
Remove Ai Style
- 3k installs
- Updated July 30, 2026
- zc277584121/marketing-skills
remove-ai-style reduces AI writing patterns in Chinese or English at configurable intensity.
About
The remove-ai-style skill reviews and adjusts writing to reduce obvious AI-generated patterns so text reads more naturally in Chinese or English. Users can specify moderate, heavy, or full intensity; heavy is the default when unspecified. Moderate fixes only the most glaring patterns while preserving structure. Heavy actively rewrites AI-ish sentences and formulaic paragraphs. Full treats the text as a draft rewritten from scratch in a human voice while preserving meaning and key information. Workflow detects language, loads references/chinese.md or references/english.md, runs quick-scan scripts for symbol-level issues when provided, then reviews against style guidelines scripts cannot catch such as robotic transitions and formulaic structure. Chinese scans handle both ASCII and Chinese double quotes with equal priority. Core message and tone must remain intact even at full intensity. Scripts cannot catch every pattern; full-text review still follows scans.
- Supports Chinese and English with separate reference style guides.
- Three intensity levels: moderate, heavy default, and full rewrite.
- Quick-scan scripts flag symbol issues before manual style review.
- Heavy rewrites formulaic paragraphs; full preserves meaning in new voice.
- Chinese handling treats ASCII and Chinese quote pairs equally.
Remove Ai Style by the numbers
- 3,050 all-time installs (skills.sh)
- +198 installs in the week ending Aug 5, 2026 (Skillselion tracking)
- Ranked #205 of 1,879 Marketing & SEO skills by installs in the Skillselion catalog
- Security screen: LOW risk (skills.sh audit)
- Data as of Aug 5, 2026 (Skillselion catalog sync)
remove-ai-style capabilities & compatibility
- Capabilities
- language detection and intensity level selection · reference guided chinese and english style rules · quick scan scripts for symbol level issues · moderate, heavy, and full rewrite workflows · meaning preservation even at full intensity
- Use cases
- copywriting · marketing
What remove-ai-style says it does
Preserve the original meaning and tone
npx skills add https://github.com/zc277584121/marketing-skills --skill remove-ai-styleAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 3k |
|---|---|
| Security audit | 3 / 3 scanners passed |
| Last updated | July 30, 2026 |
| Repository | zc277584121/marketing-skills ↗ |
This copy sounds robotic or formulaic; how do I make it read more human?
Remove AI-generated writing patterns from Chinese or English text at moderate, heavy, or full intensity levels.
Who is it for?
Articles, landing copy, or posts that need human-sounding revision in Chinese or English.
Skip if: Skip for factual research or SEO keyword strategy without a draft to polish.
When should I use this skill?
User asks to remove AI style, sound more natural, or polish AI-generated text.
What you get
Naturally phrased text with AI tells removed per the chosen intensity level.
- polished prose draft
By the numbers
- Supports 3 intensity levels: light, medium, and heavy
Files
Remove AI Style
Review and adjust the writing style of an article to reduce obvious AI-generated patterns, making the text read more naturally and human-like.
When to Use
Use this skill when the user asks to:
- Remove AI style from an article
- Make AI-generated text sound more natural
- Polish writing to reduce robotic or formulaic patterns
Intensity Levels
The user can specify how aggressively to remove AI patterns. If they don't specify, default to "heavy".
| Level | Description |
|---|---|
| Moderate (中等) | Only fix the most obvious AI patterns. Preserve most of the original structure and phrasing. Light touch. |
| Heavy (尽力去除) | Actively rewrite AI-ish sentences, restructure overly formulaic paragraphs, and replace robotic transitions. This is the default. |
| Full (完全彻底) | Treat the entire text as a draft and rewrite it from scratch in a natural human voice, while preserving the original meaning and key information. The output should read as if a human wrote it from the start. |
Instructions
1. Determine the language of the article (Chinese or English). 2. Determine the intensity level — check if the user specified moderate / heavy / full. Default to heavy. 3. Load the corresponding reference document:
- Chinese articles:
references/chinese.md - English articles:
references/english.md
4. Run the quick-scan scripts provided in the reference document (if any) to locate symbol-level issues first. This gives you a fast overview of problem spots without reading line by line.
- For Chinese articles, scan and handle ASCII double quotes (
") and Chinese double quotes (“”) with equal priority. Do not only fix ASCII quotes.
5. Review the article against the style guidelines in the reference document. The script results are just a starting point — you still need to read through the full text for patterns that scripts can't detect (e.g., overuse of metaphors, formulaic structure, robotic transitions). 6. Apply fixes according to the intensity level:
- Moderate: only fix what the scripts flagged + the most glaring patterns.
- Heavy: fix everything the guidelines call out, rewrite awkward sentences.
- Full: rewrite the text from scratch preserving meaning.
7. Preserve the original meaning and tone — even at "full" intensity, the core message should remain intact.
中文去除 AI 味指南
检查文章中的风格,稍微微调一些地方,如果没有问题,不用调整也行。
快速扫描脚本
在逐行阅读之前,先跑以下脚本快速定位符号相关的问题。脚本结果仅供参考,帮助你快速跳转到可疑位置。
扫描英文直双引号
grep -n '"' <file_path> || echo "No ASCII double quotes found."扫描中文弯双引号
grep -n '[“”]' <file_path> || echo "No Chinese double quotes found."扫描破折号(英文 em dash / en dash,中文文章中通常应避免或替换)
grep -nP '[\x{2013}\x{2014}—–-]{2,}|--' <file_path> || echo "No suspicious dashes found."扫描「核心」相关表达
grep -n '核心' <file_path> || echo "No '核心' patterns found."扫描「不是...而是」「并非...而是」等否定-肯定转折
grep -nP '(不是|并非|而非|而不是|拒绝|舍弃).{0,15}(而是|专注|追求|而非)' <file_path> || echo "No negation-affirmation patterns found."扫描「更xx的是」「最xx的是」
grep -nP '(更|最).{1,4}的是' <file_path> || echo "No '更/最xx的是' patterns found."注意:以上脚本只能抓到符号和固定句式,比喻、结构化表达等问题仍然需要通读全文才能发现。
---
1. 少用特殊符号
- 尽量少用双引号、破折号等显眼符号。如果是中文文章,英文直双引号
"和中文弯双引号“”都要检查,二者同等处理;不能因为英文直双引号更容易被脚本抓到,就放过正文里成片的中文弯双引号。 - 正文里的双引号要主动压缩:能去掉就去掉,能改成自然转述就改成自然转述;少数确实需要强调的,优先改成「」或用其他表达方式变化一下,尽量不要沿用原来的双引号,因为双引号已经很容易被读者当成机器腔的马脚。
- 不要动代码块、JSON/YAML、命令行示例、Markdown 链接、图片 alt 文本里必要的引号,除非它们明显影响展示。
2. 少用比喻
- 少用比喻,可以接受一小部分的比喻,但不要在文章里多次使用比喻。大量的比喻会显得很浮夸。
3. 少用【不是而是】的表达
- 尽量少用【不是xx,而是xx】这样的意思上的转折。不是指字面上的【不是xx,而是xx】,我是指意思上出现【否定A,肯定B】这样的表达,都不行,举几个例子:
❌ 这款零食拒绝高糖高脂的配方,专注天然食材的原汁原味。
❌ 该模型可以通过真正的语义理解,而非简单的关键词匹配。
❌ 开源项目文档舍弃晦涩的专业术语,专注通俗易懂的实操指引。
❌ 模型部署容器化方案,要追求轻量高效的资源占用,而不要臃肿的镜像体积。
4. 少用【核心是】的表达
- 尽量少用【核心是xx】这样的表达。举例:
❌ 这才是核心问题所在
❌ 该方法的核心思想是xx
❌ 该模型的核心优势是xx
5. 少用【更xx的是】【最xx的是】的表达
- 尽量少用【更xx的是xx】【最xx的是xx】这样的表达。举例:
❌ 更要命的是,这种问题在实际应用中非常常见。
❌ 最糟糕的是,他们没有意识到这个问题。
❌ 这样,最厉害的是,整个行业都因此受益。
6. 小标题少用反问句
- 尽量少在小标题里用反问句。反问句做小标题是 AI 生成内容的常见特征,显得刻意和做作。举例:
❌ 为什么你还在用传统方案?
❌ 难道你不想提升效率吗?
❌ 谁说开源不能做到企业级?
7. 少用结构化表达
- 尽量少用结构化表达,比如列项,bullet point,第一,第二,第三,等。你甚至可以把有些比较结构化整齐的地方,改成自然一点,甚至稍有点混乱的表达,以模拟人类写作时的随意性和跳跃的思维方式。
Related skills
FAQ
What is the default intensity?
Heavy: actively rewrite AI-ish sentences and formulaic paragraphs.
Does full intensity change the meaning?
No. Core message and tone should remain intact while the voice is rewritten.
How does Chinese differ?
Load references/chinese.md and scan both ASCII and Chinese double quotes equally.
Is Remove Ai Style safe to install?
skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.