The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Installs the @membranehq/cli package from the NPM registry. This is a verified tool from the skill's author used to facilitate secure communication with the R3 platform.
[COMMAND_EXECUTION]: Instructs the agent to use shell commands via the membrane CLI to authenticate users and manage multi-party workflows. These commands are specific to the skill's core functionality.
[PROMPT_INJECTION]: The skill ingests data from external R3 actions and workflows, representing a potential surface for indirect prompt injection. Ingestion points: Output from membrane action run and action list commands. Boundary markers: Not present. Capability inventory: Command execution through the membrane CLI for managing R3 records and actions. Sanitization: Relies on the underlying platform's handling of action inputs and outputs.

r3