That day, I found two great things at the same time.

Liu Run’s business reference distilled skills, and Luo Zhenyu’s quote distilled skills.

What does that mean? It’s not telling you to learn how Liu Run and Luo Zhenyu write — it’s turning their writing systems into templates that AI can use directly.

In other words, now you feed in a piece of material, and AI will use Liu Run’s approach to break down the structure, create analogies, build the SCQA logic chain; then switch to Luo Zhenyu’s mode to generate quotes, provide inspiration, and add “rolling up sleeves and jumping in.”

One handles logic, the other handles quotes. When you use both together, the article gets both skeleton and soul.

At the core of Liu Run’s system, I think the three most valuable things are:

• SCQA logical framework (Situation → Conflict → Question → Answer), a magical tool for writing business analysis articles
• Ability to create analogies, translating complex business logic into relatable everyday scenarios
• Three-paragraph structure (3-segment / 10-point / 32-items), each structure suited for a specific reading context

Luo Zhenyu’s system goes in a different direction:

• Quote framework — every article must have that one sentence that can be shared
• Counterintuitive framework — not to persuade you, but to make you go “oh?”
• Jump in and do it — not preaching, but “I’m doing it with you”

Combined, they form a complete writing production line:

• Liu Run is responsible for turning your material into logically clear business analysis
• Luo Zhenyu is responsible for sprinkling quotes and inspiration on top
• You only need to be the person who inputs the material

Why does this excite me?

Because I’ve been thinking about one question: how do you write an article that is “both professional and shareable”? These two needs are inherently conflicting — professional and shareable, one inward-facing, one outward-facing.

But putting these two skills together, it precisely resolves that conflict:

Liu Run’s approach ensures professionalism without being shallow; Luo Zhenyu’s approach ensures shareability without being ugly.

What’s the killer feature?

These two skills are open source. Anyone can use them.

And it’s not just about rewriting articles — it even provides references and a clear quality control checklist.

It shows that the people who created these skills didn’t just write casually — they really polished a writing system.

Seeing both in one day, I can only say:

In the AI era, the barrier to writing has changed.

It’s not about AI writing for you; it’s about AI helping you have a writing style.

Before, you had to spend ten years to develop Liu Run’s sense of logic, ten years to develop Luo Zhenyu’s sense of quotes.

Now you download a set of skills and you can use it today.

That, damn it, is the real dimensionality reduction strike of the AI era.

liangdabiao/liurun-bookwriter-skills

Source: https://github.com/liangdabiao/liurun-bookwriter-skills

liurun-bookwriter · Dual-Style Long-Form Writing Skill Set

Two skills, two styles, one goal — to help you write long articles with a “writer’s flavor.”

This project includes two complementary Chinese long-form writing skills:

Quick Selection

Not sure? Look at the core question — is your article about “solving a problem” or “sparking thinking”? For the former, choose Liu Run; for the latter, choose Luo Zhenyu.

See §3. Comparison and Complementarity for detailed comparison.

I. liurun-bookwriter · Liu Run Style Business Long-Form Article

Empathy is the most important fundamental skill. What fills your mind is not “I,” but “You.” — Liu Run

A complete replication of Liu Run’s 28 years of business writing experience. Refined from his “My 28 Years of Writing Tips” into 8 major principles, 3 structures, SCQA logical momentum, 5 Business School SCA++ template, and 7 types of callouts, specifically designed for business long-form writing.

What This Skill Can Do

5-Minute Quick Start

Step 1: Trigger the Skill

Directly say to the Agent:

"Use Liu Run's style to write a 32-item commentary on HarmonyOS"

The Agent will automatically execute the following process:

1. Identify structure type → 32 items
2. Select SCQA variant → CSA (default)
3. Confirm topic angle → 32 items on HarmonyOS
4. Research material (auto) → Cases + data + quotes
5. Write → Follow the 8 major principles
6. QC self-check → 12 quality checks
7. Wait for your confirmation on each item

Step 2: Confirm Each Time

After each paragraph/point/item, the Agent will pause and wait for your confirmation. No manual operation required from you.

Step 3: Export to PDF

python scripts/export_pdf.py article.md

8 Major Writing Principles (Core Mental Models)

For detailed explanation, see references/style-dna.md

3 Structure Blueprints

How to choose?

• Not sure → Default to 3-segment (basic editor requirement)
• Many cases, with interviews → 10-point
• Expressing a stance, need restraint → 32-item
• Creating 5-Minute Business School audio → 5-Business-School SCA++

For detailed blueprints, see references/book-blueprints.md

3 SCQA Logical Momentum Variants

Explicit annotation method:

**A Answer**: Change the commission system to a bonus system.
[body text expands]

**C Conflict**: But doing so will trigger backlash from the sales team.
[body text expands]

For detailed logical momentum explanation, see “Principle 4” in references/style-dna.md

7 Callout Special Content Blocks

For detailed formats, see references/callout-patterns.md

Installation

Method 1: Copy to Agent skills directory

# Claude Code
cp -r liurun-bookwriter ~/.claude/skills/

# WorkBuddy
cp -r liurun-bookwriter ~/.workbuddy/skills/

Method 2: Use as a local Skill directory

Directly tell the Agent the path to the skill; no need to copy.

Dependencies

Installation by Platform

macOS

brew install pandoc
brew install --cask mactex
brew install --cask font-source-han-serif
brew install --cask font-lxgw-wenkai

Linux (Ubuntu/Debian)

sudo apt install pandoc texlive-xetex texlive-lang-chinese fonts-noto-cjk

Windows

winget install --id JohnMacFarlane.Pandoc
winget install --id MiKTeX.MiKTeX

Verify Dependencies

python scripts/export_pdf.py --list-fonts
echo "# Test" > test.md
python scripts/export_pdf.py test.md

Command Line Tools

1. PDF Export

# Basic usage
python scripts/export_pdf.py article.md

# Specify output file
python scripts/export_pdf.py article.md -o output.pdf

# Specify font
python scripts/export_pdf.py article.md --font "Source Han Serif SC"

# Verbose output
python scripts/export_pdf.py article.md -v

# List available Chinese fonts
python scripts/export_pdf.py --list-fonts

PDF Styling (optimized for business long-form articles):

• Font: Source Han Serif (Windows/Linux) / LXGW WenKai (preferred) / Microsoft YaHei (fallback)
• Font size: 11pt
• Line spacing: 1.5
• Margins: 3cm

2. Structure Validation

# Validate long-form structure (auto-detect: 3-segment/10-point/32-item/5-Business-School)
python scripts/validate_structure.py article.md

# Silent mode (only return exit code)
python scripts/validate_structure.py article.md --quiet

Auto-checks 12 items:

✅ Article type identification     ✅ SCQA variant identification
✅ Correct number of paragraphs    ✅ Paragraph number continuity
✅ Zero tolerance for banned words ✅ Empathy anchor
✅ "I" / "You" frequency          ✅ "Everyone" = 0
✅ Callout count                   ✅ SCQA node annotation
✅ Paragraph end "Final Words"     ✅ Fuzzy word check

3. Multi-Agent Collaboration

# Initialize a 32-item long-form article
python scripts/agent_scheduler.py --init "32-tiao-hongmeng" --type "32条" --scqa "CSA"

# Initialize a 10-point long-form article
python scripts/agent_scheduler.py --init "hua-wei-10" --type "10点式" --scqa "QSCA"

# Check current status
python scripts/agent_scheduler.py --status

# Get next batch of tasks
python scripts/agent_scheduler.py --next

# Advance to next stage
python scripts/agent_scheduler.py --advance

5 Agent roles: Editor-in-Chief / Research / Writing / Editing / Typesetting For detailed process, see references/agent-protocol.md

File Structure

liurun-bookwriter/
├── SKILL.md                    # Main skill definition (Agent auto-loads)
├── README.md                   # This file
├── LICENSE                     # MIT License
│
├── references/                 # Reference documents (consulted by Agent during writing)
│   ├── book-blueprints.md      # 3 structure blueprints + SCQA pairings
│   ├── chapter-templates.md    # 3 structure templates + 5-Business-School SCA++ template
│   ├── style-dna.md            # 8 major principles complete DNA
│   ├── opening-techniques.md   # 6 opening techniques
│   ├── callout-patterns.md     # 7 callout formats
│   ├── quality-checkpoints.md  # 12+10 QC checklist
│   ├── agent-protocol.md       # Agent collaboration process
│   └── research-sources.md     # Business research sources
│
├── assets/                     # Resource templates
│   ├── templates/
│   │   ├── cover-template.md   # 4 long-form article cover templates
│   │   └── toc-template.md     # 4 structure table of contents templates
│   └── schemas/
│       └── outline-schema.json # Outline data structure
│
├── scripts/                    # Tool scripts
│   ├── export_pdf.py           # PDF export (Source Han Serif / 11pt / line spacing 1.5)
│   ├── validate_structure.py   # Structure validation (12-item QC auto-check)
│   └── agent_scheduler.py      # Multi-Agent collaboration scheduling
│
└── tests/                      # Tests
    ├── baseline-checks.md      # 5 baseline failure modes
    ├── pressure-scenarios.md   # 7 stress test scenarios
    └── fixtures/
        └── sample-3duan.md     # 3-segment sample long-form article

Quality Assurance

Each long-form article automatically executes 12 QC checks:

Structure Checks (4 items)

• Article type matches metadata
• Correct number of paragraphs (3-segment=5, 10-point=12, 32-item=32, 5-Business-School=5)
• Paragraph ends with “Final Words”/“Conclusion” (3-segment, 10-point)
• Numbering is continuous with no breaks

Style Checks (5 items)

• Zero banned words (key: “everyone” = 0)
• “I” frequency ≥ 3 times per thousand words
• “You” frequency ≥ 8 times per thousand words
• Fuzzy words appear consecutively ≤ 3 times
• Sentence length ≤ 45 characters

Content Checks (3 items)

• Empathy anchor within first 3 paragraphs
• Callout count ≥ 1 (quote/story/example/analogy)
• At least 1 explicitly annotated SCQA node

For the complete checklist, see references/quality-checkpoints.md

Non-Applicable Scenarios

• Academic paper format
• Pure story/novel-style creation
• Ultra-short copy (WeChat Moments, Weibo)
• Financial reports requiring complex charts
• Legal provisions, technical manuals

Example: 3-Segment Long-Form Article

Refer to the complete example in tests/fixtures/sample-3duan.md. The structure is as follows:

# [Title]

**Creator**: Liu Run
**Source Column**: Official WeChat Account "Liu Run"
**Publication Date**: YYYY-MM-DD
**Structure Type**: 3-segment
**SCQA Variant**: ASC
**Target Readers**: Entrepreneurs · Business Readers
**Core Insight**: [One sentence]

---

## §01 Introduction: Why This Article Was Written
[Empathy anchor]
[Why the reader should keep reading]

## §02 [Body 1: First core argument]
[Start from the answer (A of ASC)]
[Support with story/example/analogy]
[Conclude with a quote]

## §03 [Body 2: Second core argument]
[Connect from the end of §02]
[Deeper insight]
[Conclude with a quote]

## §04 [Body 3: Third core argument]
[Go even deeper]
[Actionable methods or suggestions]
[Conclude with a quote]

## §05 Final Words
[Review the three arguments]
[Elevate to a higher level]
[Conclude with a quote / method / question]

Frequently Asked Questions

Q: Can I write business long-form articles in other styles?

Not recommended. This skill specializes in replicating Liu Run’s style. To write in another style, please disable this skill.

Q: What if I can’t fill 32 items?

Don’t force it. It’s better to say less. You can switch to the 3-segment (5 paragraphs) or 10-point (10 points).

Q: What if Chinese characters are garbled in the PDF?

# Confirm Chinese font is installed
fc-list :lang=zh

# macOS: brew install --cask font-source-han-serif
# Linux: sudo apt install fonts-noto-cjk

Q: Can I reference other writers in the long-form article?

Yes, but you must cite the source and not imply it’s Liu Run’s own opinion. See the “Quote Material Library” in references/research-sources.md.

Q: How should business data be handled?

Must annotate timeliness (“as of September 2024”) and source (company announcement / authoritative media / well-known research institution). See references/research-sources.md.

II. luozhenyu-bookwriter · Luo Zhenyu Style Inspirational Long-Form Article

People who act don’t stand on the sidelines and point fingers; they roll up their sleeves and jump in, making themselves the key variable in solving the problem. — Luo Zhenyu

A complete replication of Luo Zhenyu’s 14 years of content creation experience (founder of Dedao App, host of “Luo Ji Si Wei,” host of the “Friend of Time” New Year’s Eve Speech, host of “Civilization Journey”). Refined from his 2012–2026 video scripts of “Luo Ji Si Wei,” 3652 audio clips of “Luo Pang 60 Seconds,” three published books (“The Unworried Achiever,” “Reading as a Method,” “Inspiration”), 11 “Friend of Time” New Year’s Eve speeches, and the “Civilization Journey” program into 12 major principles, 3 structures, 3 SCQA variants, 7 core callouts (+6 extended), specifically designed for cognitive/inspirational/business long-form writing. Core principle: Learn the style, don’t copy sentences; every quote/story/analogy is created fresh on the spot for each piece.

For detailed documentation, see luozhenyu-bookwriter/README.md

What This Skill Can Do

12 Major Writing Principles (Core Mental Models)

⚠️ Most important: Quotes/stories/analogies must be created fresh on the spot for the current topic; reproducing original sentences from representative works is prohibited.

For detailed explanation, see style-dna.md

3 Structure Blueprints

How to choose?

• Not sure → Default to Luo Ji Si Wei long-form (TQA trigger-question-answer)
• Short content, need speed → Luo Pang 60 Seconds (PEI phenomenon-explanation-inspiration)
• New Year’s Eve speech, need momentum → New Year’s Eve speech (CAA concrete-abstract-action)

For detailed blueprints, see book-blueprints.md

3 SCQA Logical Momentum Variants (Specific to Luo Zhenyu)

Explicit annotation method:

**T Trigger**: When Zeng Guofan first arrived in Changsha to train troops, his Hunan soldiers were unruly. Instead of getting anxious, he first built sturdy camps and dug deep trenches.

[body text expands]

**Q Question**: Why does "doing the task at hand" break through entanglement better than "thinking about the past"?

[body text expands]

**A Answer**: Because the essence of entanglement is "thinking about the past"; the antidote is to shift attention from the past to the present.

[body text expands]

7 Core Callout Special Content Blocks

There are also 6 extended callouts (SCQA nodes / SCQA variants / decision frameworks / enlightened confused person / binary deconstruction / counterintuitive), see callout-patterns.md.

Installation

# Already in the project's .workbuddy/skills/ directory (default location)
ls d:/liurun-bookwriter-main/.workbuddy/skills/luozhenyu-bookwriter/

# Or copy to another location
cp -r .workbuddy/skills/luozhenyu-bookwriter ~/.claude/skills/

Directly tell the Agent the path to the skill; it’s ready to use.

Dependencies

Command Line Tools

1. Structure Validation

# Validate long-form structure (auto-detect: Luo Pang 60 Seconds / Luo Ji Si Wei Long-Form / New Year's Eve Speech)
python scripts/validate_structure.py article.md

# Silent mode (only return exit code)
python scripts/validate_structure.py article.md --quiet

Auto-checks 12 items:

✅ Article type identification     ✅ SCQA variant identification
✅ Correct number of paragraphs    ✅ Paragraph number continuity
✅ Zero tolerance for banned words ✅ "Jump in" anchor
✅ "I" / "You" frequency          ✅ "Everyone" = 0
✅ Callout count                   ✅ SCQA node annotation
✅ Paragraph end "Conclusion"      ✅ Fuzzy word check

2. Multi-Agent Collaboration

# Initialize a New Year's Eve speech
python scripts/agent_scheduler.py --init "ai-1000days" --type "跨年演讲稿" --scqa "CAA"

# Initialize a Luo Pang 60 Seconds
python scripts/agent_scheduler.py --init "60s-decision" --type "罗胖60秒" --scqa "PEI"

# Check current status / advance
python scripts/agent_scheduler.py --status
python scripts/agent_scheduler.py --next
python scripts/agent_scheduler.py --advance

5 Agent roles: Editor-in-Chief / Research / Writing / Editing / Typesetting For detailed process, see agent-protocol.md

3. PDF Export

# Convert Markdown long-form article to PDF
python scripts/export_pdf.py article.md -o article.pdf

# Specify font
python scripts/export_pdf.py article.md --font "Microsoft YaHei"

File Structure

.workbuddy/skills/luozhenyu-bookwriter/
├── SKILL.md                    # Main skill definition (Agent auto-loads)
├── README.md                   # This file
├── LICENSE                     # MIT License
│
├── references/                 # Reference documents (consulted by Agent during writing)
│   ├── book-blueprints.md      # 3 structure blueprints + 3 SCQA pairings
│   ├── chapter-templates.md    # 3 structure templates + New Year's Eve speech SCA template
│   ├── style-dna.md            # 12 major principles complete DNA + generation formulas
│   ├── opening-techniques.md   # 6 opening techniques
│   ├── callout-patterns.md     # 7 core callouts + 6 extended callout formats
│   ├── quality-checkpoints.md  # 12+10 QC checklist
│   ├── agent-protocol.md       # Agent collaboration process
│   ├── research-sources.md     # Luo Zhenyu content research sources
│   └── real-works-extraction.md# Extraction of real features from 20 representative works
│
├── assets/                     # Resource templates
│   ├── templates/
│   └── schemas/
│
├── scripts/                    # Tool scripts
│   ├── validate_structure.py   # Structure validation (12-item QC auto-check)
│   ├── agent_scheduler.py      # Multi-Agent collaboration scheduling
│   └── export_pdf.py           # PDF export
│
└── tests/                      # Tests
    ├── baseline-checks.md
    ├── pressure-scenarios.md