The Agent Skills Directory

[COMMAND_EXECUTION]: The skill workflow involves executing a local Python script scripts/screenplay_consistency.py with a variable project argument to verify manifest alignment.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from screenplay and character profile files which represents an attack surface for indirect instructions.
Ingestion points: The workflow reads CHARACTER_PROFILE.md, 01_story/characters.md, and screenplay content.
Boundary markers: No explicit delimiters or instructions to ignore embedded prompts are present in the skill instructions.
Capability inventory: The skill has permissions to update production manifests and execute local validation scripts.
Sanitization: No content sanitization or structured data validation is defined for the external text content being processed.

revise-screenplay