The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill guides the installation of the @membranehq/cli package from the official npm registry. This is a legitimate tool provided by the vendor to facilitate communication between the agent and external services.
[COMMAND_EXECUTION]: Instructions include the execution of membrane CLI commands to perform tasks such as logging in, connecting to services, and running API actions. These operations are within the expected scope of a workflow automation skill and do not involve unauthorized privilege escalation or persistence mechanisms.
[CREDENTIALS_UNSAFE]: The skill explicitly advises against hardcoding API keys or secrets, instead utilizing a connection-based authentication system managed by the Membrane platform, which is a recommended security practice.

safebase