The Agent Skills Directory

[COMMAND_EXECUTION]: The skill coordinates the execution of bundled Node.js and Python scripts (e.g., check-ai-patterns.js, tracking_commit.py) to perform stylistic analysis and manage story state. These commands are executed locally within the user's project environment to provide automated feedback.
[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by ingesting and analyzing untrusted story text. However, it mitigates this by using specialized sub-agent personas and structured analysis rubrics. Ingestion points are the story files; boundary markers are set by specific sub-agent prompts; capabilities include spawning agents and local file writes; and the skill relies on instructional structure rather than text sanitization to manage input risks.

story-review