The Agent Skills Directory

[COMMAND_EXECUTION]: The skill invokes local Python scripts located within the skill's directory structure to perform specialized tasks.
Evidence: helpers/python/check_timeline_continuity.py is used to audit story consistency.
Evidence: generate_fiction_docx.py is executed to generate formatted manuscript files (DOCX/EPUB).
[INDIRECT_PROMPT_INJECTION]: The skill acts as a data processor for user-provided fiction concepts, which represents a potential attack surface for indirect injection if the processed data contains instructions.
Ingestion points: Phase 1 (story-concept-intake) and Phase 5 (beta-reader-critique-simulator) accept external story data and simulated feedback.
Boundary markers: None specified in the orchestrator instructions.
Capability inventory: The skill has the ability to write multiple markdown files, generate DOCX/EPUB files, and execute local Python scripts.
Sanitization: No explicit sanitization or filtering logic is defined for the external story content.

fiction-book-orchestrator