From content-creation
Analyzes Chinese articles for AI-generated content indicators (template phrases, transition density, sentence uniformity) and optionally rewrites to pass WeChat's 3.27 non-human content detection. Use when checking AI traces, humanizing text for WeChat publication, or bypassing WeChat AI detection.
How this skill is triggered — by the user, by Claude, or both
Slash command
/content-creation:anti-wechat-ai-checkThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
检测文章中的 AI 生成痕迹(模板短语、过渡词堆砌、句式雷同等),给出风险
检测文章中的 AI 生成痕迹(模板短语、过渡词堆砌、句式雷同等),给出风险 评分和修改建议,并可输出人性化润色后的版本。基于微信公众平台运营规范 3.27 条款(非真人自动化创作行为)的检测逻辑。
You MUST follow these steps in order:
Determine the input source:
--textpython skills/lovstudio-anti-wechat-ai-check/scripts/analyze.py \
--input <path> --format json
Or with inline text:
python skills/lovstudio-anti-wechat-ai-check/scripts/analyze.py \
--text "文章内容" --format json
Show the user:
IMPORTANT: Use AskUserQuestion to ask what to do next:
| Option | Description |
|---|---|
| 仅查看报告 | 用户自己修改,skill 结束 |
| 给出修改建议 | 列出每个问题的具体修改建议,不改原文 |
| 直接输出修改版 | 输出人性化润色后的完整文章 |
When rewriting, follow these humanization rules:
Output the humanized article as markdown. If the input was a file, also offer
to write the result back to a file (with -humanized suffix).
| Argument | Default | Description |
|---|---|---|
--input, -i | — | Input file path (.md, .txt) |
--text, -t | — | Inline text to analyze |
--format, -f | text | Output format: text or json |
No external dependencies — stdlib only.
npx claudepluginhub lovstudio/skills --plugin generalRewrites Chinese articles to remove AI-generated patterns like template openings, cliché transitions, buzzwords, fake quotes, overused dashes, bullet stacking, and translationese. Supports diagnostic, light, deep, and final editing modes.
Detects AI-like patterns in Chinese text and rewrites for naturalness, academic AIGC reduction (CNKI/VIP checks), and style conversion (Zhihu, WeChat, etc.).
Detects AI writing patterns and ChatGPT artifacts in text, guiding revision to sound more natural. Use before finalizing AI-assisted writing.