The Agent Skills Directory

[PROMPT_INJECTION]: The skill contains no instructions aimed at overriding AI behavior, bypassing safety guidelines, or extracting system prompts. It remains strictly focused on its task of logic checking in fiction.
[DATA_EXFILTRATION]: There are no network operations, data exfiltration patterns, or attempts to access sensitive system files. The skill interacts solely with novel-related documentation files (e.g., character lists, timelines).
[EXTERNAL_DOWNLOADS]: The skill does not perform any external downloads, package installations, or remote code execution. All logic is contained within the markdown instructions.
[COMMAND_EXECUTION]: No shell commands, subprocess spawning, or system-level administrative operations are present in the skill instructions.
[OBFUSCATION]: The content is written in clear, plain text (Chinese/English). No Base64, zero-width characters, or other hidden encoding techniques were detected.

continuity