Starts a new browser session for you, with options to use a proxy and record the session if needed.

Creates a new task, or if a task with the same name already exists, updates that task instead.

Fetch the displayed content of a webpage, and choose to receive it in either Markdown or HTML format if you prefer.

Simulates a keyboard shortcut by pressing the keys you specify.

Fetches a list of all tasks for your team, organized into pages, so you can easily view and manage them.

Make a custom API request using your authorized account.

Clicks the mouse at the exact location you choose on your screen.

Performs a double-click at the exact location you specify on the screen.

Moves your mouse pointer to the exact location you choose on the screen.

Opens the web page you specify in the current browser session.

Begin with a URL and carry out the specified action.

Runs a specific task within a browser session. You can choose to use a particular version or always run the latest version of the task. If you have a session ID, you can use it, or simply let the system start a new browser session for you.

This module takes a screenshot of any webpage you choose using Chromium. You can easily set the size of the screenshot and adjust capture settings to fit your needs.

Scrolls the page to the exact coordinates you specify, letting you control where the view moves.

Enters the text you provide into the designated field.