Humanizer (Academic): register-aware AI-tell removal

Polish an academic draft so it reads like a careful human author and conforms to its register's norms. Two modes: English journal articles (en-journal) and Chinese doctoral dissertations (zh-dissertation).

The analysis kernel is the "Signs of AI writing" taxonomy from Wikipedia (WikiProject AI Cleanup), re-gated for academic register: several general-prose defaults are backwards in a journal or dissertation, so each tell is kept, calibrated, or disabled rather than applied blindly. The heavy content lives in references/; this file is the router and the behavioral rules.

In the python command below, <skill-dir> is this skill's base directory, announced when the skill loads. Substitute that literal path; it is not an environment variable. The bundled script self-locates, so only the path needs to resolve.

诚信边界 (behavioral hard rule)