browser from a concise command surface to perform tasks like open pages, fill forms, take snapshots, and extract data.
  • Rich interaction and debugging: snapshot refs, interact with elements via refs, and re-snapshot after navigation or dynamic changes.
  • Use Case: automate customer onboarding by navigating to signup, filling fields, submitting, and validating the result across web and mobile contexts.

Quick Start

Use agent-browser to open a URL, snapshot the page, and interact with elements using the generated 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 browser interactions for AI agents without manual GUI intervention?▼

Automate browser interactions for AI agents by using a CLI to drive page navigation, fill forms, click elements, and extract data. This provides a programmable way to execute web tasks without manual GUI intervention.

How does snapshot-based element interaction work in web testing automation?▼

Snapshot-based interaction captures page elements and assigns refs, allowing you to interact with elements via refs and re-snapshot after navigation or dynamic changes to ensure accurate web testing automation.

Can I use browser automation for tasks across both desktop and mobile contexts?▼

Yes, browser automation supports cross-device automation across desktop and mobile contexts, enabling you to perform tasks like customer onboarding, login flows, and form filling on various device profiles.

Does this browser automation tool support multi-session isolation and proxies?▼

Yes, the browser automation tool supports multi-session isolation alongside optional proxies and retries, allowing you to manage concurrent automated tasks and handle network routing securely.

What is the best way to extract data and capture screenshots from web apps programmatically?▼

The best way to extract data and capture screenshots from web apps programmatically is using a CLI that drives a browser to navigate pages, capture screenshots, and harvest data via element refs.

How do I maintain state persistence during automated login flows and form filling?▼

Maintain state persistence during automated login flows and form filling by utilizing the CLI's built-in state management features, which preserve session data across multiple navigation and interaction steps.

Related Skills

Explore More Software Engineering Skills→
agent0aiagent0ai
1.4k

Screenshots

Capture browser-rendered pages or DOM elements as PNG images.

Official
Basic
dpladpla
35

dpla-community-webs-ingest

Automate Community Webs data harvesting and ingestion into the DPLA pipeline via EC2 and SSM.

Official
Intermediate
DayronDLRDayronDLR
3

sap-orchestrator

Route natural language SAP queries to relevant agents and commands.

Community
Advanced
drewsephskidrewsephski
1

browser

Automate headless browser tasks for web testing and data extraction.

Community
Intermediate