The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the installation of the @membranehq/cli package from the official npm registry. This is a scoped package associated with the vendor's platform.
[COMMAND_EXECUTION]: Uses the membrane CLI to perform operations such as searching for connectors, establishing connections, and executing intelligence actions. These commands are restricted to the functionality of the integrated service.
[CREDENTIALS_UNSAFE]: The skill implements secure credential management by explicitly advising the agent never to request API keys or tokens from the user. Instead, it leverages Membrane's managed authentication system to handle the full auth lifecycle.

recorded-future