The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use the membrane command-line interface to manage sessions, authenticate, and execute actions against the Mezmo API.
[EXTERNAL_DOWNLOADS]: Installs the @membranehq/cli package from the npm registry. This package is the official tool maintained by the skill's authoring organization.
[PROMPT_INJECTION]: The skill processes log data and action schemas retrieved from Mezmo, creating a surface for indirect prompt injection.
Ingestion points: Command-line output from membrane action run and membrane action list commands described in SKILL.md.
Boundary markers: None present in the instructions to delimit external data from agent commands.
Capability inventory: Subprocess execution through the membrane CLI.
Sanitization: No explicit sanitization or filtering of retrieved log content is specified.

mezmo