The Agent Skills Directory

[SAFE]: The skill is entirely instructional and does not contain any executable scripts, binary files, or network-enabled code. It functions as a complex system prompt for AI assistants.
[SAFE]: The installation instructions use standard npx and git clone commands for legitimate tools (skills.sh registry and GitHub), which are typical for agent skill distribution. No suspicious or obfuscated URLs were found.
[SAFE]: Prompt instructions focus on maintaining high editorial standards, professional tone, and medical accuracy. There are no attempts to bypass safety filters or extract system prompts. On the contrary, the skill imposes strict negative constraints on the AI (banned phrases and prohibited medical claims).
[SAFE]: Data processing is limited to natural language text for writing and editing. There is no access to sensitive system files or credentials.

wechat-writing