The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package from NPM. This is a legitimate installation of the vendor's CLI tool required for the skill's functionality.
[COMMAND_EXECUTION]: The skill uses various membrane CLI commands to manage authentication (membrane login), create connections (membrane connect), and execute actions (membrane action run). These commands are standard operations for interacting with the Membrane platform.
[SAFE]: Authentication is handled through a secure browser-based flow or a headless authorization code process, ensuring that the agent does not directly handle or store sensitive user credentials or API keys.
[SAFE]: The skill explicitly advises against asking users for API keys, instead utilizing the platform's built-in credential management and action discovery features.

chatbase