The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the membrane CLI tool for managing the integration lifecycle, including logging in, creating data connections, and running automated actions. This is the intended functional mechanism of the skill.
[EXTERNAL_DOWNLOADS]: The instructions guide the installation of the @membranehq/cli package from the public NPM registry. This is a vendor-owned resource used for interacting with the Membrane platform.
[REMOTE_CODE_EXECUTION]: The skill uses npx @membranehq/cli to execute commands, which involves fetching and running the vendor's CLI tool directly.
[CREDENTIALS_UNSAFE]: The skill documents a secure authentication flow using membrane login. It explicitly advises against manual credential management, instructing the agent to let the platform handle secrets server-side.

safegraph