The Agent Skills Directory

[SAFE]: The skill provides instructions for a "Director" persona to manage creative tasks in a film production pipeline. It functions primarily by reading screenplay files and writing structured markdown documentation to the local filesystem.
[DATA_EXPOSURE]: The skill is designed to access files in project/screenplay/ and write outputs to project/continuity/. This behavior is transparently documented and consistent with the skill's stated purpose of maintaining project continuity.
[INDIRECT_PROMPT_INJECTION]: The skill identifies a potential attack surface by ingesting external screenplay data and outputs from other AI skills. However, the risk is negligible as the skill's operations are restricted to generating creative text documents rather than executing code or making network requests.
Ingestion points: The agent reads untrusted data from project/screenplay/* and outputs from other department skills (e.g., cinematographer, character designer).
Boundary markers: The instructions do not define specific delimiters for separating ingested content from the system prompt.
Capability inventory: The skill's capabilities are limited to reading and writing text-based files within the project directory.
Sanitization: There are no explicit instructions to sanitize or validate the content of the ingested screenplays.

creator-director