| name | humanizer-paper |
| description | Register-aware academic language polisher for English journal articles and Chinese doctoral dissertations: removes AI-writing tells while keeping academic norms. Use whenever the user wants to polish, 降AI味, 润色, or norm-check an academic draft, paper section, abstract, or 学位论文 paragraph. Polishes the author's own drafts only — not for laundering generated text past Turnitin or 知网 AIGC detection.
|
| category | research-learning-knowledge |
| tags | ["academic-writing","humanizer","ai-tells","journal","dissertation","zh","en","polishing"] |
| version | 3.0.0 |
| argument-hint | [text-or-file] [--target en-journal|zh-dissertation] [--section abstract|intro|methods|results|discussion|conclusion] [--style STYLE] [--check-only] |
| license | MIT |
| allowed-tools | Read, Write, Edit, Grep, Glob, AskUserQuestion, Bash(python *) |
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)
This skill polishes the author's own draft for clarity and for compliance
with academic norms. It is not a detector-evasion tool.
- The legitimate, transferable techniques here — varying cadence, calibrating
hedging, tightening argumentation, enforcing terminology consistency,
protecting citations — apply only to text the author actually wrote or
substantively authored.
- If the request is framed as "rewrite this generated text so it passes Turnitin
/ 知网 AIGC / an AI detector", refuse that framing. Redirect to the
legitimate goal: improving real originality (add real data and citations,
deepen analysis, fix norms). High AIGC rate is treated by many institutions as
academic misconduct; do not position this skill as a way around that.
When to use
- Polish an English journal/conference manuscript or section to remove AI tells
while keeping formal register, hedging, and section-appropriate passive.
- Polish a Chinese 学位论文 (摘要/引言/方法/结果/讨论/结论/致谢) for AI tells and
GB punctuation, terminology unification, and AIGC quantitative self-check.
- Norm-check a draft (
--check-only) and report mechanical tells without rewriting.
When NOT to use
- Generic / non-academic prose (blog posts, essays, marketing). This skill's
defaults are tuned for academic register; for general "make it sound human" use
an upstream generic humanizer, not this one.
- Paper intake, reading, synthesis, or literature review (skim, deep-read,
card, compare, gap map, review outline, normalize a DOI/arXiv source). That is
, not this skill. This skill edits ;
analyzes .
