The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the @membranehq/cli package from the NPM registry. This is a vendor-controlled resource necessary for the skill's operation.
[COMMAND_EXECUTION]: The instructions involve executing various membrane CLI commands for authentication (membrane login), connection management (membrane connect), and running integration logic (membrane action run). These are standard operations for the platform.
[CREDENTIALS_UNSAFE]: The skill follows secure practices by explicitly advising against asking users for API keys or tokens, instead utilizing the platform's connection system to manage credentials server-side.

radar