ai-taste-proofreading

AI-tone proofreading and polishing

Systematically reduce the AI detection rate of articles and enhance the human touch through a professional three-pass proofreading capability.

When to Use This Skill

Automatically load this skill when the following scenarios are detected:

• The user says "proofread it", "reduce the AI tone", "too AI-like"
• After the first draft is completed
• The user mentions "high AI detection rate", "no human touch"
• The article needs a final polish

Core Objectives

• Reduce AI detection rate: target below 30%
• Increase human touch: make the article feel experienced, warm, and like a real person speaking
• Maintain the Peanut style: practice-oriented, technically deep, easy to understand, useful and actionable

Three-Pass Proofreading Process

First Pass: Content Proofreading (Logic, Facts, Structure)

Objective: ensure the content is accurate and the logic is clear

Checklist：

• Are the facts accurate? (data, dates, product names)
• Is the logic clear? (no contradictions before and after)
• Is the structure reasonable? (no going off topic)
• Is the information complete? (all key points are covered)
• Is there no fabrication? (all data and cases are real)

Method：

• Read through from beginning to end and mark questionable points
• Search to verify uncertain information
• Check the accuracy of numbers and proper nouns

---

Second Pass: Style Proofreading (Reducing AI Tone)

Objective: remove the AI tone and increase the human touch

Core Check: Identifying 6 Major Types of AI-Sounding Language

1️⃣ Full of Clichés

❌ AI often says：

• "in today's era", "against the backdrop of..."
• "in summary", "all in all"
• "it is worth noting that", "it must be emphasized that"
• "with the development of...", "along with..."

✅ Rewrite direction: get straight to the point, do not beat around the bush

Example：

❌ "在当今AI技术飞速发展的时代，编程工具也在不断进化..."
✅ "Claude Code出了。我用了两周，确实比Cursor好用。"

2️⃣ AI Sentence Patterns (High-Frequency Repeated Templates)

❌ AI often says：

• "not... but..." (appears more than 3 times in a row)
• "not only... but also..." (used in stacked form)
• "on the one hand... on the other hand..."
• "both... and..." (overused)

✅ Rewrite direction: split into short sentences and use varied expressions

Example：

❌ "Claude Code不是简单的工具，而是智能助手。它不仅能写代码，而且能理解意图。"
✅ "Claude Code不只是补全代码。它能理解你的意图，知道你想做什么。这个很关键。"

3️⃣ Formal Vocabulary (Strong Sense of Distance)

❌ AI often says：

• "significantly improve", "greatly enhance" → use specific numbers
• "fully utilize" → "make good use of"
• "perform an operation" → use the verb directly ("click", "enter")
• "implement functionality" → "get it done"
• "promote development" → "help..."

✅ Rewrite direction: make it colloquial and specific

Example：

❌ "通过充分利用Claude Code的能力，可以显著提升开发效率..."
✅ "用好Claude Code，你的开发速度能快不少。我测下来，平均每个项目省3-5小时。"

4️⃣ Mechanical Structure (AI-Style List Obsession)

❌ AI characteristics：

• Overuse of "first, second, finally"
• Dense meaningless subheadings (one every 200 words)
• If it can be explained clearly in prose, it insists on using a list
• "the following points", "mainly reflected in the following aspects"

✅ Rewrite direction: natural narration, moderate use of lists

Example：

❌ "Claude Code的优势主要体现在以下几个方面：首先，它具有强大的上下文理解能力；其次，它支持多种编程语言；最后，它的响应速度很快。"

✅ "Claude Code最强的地方是什么？理解上下文。你让它改一个功能，它知道要动哪几个文件，不会漏掉。而且支持20多种语言，速度也很快。"

5️⃣ Neutral stance (no position, no viewpoint)

❌ AI characteristics：

• Always objectively balanced: "has both advantages and disadvantages"
• Afraid to make judgments: "it depends on the specific situation"
• Every sentence has qualifiers: "maybe", "perhaps", "in some cases"

✅ Rewrite direction: take a clear stance, dare to make judgments

Example：

❌ "Claude Code在某些场景下可能表现较好，但也存在一些局限性，具体效果取决于实际使用情况。"

✅ "Claude Code确实好用。处理大型项目时，比Cursor稳定多了。但价格贵，个人开发者可能扛不住。"

6️⃣ Missing details (abstract, not grounded)

❌ AI characteristics：

• Many big words, few specific details
• "Many", "some", "significant", "a large amount" (without giving numbers)
• Lacks real feelings and personal experience
• No timeline, no scenes, no conflict

✅ Rewrite direction: add real details, specific numbers, personal experience

Example：

❌ "经过一段时间的使用，我发现Claude Code能够有效提升开发效率。"

✅ "用了两周。最明显的变化是，之前要3天的项目，现在1天半就能搞定。特别是重构老代码，Claude Code能一次性找出所有关联文件，不用我一个个翻。"

---

Second pass review: specific methods

1. Check paragraph by paragraph, mark AI-sounding expressions
2. Compare against the list of 6 major categories of AI tonerewrite
3. Add personal experience and real details(check the personal material library)
4. Add expressions of uncertainty(use "I think", "maybe", "perhaps" in moderation)
5. Check whether it sounds like Huasheng talking

Common rewriting techniques：

• Split long sentences into short ones (split anything over 30 characters into 2-3 sentences)
• Change abstract to concrete ("many" → "3", "significantly improved" → "saves 3-5 hours")
• Change written language to spoken language ("perform an operation" → "click")
• Add real feelings ("when I used it before...", "to be honest...")

---

Third pass: detail polishing (punctuation, formatting, rhythm)

Goal: make the article read comfortably and naturally

Checklist：

• Is the sentence length appropriate? (mainly 15-25 characters, no more than 30 characters)
• Are paragraphs not too long? (3-5 lines on a phone screen)
• Is the punctuation natural? (use more periods, fewer commas connecting long sentences)
• Is there variation in rhythm? (combine fast and slow)
• Are subheadings not too dense? (one every 300-500 characters)
• Are lists used in moderation? (if prose works, don't use a list)
• Is bolding used in moderation? (1-2 places every 200-300 characters)

Method：

• Read aloud and feel the rhythm
• Find long sentences over 30 characters and split them shorter
• Check paragraph length and split ones that are too long
• Adjust formatting and remove excessive formatting

---

Final check

• Read through from beginning to end and rewrite places where it gets stuck
• It feels like Huasheng himself is talking
• (Optional) AI detection rate below 30%

---

Huasheng style characteristics (must maintain)

• Practice-oriented: has specific cases and actionable steps
• Technical depth + easy-to-understand expression: doesn't show off jargon, but has depth
• Useful and actionable: readers can act immediately after reading
• Strong human touch: has a sense of experience, warmth, and avoids AI tone
• Authentic data: all tests and cases must be real
• Moderate uncertainty: say "I think" when appropriate, don't pretend to be omniscient

Personal Material Library Usage

When to Use：

• ✅ Article needs real case support
• ✅ Needs genuine evaluation of tools/products
• ✅ Needs personal experience as an opening
• ✅ Article has too much "AI flavor" and needs more human touch

Quick Usage Process：

Method A: Directly search raw data (recommended for priority use)

Applicable scenarios: New topics, unorganized themes, needing the most original genuine expression

Use the Grep tool to search /写作参考/个人素材库/全部即刻动态.csv：

pattern: "关键词1|关键词2"
path: /Users/alchain/Documents/写作/写作参考/个人素材库/全部即刻动态.csv
output_mode: content
-n: true

Example：

• Writing about Amap Street Scan List → search "高德|扫街榜"
• Writing about AI coding tools → search "Cursor|Claude Code|Copilot"
• Writing about product growth → search "增长|转化|用户"

Method B: View refined materials

Applicable scenarios: Common topics (AI coding tools, product development, etc.) already have systematized organization

1. Open the master index:/写作参考/个人素材库/README.md
2. Find the topic: open _即刻动态主题索引.md
3. Select materials: view the refined file (e.g.AI编程工具使用心得.md）
4. Rewrite for use: expand into long-form article logic, maintaining a genuine attitude

Notes：

• All materials are genuine and cannot be fabricated or exaggerated
• Pay attention to the time span (2025.05-2025.10) to avoid outdated information
• Must rewrite into long-form article logic; cannot directly copy and paste

---

Review tools (optional)

Automatic detection tools

• Keyword detection: Search for clichés like "在当今", "综上所述", "值得注意的是", etc.
• Sentence length check: Mark long sentences over 30 characters
• AI detection: Use tools such as GPTZero, Originality.AI, etc. (for reference only)

Manual detection methods

• Read aloud: The places where you stumble are the places that need revision
• Compare with historical articles: Compare with Huasheng's previous excellent articles to see if the style is consistent
• Ask yourself: Would Huasheng say it this way?

---

Common mistakes and rewrite examples

Mistake 1: Beating around the bush at the beginning

❌ "在当今AI技术飞速发展的背景下，编程工具领域也迎来了新的变革。作为一款新兴的AI编程助手，Claude Code正在受到越来越多开发者的关注..."

✅ "Claude Code出了。我用了两周，确实比Cursor好用。今天聊聊为什么。"

Mistake 2: Overusing AI sentence patterns

❌ "Claude Code不是简单的代码补全工具，而是一个智能编程助手。它不仅能够生成代码，而且能够理解开发者的意图。"

✅ "Claude Code不只是补全代码。它能理解你想干嘛。比如你说'重构这个模块'，它就知道该怎么做。"

Mistake 3: Lack of specific details

❌ "经过一段时间的测试，我发现Claude Code在很多方面都表现优秀。"

✅ "用了两周。最明显的变化是，之前要3天的项目，现在1天半就能搞定。"

Mistake 4: Attitude too neutral

❌ "Claude Code有其优势，也存在一些不足，具体是否适合使用需要根据实际情况判断。"

✅ "Claude Code确实好用。但价格贵，个人开发者可能扛不住。如果你公司报销，强烈推荐。"

---

Reference resources

• /写作参考/AI味审校指南.md - Complete review guide (including more examples)
• /写作参考/个人素材库/README.md - Master index of the personal material library
• /写作参考/个人素材库/全部即刻动态.csv - Raw material data
• /写作参考/个人素材库/_即刻动态使用规范.md - Material usage guidelines

---

Success cases

• "Why the Best Content Is All Useless": After three rounds of review, the AI detection rate dropped to 28%
• "How a Team Burning Billions of Tokens a Month Uses Claude Code": Added a large number of real cases, with a strong human touch

---

Last updated: 2025-11-07 Applicable projects: Official account writing, video scripts Maintainer: Huasheng