The Agent Skills Directory

[SAFE]: The skill package is composed exclusively of markdown files (SKILL.md and several files in references/) that provide text-editing guidelines and heuristics. There are no executable scripts (.sh, .py, .js, etc.) or binary files included in the skill.
[SAFE]: No network activity was detected. The skill does not perform any curl, wget, or API calls to external services.
[SAFE]: There are no external dependencies or package manifests (such as package.json or requirements.txt). All processing logic is contained within the natural language instructions provided to the AI.
[SAFE]: The skill does not attempt to access sensitive file paths, environment variables (other than a configuration path for a style guide), or hardcoded credentials.
[SAFE]: No obfuscation techniques, such as Base64 encoding of commands, zero-width characters, or homoglyph attacks, were found in the documentation.

humanize