The Agent Skills Directory

[COMMAND_EXECUTION]: The skill directs the agent to execute a Python script (emulo.py) to initialize user profiles and creative configuration. It also invokes Node.js scripts (shoot.mjs, frames.mjs) and standard system utilities including ffmpeg and ffprobe to perform media verification and metadata analysis.
[DYNAMIC_EXECUTION]: The skill employs dynamic path resolution to locate its primary initialization script (emulo.py) by searching parent directories and subsequently executes it using the resolved absolute path.
[INDIRECT_PROMPT_INJECTION]: The skill is susceptible to instruction influence through external data ingestion. Ingestion points: Profile configuration files whose paths are returned by the emulo.py script and local documentation files (videos/README.md). Boundary markers: The skill lacks explicit delimiters or "ignore" instructions when processing the contents of these external files. Capability inventory: The skill maintains capabilities for command execution (Python, Node.js, ffmpeg) and local file writing. Sanitization: No validation or filtering is performed on the ingested configuration content before it is used to define the agent's creative constraints and persona.

video