The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill directs the installation of the @membranehq/cli package from the official NPM registry. This package is a vendor-owned resource required for the skill to interact with the Membrane platform.
[COMMAND_EXECUTION]: Instructions involve executing the membrane CLI for authentication (membrane login), connection management (membrane connect), and action execution (membrane action run). These commands are scoped to the intended functionality of the integration.
[CREDENTIALS_UNSAFE]: The skill implements safe secret management practices by delegating credential handling and token refresh logic to the Membrane server, preventing the exposure of raw API keys within the agent's context.

lexoffice