Help us improve
Share bugs, ideas, or general feedback.
From antigravity-awesome-skills
Detects AI-like patterns in Chinese text and rewrites for naturalness, academic AIGC reduction (CNKI/VIP checks), and style conversion (Zhihu, WeChat, etc.).
npx claudepluginhub sickn33/antigravity-awesome-skills --plugin antigravity-awesome-skillsHow this skill is triggered — by the user, by Claude, or both
Slash command
/antigravity-awesome-skills:humanize-chineseThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use this skill when you need to detect AI-like Chinese writing, rewrite it to feel less synthetic, reduce AIGC signals in academic prose, or convert the text into a more specific Chinese writing style.
Detects AI-like Chinese text and rewrites it to sound more natural. Supports academic AIGC reduction, style conversion (zhihu, xiaohongshu, etc.), and targeted rewriting without factual drift.
Humanizes AI-generated text by removing formulaic patterns, filler phrases, and unnatural structures, especially Taiwanese Traditional Chinese. Useful for editing text on requests to remove AI tone, rewrite naturally, or polish.
Removes AI writing patterns from prose to make text sound natural and human-written. Detects filler phrases, formulaic structures, and other LLM tells in English and Chinese.
Share bugs, ideas, or general feedback.
Use this skill when you need to detect AI-like Chinese writing, rewrite it to feel less synthetic, reduce AIGC signals in academic prose, or convert the text into a more specific Chinese writing style.
去AI味, 降AIGC, 去除AI痕迹, 让文字更自然, 改成人话, or 降低AI率zhihu, xiaohongshu, wechat, weibo, literary, or academicStart by identifying the most obvious AI markers instead of rewriting blindly:
first/second/finally structures综上所述, 值得注意的是, 由此可见If the user provides a short sample, call out the suspicious phrases directly before rewriting.
Prefer targeted rewrites over total regeneration:
After rewriting, verify that the text:
For academic text, preserve a scholarly tone. Do not over-casualize.
If the user has a local clone of the source toolkit, these examples are useful:
python3 scripts/detect_cn.py text.txt -v
python3 scripts/compare_cn.py text.txt -a -o clean.txt
python3 scripts/academic_cn.py paper.txt -o clean.txt --compare
python3 scripts/style_cn.py text.txt --style xiaohongshu -o out.txt
Use this CLI sequence when available:
If the scripts are unavailable, use this manual process.
For papers, reports, or theses:
Examples of safer direction changes:
本文旨在 -> 本文尝试 or 本研究关注具有重要意义 -> 值得关注 or 有一定参考价值研究表明 -> 前人研究发现 or 已有文献显示Do not invent citations, evidence, or data.
Use style conversion only after the base text is readable and natural.
Supported style directions from the source workflow:
casualzhihuxiaohongshuwechatacademicliteraryweiboWhen switching style, keep the user's meaning stable and change only tone, structure, and surface wording.
Adapted from the voidborne-d/humanize-chinese project and its CLI/script workflow for Chinese AI-text detection and rewriting.