The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional markdown text and does not contain any executable code, shell commands, or scripts.
[SAFE]: No network operations, external downloads, or data exfiltration patterns were detected. The skill operates purely within the chat context.
[SAFE]: There are no signs of prompt injection, obfuscation, or attempts to bypass agent safety guidelines. The instructions are focused on the stated purpose of video prompt engineering.
[SAFE]: While the skill ingests user input (video ideas), it lacks any dangerous tools or capabilities (like file system access or API execution) that could be exploited through indirect prompt injection.
[SAFE]: No sensitive information, hardcoded credentials, or persistence mechanisms are present in the provided file.

prompt-writer