The Agent Skills Directory

[SAFE]: The skill provides instructional content focused on writing style and craft. It defines vocabulary restrictions, structural patterns, and tonal principles aimed at improving the human-like quality of generated text.
[SAFE]: Extensive external documentation and research are provided in the references directory. All analyzed links point to reputable sources including academic repositories (arXiv, NIH/PMC, ACM Digital Library), educational institutions (Stanford, Cornell), and established technology or publishing domains (Nature, Scientific American, MIT Technology Review). There are no attempts to download or execute remote code.
[SAFE]: No obfuscation techniques, hidden characters, or encoded payloads were detected in the skill instructions or reference files.
[SAFE]: The skill does not request or use any sensitive tools, credentials, or file system access beyond processing the user's writing request.
[SAFE]: While the skill processes user input via $ARGUMENTS, the lack of dangerous capabilities (such as shell access or network operations) effectively prevents exploitation through indirect prompt injection.

human-writing