The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the official @membranehq/cli package from npm. This tool is the authorized interface for the Membrane platform, as noted in the vendor's documentation.- [COMMAND_EXECUTION]: The skill executes membrane CLI commands to manage authentication and run integration tasks. These commands are the standard and expected method for interacting with the platform's features.- [PROMPT_INJECTION]: The skill ingests data from Papyrs pages, users, and forms, creating an indirect prompt injection surface.
Ingestion points: Retrieval of action schemas and execution results from Papyrs via the membrane CLI as documented in SKILL.md.
Boundary markers: No specific boundary markers or instructions for the agent to disregard potential instructions within the Papyrs data are provided.
Capability inventory: The skill can execute actions and dynamically create new ones using the membrane action run and membrane action create commands.
Sanitization: The instructions do not define any explicit sanitization or validation of the data retrieved from Papyrs before it is consumed by the agent.

papyrs