The Agent Skills Directory

[SAFE]: The skill implements a structured methodology for spatial design, character blocking, and visual continuity. All instructions are aligned with the stated purpose of producing Midjourney prompts and scene packets.
[DATA_EXPOSURE]: No sensitive file access or network communication was detected. The local file paths referenced in SKILL.md (e.g., /Users/baimengke/.agents/skills/...) are internal pointers to other modules in the skill framework and do not access system credentials or private user data.
[REMOTE_CODE_EXECUTION]: The skill does not download external scripts, install unverified packages, or use dynamic execution functions like eval() or exec().
[PROMPT_INJECTION]: The instructions do not contain markers for overriding agent behavior, bypassing safety filters, or extracting system prompts. It uses standard instructional language to guide the AI's creative output.
[COMMAND_EXECUTION]: There is no use of shell commands or the !command`` syntax for dynamic context injection.

scene-design