AI Summary检测和改写中文 AI 生成文本的完整工具链。可独立运行（统一 CLI 或独立脚本），也可作为 LLM prompt 指南使用。 所有脚本在 目录下，纯 Python，无依赖。 v3.0 所有阈值都基于 HC3-Chinese 300+300 人类/AI 样本的 Cohen's d 校准：
Install
Copy this and paste it into Claude Code, Cursor, or any AI assistant:
I want to install the "humanize-chinese" skill in my project. Please run this command in my terminal: # Install skill into your project mkdir -p .claude/skills/humanize-chinese && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/humanize-chinese/SKILL.md "https://raw.githubusercontent.com/voidborne-d/humanize-chinese/main/SKILL.md" Then restart Claude Code (or reload the window in Cursor) so the skill is picked up.
Description
Detect and humanize AI-generated Chinese text. 20+ rule detection categories plus 8 HC3-calibrated statistical features (sentence-length CV Cohen's d=1.22, short-sentence fraction d=1.21, comma density, GLTR rank buckets, DivEye surprisal). Unified CLI: ./humanize {detect,rewrite,academic,style,compare}. 7 style transforms (casual/zhihu/xiaohongshu/wechat/academic/literary/weibo), 40 paraphrase templates, 122 academic replacements, CiLin synonym expansion with semantic filter. Academic paper AIGC reduction for CNKI/VIP/Wanfang (知网/维普/万方 AIGC 检测降重), 11 academic detection dimensions. Pure Python, no dependencies. v3.0.0 — HC3 accuracy 73%, humanize avg delta +4.2 on HC3-Chinese 100-sample. Use when user says: "去AI味", "降AIGC", "人性化文本", "humanize chinese", "AI检测", "AIGC降重", "去除AI痕迹", "文本改写", "论文降重", "知网检测", "维普检测", "AI写作检测", "让文字更自然", "detect AI text", "humanize text", "reduce AIGC score", "make text human-like", "去ai化", "改成人话", "去机器味", "降低AI率", "过AIGC检测"
Humanize Chinese AI Text v3.0
检测和改写中文 AI 生成文本的完整工具链。可独立运行（统一 CLI 或独立脚本），也可作为 LLM prompt 指南使用。 v3.0 亮点： HC3 accuracy 51→73% (+22 pts)；句长 CV Cohen's d=1.22 最强统计特征；40 paraphrase 模板 + 122 学术替换；统一 CLI + --quick 18× 速度。
统一 CLI（推荐）
`bash ./humanize detect 文本.txt -v # 检测 + 详细 ./humanize rewrite 文本.txt -o 改后.txt --quick # 快速改写（18× 速度） ./humanize academic 论文.txt -o 改后.txt --compare # 学术降重 + 双评分对比 ./humanize style 文本.txt --style xiaohongshu # 风格转换 ./humanize compare 文本.txt -a # 前后对比 `
独立脚本形式（等价）
所有脚本在 scripts/ 目录下，纯 Python，无依赖。 `bash
检测 AI 模式（20+ 规则维度 + 8 统计特征，0-100 分）
python scripts/detect_cn.py text.txt python scripts/detect_cn.py text.txt -v # 详细 + 最可疑句子 python scripts/detect_cn.py text.txt -s # 仅评分 python scripts/detect_cn.py text.txt -j # JSON 输出
Discussion
Health Signals
My Fox Den
Community Rating
Sign in to rate this booster