The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Fetches and installs the @membranehq/cli package from the NPM registry. This package is the official command-line interface for the Membrane platform.
[COMMAND_EXECUTION]: Guides the agent through using membrane login, membrane action, and membrane request commands to manage Tray integrations and automate workflows.
[SAFE]: Adheres to security best practices by instructing the agent never to request API keys or sensitive tokens directly from users, instead utilizing Membrane's server-side connection management.
[SAFE]: Ingests and processes data from external Tray API endpoints.
Ingestion points: Output from actions and proxy requests in SKILL.md.
Boundary markers: None explicitly defined in the skill instructions.
Capability inventory: Subprocess calls via the membrane CLI to execute network operations and data modifications.
Sanitization: Authentication and request construction are handled by the Membrane CLI.

tray