The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires installing the @membranehq/cli package via NPM and uses npx to execute commands from this package. These resources are provided by the platform vendor for its integration workflow.
[COMMAND_EXECUTION]: The instructions involve running various CLI commands (e.g., membrane login, membrane connect, membrane action run) to manage data flows and authenticate the agent. These commands are localized to the platform's managed environment.
[CREDENTIALS_UNSAFE]: The skill follows security best practices by explicitly instructing the agent to avoid asking for user API keys and instead use managed connections that handle credential lifecycles server-side.

chartiq