The Agent Skills Directory

[SAFE]: The skill package is entirely instructional, containing only Markdown files and JSON evaluation cases. There are no executable scripts, binaries, or shell commands included in the files.
[SAFE]: No indicators of malicious activity such as hardcoded credentials, obfuscation, or suspicious external network calls were found during the analysis.
[SAFE]: The instructions and evaluation criteria explicitly guide the agent to adhere to platform safety standards, including truthful disclosure of branded content and the refusal to generate prohibited content like deepfakes or fake endorsements.

tiktok-video-publishing