The Agent Skills Directory

[SAFE]: The skill operates entirely within the scope of content generation for scriptwriting and narrative design, with no evidence of system-level command execution or privilege escalation.\n- [SAFE]: The skill instructions do not include any hidden URLs, Base64-encoded payloads, or obfuscated text patterns.\n- [SAFE]: While the skill takes user input (a project brief) to generate content for downstream processes, the use of a strict JSON output schema and specific language requirements (English for technical descriptions, Chinese for narrative) provides inherent structural boundaries that mitigate indirect prompt injection risks.\n- [SAFE]: No remote dependencies or external script executions are defined in the skill metadata or body.\n- [SAFE]: All metadata and instructional content are consistent with the stated purpose of professional series development.

series-development