The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local Node.js scripts (check-ai-patterns.js, check-degeneration.js, normalize-punctuation.js, check-outline-copy.js) to scan and validate novel content. These scripts are provided within the skill package and perform static analysis without any external network connections.- [COMMAND_EXECUTION]: A cross-platform shell command is utilized to invoke Python for precise word count verification of generated text. This ensures the output meets the specific length requirements of novel platforms.- [SAFE]: The skill employs a multi-agent orchestration pattern, spawning specialized sub-agents such as story-architect and character-designer through the platform's local agent registry. These actions are transparent and integral to the intended writing process.- [SAFE]: The skill ingests reference data from local directories like 拆文库/ to provide the agent with style and structure guidance. This ingestion is used for content generation purposes and is limited to project-related files.

story-short-write