The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to perform project maintenance using the story CLI tool or a fallback Node.js script.
Executed commands include story reindex ., story links ., story validate ., story continuity ., and story pacing ..
The fallback mechanism uses bun run story -- or node ../story-maintenance/scripts/story.js, referencing a script in a neighboring directory within the repository structure.
[INDIRECT_PROMPT_INJECTION]: The skill's primary function involves reading and updating external story project files (scenes, characters, plot, and continuity logs).
Ingestion points: Reads content from scenes/, characters/, plot/, and continuity/ directories.
Boundary markers: The workflow emphasizes structured data using YAML frontmatter and specific markdown headers (e.g., ## Planning, ## Scene Card, ## Sequel) to separate instructions from narrative content.
Capability inventory: The skill has the ability to write to the local filesystem and execute the story CLI validation tools.
Sanitization: The skill relies on specific machine-readable state fields (e.g., outcome, sequel, flashback-to) and the story validate command to ensure project consistency.

scene-craft