The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill recommends installing the @membranehq/cli package from npm. This is the official tool provided by the platform vendor for managing integrations and authentication.
[COMMAND_EXECUTION]: Various CLI commands such as membrane login, membrane connect, and membrane action run are utilized to interact with the service. These commands are well-defined and restricted to the functionality required for the skill's operation.
[CREDENTIALS_UNSAFE]: The instructions explicitly guide the agent to avoid direct handling of sensitive API keys or tokens, instead delegating credential lifecycle management to the Membrane platform. This is a secure approach to secret management in AI agent environments.

carapi