The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli package from the official npm registry. This is the standard tool provided by the vendor (Membrane) to manage its integrations.
[COMMAND_EXECUTION]: Uses the membrane CLI to perform operations such as logging in, connecting to services, and running actions. All commands are documented as part of the official platform workflow.
[CREDENTIALS_UNSAFE]: The skill explicitly instructs the agent to let the platform handle credentials server-side and never to ask the user for API keys or tokens, which is a significant security best practice.
[REMOTE_CODE_EXECUTION]: While the platform can dynamically create actions based on descriptions (membrane action create), this process is managed through the vendor's official infrastructure and CLI, which is the intended core functionality of the service.

manifestly-checklists