The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides instructions for the AI agent to use the membrane command-line tool to manage connections, discover available actions, and execute tasks such as creating transcriptions and orders.
[EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli package from npm. This is a vendor-owned utility provided by Membrane for managing integrations.
[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it is designed to ingest and process external content from Happy Scribe.
Ingestion points: Data is ingested through actions like get-transcription, list-transcriptions, and get-export, which retrieve user-controlled transcription text and metadata.
Boundary markers: There are no explicit instructions or delimiters defined to isolate retrieved transcription content from the agent's core instructions.
Capability inventory: The skill has the capability to execute actions and make authenticated proxy requests via the membrane CLI.
Sanitization: The skill does not describe any specific sanitization or filtering of the retrieved content before it is processed by the agent.

happy-scribe