What problem does it solve?
Many web workflows require repetitive, multi-step browser interactions such as form filling, authenticated testing, screenshots, and data extraction, which are time-consuming and error-prone when done manually. This Skill provides a CLI-driven, session-persistent browser interface to automate those interactions and keep context across steps.
Core Features & Use Cases
- Persistent Sessions: Keep browser sessions open across commands to perform complex, multi-step workflows without losing context.
- Inspect & Interact: Inspect page state to get indexed, clickable elements and interact by index with clicks, typing, selection, and keyboard events.
- Data Extraction & Visuals: Capture screenshots, extract text or HTML, evaluate JavaScript, and export cookies or profile data for authenticated tasks.
- Cloud Agents & Profiles: Run asynchronous cloud agents, manage cloud and local profiles, create tunnels for local development, and orchestrate parallel or sequential tasks.
- Use Cases: End-to-end web testing, automated form filling, authenticated site scraping, visual regression checks, and remote agent research or monitoring.
Quick Start
Open a persistent browser session to the target URL, inspect the page state to find element indices, interact with elements as needed, and take a screenshot to verify results.