The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions direct the agent to utilize a local CLI tool named story or a fallback script located at ../story-maintenance/scripts/story.js. These tools are used for project maintenance tasks such as indexing, link validation, and generating clue diagrams based on local files.
[INDIRECT_PROMPT_INJECTION]: The skill functions by ingesting and analyzing user-created content within a story project (specifically story.md, plot/timeline.md, and the continuity/clues/ directory). While this involves processing untrusted data to perform genre audits, it is consistent with the primary purpose of the skill and relies on standard project file parsing. -- Ingestion points: Files like story.md, plot/timeline.md, and markdown files in continuity/clues/ are read to extract genre data, clues, and timelines. -- Boundary markers: None explicitly defined in the skill instructions for data ingestion. -- Capability inventory: The skill can execute local shell commands via the story CLI and write new clue files to the continuity/clues/ directory. -- Sanitization: No specific sanitization or filtering of the ingested story content is described in the workflow.

genre-craft