agent-browser

Automate browser navigation, form filling, clicks, and data extraction via snapshots.

Updated Apr 2, 2026
One-click install
npx skills add https://github.com/andrelandgraf/caspers-kitchen --skill agent-browser-andrelandgraf
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/andrelandgraf/caspers-kitchen/tree/main/.agents/skills/agent-browser
Command: npx skills add https://github.com/andrelandgraf/caspers-kitchen --skill agent-browser-andrelandgraf

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Automates browser interactions and data extraction for AI agents, removing manual UI tasks and enabling repeatable web automation.

Core Features & Use Cases

  • Navigate and interact with pages using refs: take snapshots to build a stable element map and drive actions without brittle selectors.
  • Snapshot-driven interactions: perform clicks, fills, and form submissions using short, stable refs.
  • Session and authentication handling: manage multiple sessions, save and restore cookies/storage, and support auth flows.
  • Data extraction and reporting: extract text, attributes, and page structure, plus generate screenshots and PDFs for records.
  • Testing and automation workflows: automate repetitive browser tasks, validate flows, and record sessions for debugging.

Quick Start

Open a website, snapshot the page, fill a form, and verify results end-to-end.

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 browser interactions without brittle CSS selectors?

Browser automation uses snapshot-driven interactions to build a stable element map, letting you perform clicks and form filling using short, stable refs instead of brittle selectors.

Can I manage multiple browser sessions and handle authentication flows for automated testing?

Yes, session management handles multiple browser sessions, saves and restores cookies and storage, and supports authentication flows to enable reliable automated testing.

How do I extract data and generate records from web pages during UI automation?

Data extraction captures text, attributes, and page structure during UI automation, and can generate screenshots and PDFs to create permanent records of the web page state.

What is the best way to automate login flows and validate web apps end-to-end?

Automating login flows and validating web apps requires a command surface including open, snapshot, fill, click, wait, and session management to operate reliably across multi-session scenarios.

Does this browser automation approach work for repetitive web testing and debugging?

Yes, browser automation supports testing workflows by automating repetitive browser tasks, validating flows, and recording sessions for later debugging.