The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the installation of the @membranehq/cli package from the npm registry. This is the official command-line tool provided by the vendor (Membrane) to facilitate the integration.
[COMMAND_EXECUTION]: The skill utilizes the membrane CLI for various operations, including authentication (membrane login), connection management (membrane connect), and executing VideoAsk API actions (membrane action run). These commands are necessary for the skill's stated purpose of managing VideoAsk data.
[PROMPT_INJECTION]: The skill processes external data from VideoAsk responses. While this represents an ingestion point for untrusted data, the skill limits the risk by using structured actions and recommending the use of the vendor's platform for secure communication.
Ingestion points: Data is ingested through membrane action run and membrane request calls in SKILL.md.
Boundary markers: Not explicitly defined in the provided instructions.
Capability inventory: The agent can execute shell commands via the membrane CLI as documented in SKILL.md.
Sanitization: Not specified; however, the skill promotes using pre-built actions which handle data mapping and edge cases.

videoask