The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install @membranehq/cli from the npm registry. This is a legitimate package provided by the skill's vendor to facilitate authentication and API interaction.
[COMMAND_EXECUTION]: The skill uses various membrane CLI commands to manage connections and execute actions. These operations are scoped to the Ataccama integration and include built-in mechanisms for machine-readable output and error handling.
[CREDENTIALS_UNSAFE]: The skill follows security best practices by explicitly advising against asking for API keys or tokens. It uses a server-side connection model where credentials are managed by the Membrane platform rather than being stored locally or handled by the agent.

ataccama