✍️
Writing

CNKI AIGC Rewrite

by qingshanliuci

CNKI AIGC Rewrite is a Writing skill for Claude Code, published by qingshanliuci in cnki-aigc---skill.

36 stars2 forkson qingshanliuci/cnki-aigc---skillAdded 2026/07/16+6% in starsRepository updated 2026/05/01
academic-writingai-detectionaigcchinesechinese-nlpclaudeclaude-skillcnkiprompt-engineeringthesis
Install in seconds
Install CNKI AIGC Rewrite
Copy CNKI AIGC Rewrite into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/qingshanliuci/cnki-aigc---skill ~/.claude/skills/cnki-aigc---skill

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/qingshanliuci/cnki-aigc---skill.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
SKILL.md in qingshanliuci/cnki-aigc---skill
Installs to
~/.claude/skills/cnki-aigc---skill
Collection
The only skill cataloged from this repository
Category
Writing1361 skills

What CNKI AIGC Rewrite does

Rewrites Chinese academic paper paragraphs flagged as AI-generated by CNKI's AIGC detector, reducing detection scores by altering sentence patterns while preserving facts, numbers, terminology, and citations.

CNKI AIGC Rewrite is cataloged under Writing on DirSkills. CNKI AIGC Rewrite comes from a repository tagged academic-writing, ai-detection, aigc, chinese and chinese-nlp.

Documentation

README

When to use

用户做以下任一动作时触发:

  • 提到"知网AIGC检测""AI率""红色显著""降AIGC""降AI率"
  • 上传AIGC检测报告(PDF/截图)
  • 贴出一段被标为红色或疑似的论文文本
  • 询问"怎么改这段不像AI写的"

仅适用于中文学术论文(学位论文、期刊投稿、学术报告)。不适用于:

  • 摘要/Abstract(结构化文本天然像AI,但通常不计入AI字符数)
  • 文献引用密集段("X等(2020)发现……"难以脱模板)
  • 研究方法固定描述句("采用双向固定效应模型"是规范表达)
  • 非学术文本(自媒体、营销文案、小说)

核心认知:检测器抓的是什么

知网AIGC检测器不是抓"AI写的",而是抓5种语言模式。理解这5种模式比记规则更重要:

模式1:句法节奏的可预测性 — LLM输出句长集中在20-35字(正态分布),人类写作是齐夫分布(少数特别长、少数特别短、多数中等)。改写要刻意打破均匀。

模式2:信息密度的均匀性 — LLM每段密度都差不多,人类写作有"高密度论证段"和"低密度铺陈段"。检测器跟踪段级特征值方差。

模式3:术语的句法位置固定 — LLM倾向把术语放在主语位置("逆向技术溢出转化为创新能力"),人类更常放在话题或宾语位置("企业把外部技术转化为创新能力")。不动术语本身,但挪动它在句子里的角色

模式4:连接词功能重叠 — LLM爱用"因此""从而""进而""由此",功能高度重叠都在做因果推进。人类的连接词承担多种功能:补充(也就是说)、转述(换句话说)、强调(——)、对照(同向)。

模式5:模板段功能全等性 — 三/四项工整排比、抽象名词链、段尾元话语收束、模板化报告句、平行铺陈+末尾收束。这5个具体特征是上面5种模式的表层呈现。

This is the opening of the README. Read the full README on GitHub.

Frequently asked about CNKI AIGC Rewrite

  • How does CNKI AIGC Rewrite compare to other Writing skills?

    CNKI AIGC Rewrite ranks #1259 by stars among the 1361 Writing skills in this catalog. The most-starred ones next to it are Article Writing, Social Media Content Calendar and Knowledge Comic Creator. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of CNKI AIGC Rewrite against them. Open each page to compare what they document and how they install.