The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local Python and Node.js helper scripts (such as check-ai-patterns.js and wordcount_core.py) to perform specialized novel-writing tasks like stylistic analysis and word counting. These executions are initiated by the skill's own internal management scripts (scripts/storyctl.py and scripts/build_writer_prompt.py) using subprocess.run and are restricted to the scripts distributed as part of the skill package.
[DYNAMIC_EXECUTION]: Modular loading of skill-internal components is used in scripts/storyctl.py to integrate wordcount and tracking logic. This is implemented using standard Python importlib functions and is limited to loading local skill files for the purpose of modularity.
[INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided novel content and outlines for stylistic and structural validation. While this creates a surface for indirect instructions, the skill's analysis logic is focused on deterministic stylistic metrics and structural consistency rather than responding to natural language instructions found within the novel text.
[DATA_EXFILTRATION]: No evidence of unauthorized network activity or credential harvesting was found. The skill manages its state (e.g., plot progress, author preferences) using local Project project projects and project project proyek project files within the प्रोजेक्ट project folder.

story-long-write