• User says "review this", "reduce AI-like tone", "too AI-generated"
• After the first draft is completed
• User mentions "high AI detection rate", "lack of human touch"
• The article needs final polish

• Reduce AI Detection Rate: Target to keep it below 30%
• Add Human Touch: Make articles experience-based, warm, and sound like real people speaking
• Maintain HuaSheng's Style: Practice-oriented, technically in-depth, easy to understand, practical and actionable

• Are facts accurate? (Data, time, product names)
• Is logic clear? (No contradictions)
• Is structure reasonable? (No off-topic content)
• Is information complete? (All key points covered)
• No fabrication? (All data and cases are real)

• Read through the entire text and mark questionable points
• Search to verify uncertain information
• Check the accuracy of numbers and proper nouns

• "In today's era", "Against the backdrop of..."
• "In summary", "All things considered"
• "It is worth noting that", "It should be emphasized that"
• "With the development of...", "Along with..."

❌ "In today's era of rapid AI technology development, programming tools are constantly evolving..."
✅ "Claude Code is out. I've used it for two weeks, and it's definitely better than Cursor."

• "Not... but..." (used more than 3 times consecutively)
• "Not only... but also..." (over-stacked)
• "On one hand... on the other hand..."
• "Both... and..." (overused)

❌ "Claude Code is not just a simple tool, but an intelligent assistant. It can not only write code, but also understand intentions."
✅ "Claude Code is more than just code completion. It understands your intentions and knows what you want to do. That's the key."

• "Significantly improve", "greatly enhance" → Use specific numbers instead
• "Make full use of" → "Make good use of"
• "Perform operations" → Use direct verbs ("click", "input")
• "Realize functions" → "Achieve"
• "Promote development" → "Help..."

❌ "By making full use of Claude Code's capabilities, you can significantly improve development efficiency..."
✅ "Make good use of Claude Code, and your development speed will be much faster. From my tests, it saves 3-5 hours per project on average."

• Overuse of "First, Second, Finally"
• Meaningless dense subheadings (one every 200 words)
• Forcing lists when prose can explain clearly
• "The following points", "Mainly reflected in the following aspects"

❌ "The advantages of Claude Code are mainly reflected in the following aspects: First, it has strong context understanding ability; Second, it supports multiple programming languages; Finally, its response speed is fast."

✅ "What's the strongest part of Claude Code? Context understanding. If you ask it to modify a feature, it knows which files to change and won't miss anything. It also supports over 20 languages and is fast."

• Always objectively balanced: "Has both advantages and disadvantages"
• Afraid to make judgments: "Depends on actual situations"
• Overuse of qualifiers: "May", "Perhaps", "In some cases"

❌ "Claude Code may perform well in some scenarios, but it also has limitations. The specific effect depends on actual usage."

✅ "Claude Code is really good. It's much more stable than Cursor when handling large projects. But it's expensive, which may be a burden for individual developers."

• Too many big words, few specific details
• "Many", "Some", "Significant", "Large number" (no specific numbers)
• Lack of real feelings and personal experiences
• No timeline, scenarios, or conflicts

❌ "After using it for a period of time, I found that Claude Code can effectively improve development efficiency."

✅ "I've used it for two weeks. The most obvious change is that projects that used to take 3 days now take 1.5 days. Especially when refactoring old code, Claude Code can find all related files at once, so I don't have to search one by one."

1. Check paragraph by paragraph and mark AI-like expressions
2. Rewrite against the 6 categories of AI-style checklist
3. Add personal experiences and real details (check personal material library)
4. Add uncertain expressions appropriately (use "I think", "maybe", "perhaps" when appropriate)
5. Check if it sounds like HuaSheng speaking

• Split long sentences into short ones (split sentences over 30 words into 2-3 sentences)
• Replace abstract expressions with specific ones ("many" → "3", "significantly improve" → "save 3-5 hours")
• Replace formal words with colloquial ones ("perform operations" → "click")
• Add real feelings ("When I used it before...", "To be honest...")

• Are sentence lengths appropriate? (15-25 words mainly, no more than 30 words)
• Are paragraphs not too long? (3-5 lines on mobile screens)
• Are punctuation marks natural? (Use more periods, fewer commas for long sentences)
• Is there rhythm variation? (Combine fast and slow pacing)
• Are subheadings not too dense? (One every 300-500 words)
• Are lists used moderately? (Use prose instead of lists when possible)
• Is bolding used moderately? (1-2 times every 200-300 words)

• Read aloud to feel the rhythm
• Identify long sentences over 30 words and split them
• Check paragraph length, split overly long paragraphs
• Adjust formatting, remove excessive formatting

• Read through the entire text and rewrite awkward parts
• Sounds like HuaSheng himself speaking
• (Optional) AI detection rate is below 30%

• Practice-oriented: With specific cases and actionable steps
• Technically in-depth + easy to understand: No pretentious jargon, but with depth
• Practical and actionable: Readers can take immediate action after reading
• Strong human touch: Experience-based, warm, avoid AI-like tone
• Real data: All tests and cases must be real
• Appropriate uncertainty: Say "I think" when needed, don't pretend to know everything

• ✅ When articles need real case support
• ✅ When real evaluations of tools/products are needed
• ✅ When personal experiences are needed as opening remarks
• ✅ When articles are too "AI-like" and need more human touch

/Writing References/Personal Material Library/All Jike Posts.csv

pattern: "keyword1|keyword2"
path: /Users/alchain/Documents/Writing/Writing References/Personal Material Library/All Jike Posts.csv
output_mode: content
-n: true

• Writing about Amap Street View Rankings → Search "Amap|Street View Rankings"
• Writing about AI programming tools → Search "Cursor|Claude Code|Copilot"
• Writing about product growth → Search "growth|conversion|users"

1. Open the main index:

   /Writing References/Personal Material Library/README.md

2. Find the topic: Open

   _Jike Posts Theme Index.md

3. Select materials: View organized files (e.g.,

   AI Programming Tool Experience.md

   )
4. Rewrite and use: Expand into long-form logic while maintaining real attitude

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

• Keyword Detection: Search for clichés like "In today's era", "In summary", "It is worth noting that"
• Sentence Length Check: Mark sentences over 30 words
• AI Detection: Use tools like GPTZero, Originality.AI (for reference only)

• Read aloud: Awkward parts need rewriting
• Compare with historical articles: Check if the style matches HuaSheng's previous excellent articles
• Ask yourself: Would HuaSheng say this?

• /Writing References/AI-Like Tone Review Guide.md

  - Complete review guide (with more examples)

• /Writing References/Personal Material Library/README.md

  - Main index of personal material library

• /Writing References/Personal Material Library/All Jike Posts.csv

  - Original material data

• /Writing References/Personal Material Library/_Jike Posts Usage规范.md

  - Material usage specifications

• 《Why the Best Content is Useless》: After three rounds of review, AI detection rate dropped to 28%
• 《A Team Burning Billions of Tokens Monthly: How They Use Claude Code》: Added a large number of real cases, with strong human touch

Produced by Uncle Hua | AI Native Coder · Independent Developer Official Account "HuaSheng" | 300,000+ Followers | AI Tools & Efficiency Improvement Masterpieces: Kitten Fill Light (Top 1 in AppStore Paid Charts) · Mastering DeepSeek in One Book ",