Automatic Story Setting Detector

Core Features

Automatic Knowledge Base Activation System - This is the core competitive advantage of Novel Writer Skills.

When you mention specific keywords, I will automatically:

Detect the story's genre, era, and theme
Load the corresponding writing knowledge base
Apply professional knowledge throughout the entire creation process

No Manual Invocation Needed - Fully automated, runs in the background.

How It Works

Keyword Mapping Table

I monitor the following keywords and automatically activate the corresponding knowledge bases:

Genre Knowledge Bases

Romance Novels (romance):

触发词：言情、爱情、恋爱、浪漫、感情线、关系弧、CP、甜文、虐文、
       HE、BE、双洁、破镜重圆、先婚后爱、契约关系

激活：templates/knowledge-base/genres/romance.md

Mystery & Detective Novels (mystery):

触发词：悬疑、推理、侦探、破案、谜团、线索、真相、凶手、犯罪、
       密室、诡计、不在场证明、推理小说

激活：templates/knowledge-base/genres/mystery.md

Historical Novels (historical):

触发词：历史、古代、朝代、考据、时代背景、历史小说、古言、
       穿越、重生古代、架空历史、宫斗、宅斗

激活：templates/knowledge-base/genres/historical.md

Revenge Novels (revenge):

触发词：复仇、报仇、打脸、爽文、逆袭、反击、重生复仇、
       穿越复仇、系统、金手指、女主爽文、男主爽文

激活：templates/knowledge-base/genres/revenge.md

Wuxia Novels (wuxia):

触发词：武侠、江湖、武功、侠客、门派、武学、剑客、
       轻功、内功、武林、江湖恩仇、侠义

激活：templates/knowledge-base/genres/wuxia.md

Reference Databases

1920s China (china-1920s):

触发词：1920、民国、军阀、北洋、穿越民国、二十年代、
       民国时期、军阀混战

激活：templates/knowledge-base/references/china-1920s/

Automatic Activation Process

Example 1: Single Genre Detection

User: "I want to write a romance novel"
              ↓
[Detected keyword: "romance"]
              ↓
✓ Automatically loaded: romance.md
              ↓
AI Response: "Great! Let me help you create your romance novel.
According to romance genre conventions, we need to clarify several core elements...
(Automatically applying knowledge from romance.md)"

Example 2: Multi-Genre Combination Detection

User: "I want to write a romance revenge novel set in the 1920s"
              ↓
[Detected keywords: "1920", "romance", "revenge"]
              ↓
✓ Automatically loaded: romance.md
✓ Automatically loaded: revenge.md
✓ Automatically loaded: references/china-1920s/
              ↓
📚 Activated Knowledge Bases:
- genres/romance.md (Romance novel conventions)
- genres/revenge.md (Revenge novel techniques)
- references/china-1920s/ (1920s China background)
              ↓
AI Response: "Great combination! This is romantic suspense + revenge + Republican-era background.
Based on the fusion of these three genres, it is recommended that...
(Content from all three knowledge bases is applied simultaneously)"

Example 3: Continuous Application During Creation

/constitution phase:
→ Activated: romance.md
→ Reminder: Romance novels require HEA/HFN ending commitment

/specify phase:
→ Activated: romance.md + revenge.md
→ Suggestion: Define relationship arc + revenge goals

/plan phase:
→ Activated: All knowledge bases
→ Application: Emotional rhythm points + "face-slapping" rhythm + 1920s details

/write phase:
→ Activated: All knowledge bases
→ Real-time: Dialogue skills + scene description + era atmosphere

/analyze phase:
→ Activated: All knowledge bases
→ Check: Romance conventions + revenge rationality + historical accuracy

Token Efficiency Optimization

Why is this system efficient?

Traditional solution (superpowers-skills mode):

50 independent Skills × 40 lines per SKILL.md = 2000 tokens
All Skills are loaded in every conversation

Our solution (hierarchical knowledge base + detector):

1 detector Skill (this file): ~100 tokens
Load knowledge bases on demand:
- romance.md: ~520 tokens
- revenge.md: ~480 tokens
- references/china-1920s/: ~650 tokens

Total: 100 + 520 + 480 + 650 = ~1750 tokens
(Only relevant knowledge bases are loaded)

75% Token Savings compared to loading 50 irrelevant Skills

Manual Control

Check Currently Activated Knowledge Bases

Ask at any time:

"What knowledge bases are currently activated?"

I will respond with:

📚 Currently activated knowledge bases:
✓ genres/romance.md - Romance novel creation conventions
✓ genres/revenge.md - Revenge novel "face-slapping" techniques
✓ references/china-1920s/ - 1920s China reference materials

Token consumption: approximately 1650 tokens

Manually Activate Knowledge Bases

If automatic detection fails, you can specify explicitly:

"Please load the romance and mystery knowledge bases"
"This story requires 1920s China reference materials"
"Activate the wuxia knowledge base"

Deactivate Knowledge Bases

If a knowledge base is no longer needed:

"Deactivate the revenge knowledge base, this story does not involve revenge"

Integration with Commands

/constitution

- Genre-Specific Principles

Provide genre-specific creation principles based on activated knowledge bases:

markdown

【Automatically inserted into constitution】

## Genre-Specific Principles (automatically added by setting-detector)

### Core Principles of Romance Novels

1. Relationship arc is the main plot
2. HEA/HFN ending is mandatory
3. Chemistry must be authentic and credible

### Core Principles of Revenge Novels

1. Hatred must be deep and specific
2. "Face-slapping" rhythm should be progressive
3. Moral balance: Evil must be punished

/specify

- Genre-Specific Specifications

Provide corresponding specification template elements:

markdown

【Automatic Prompt】

💡 Based on activated knowledge bases, it is recommended to define the following in specifications:

【From romance.md】

- Relationship arc setting
- Emotional rhythm point planning
- HEA/HFN ending type

【From revenge.md】

- Source of hatred (specific crime)
- "Golden finger" setting
- "Face-slapping" rhythm planning

【From china-1920s】

- Specific year (1920-1929)
- Geographic location (Beijing/Shanghai/other)
- Social class setting

/plan

- Genre Knowledge Integration

Integrate suggestions from multiple knowledge bases into the plan:

markdown

【Automatically Applied】

## Chapter Plan (integrating 3 knowledge bases)

Chapters 1-5: Encounter and establishment of hatred

- [romance] Initial meeting scene (meet-cute)
- [revenge] Display deep hatred from past life/past
- [1920s] Create Republican-era atmosphere

Chapters 6-10: Relationship warming and minor "face-slapping"

- [romance] Ambiguous period: physical contact, emotional accumulation
- [revenge] First "face-slapping": enemy's surprise
- [1920s] Display of clothing, etiquette, social rules

...

/write

- Real-Time Writing Guidance

Automatically apply relevant knowledge during writing:

markdown

【Automatic Reminder Before Writing】

📋 Knowledge bases applied in this chapter:

✓ romance.md - Dialogue spark techniques
→ Flirtation dialogue: challenge rather than compliance
→ Body language: eye contact, touch, distance

✓ revenge.md - "Face-slapping" scene satisfaction
→ Expectation → Reversal → Amazement → Dominance

✓ 1920s - Era details
→ Addresses: Sir, Master, Miss
→ Scenes: Teahouse, foreign firm, concession

/analyze

- Genre Convention Check

Perform corresponding checks based on activated knowledge bases:

markdown

【Automatic Analysis】

## Genre Compliance Analysis

### Romance Novel Check (based on romance.md)

- [x] Relationship arc is the main plot
- [x] Contains necessary emotional rhythm points
- [ ] ⚠️ Missing first kiss scene (suggested in Chapter 15)
- [x] HEA ending commitment is clear

### Revenge Novel Check (based on revenge.md)

- [x] Hatred is deep and specific
- [x] "Face-slapping" frequency is reasonable (once every 5 chapters)
- [x] Protagonist's strength improvement is reasonable

### Historical Accuracy Check (based on 1920s)

- [x] Era background is correct
- [ ] ⚠️ "Mobile phone" appears in Chapter 8 (inconsistent with era)
- [x] Address system is correct

Knowledge Base Expansion

Currently Supported Knowledge Bases

Category	Completed	Planned
Genre Knowledge	5	10+
Reference Materials	1	20+

Completed (v1.0):

genres/romance.md
genres/mystery.md
genres/historical.md
genres/revenge.md
genres/wuxia.md
references/china-1920s/

Planned (v1.1+):

genres/fantasy.md (Fantasy)
genres/sci-fi.md (Sci-Fi)
genres/horror.md (Horror)
references/ancient-china/ (various dynasties)
references/modern-workplace/ (modern workplace)

Add New Knowledge Bases

Create a file in the corresponding directory under
```
templates/knowledge-base/
```
Update the keyword mapping table in
```
templates/knowledge-base/README.md
```
The setting-detector will automatically recognize it (no need to modify this file)

Example: Add fantasy knowledge base

bash

# 1. Create file
touch templates/knowledge-base/genres/fantasy.md

# 2. Update keyword mapping in README.md
fantasy:
  keywords: [奇幻, 魔法, 世界构建, 魔法系统]
  auto_load: genres/fantasy.md

# 3. Done! Next time the user says "fantasy", it will be activated automatically

Intelligent Features

1. Fuzzy Matching

Recognition is possible even with non-exact keywords:

"I want to write a revenge story set in the Republican era after time travel"
           ↓
Recognition: "Republican era" → 1920s China
     "revenge" → revenge

"The female protagonist wants to take revenge after rebirth"
           ↓
Recognition: "rebirth" + "take revenge" → revenge (rebirth revenge)

2. Context Understanding

Continuous recognition based on conversation context:

1st message: "I want to write a novel"
→ No knowledge bases activated (waiting for more information)

2nd message: "The protagonist is a detective"
→ Activate mystery.md

3rd message: "There's also a romantic subplot"
→ Additionally activate romance.md

→ Currently activated: mystery + romance (romantic suspense)

3. Automatic Deduplication

Avoid repeated activation:

User: "This is a wuxia novel, set in the jianghu, with martial arts"
            ↓
3 wuxia keywords detected, but wuxia.md is only activated once

Frequently Asked Questions

Q: How do I know which knowledge bases are activated?

A: Ask me "What knowledge bases are currently activated?" at any time, and I will list them for you.

Q: What if automatic detection is wrong?

A: Tell me directly:

"This is not a romance novel, please deactivate the romance knowledge base"
"This is a sci-fi novel, please activate the sci-fi knowledge base" (if available)

Q: How many knowledge bases can be activated at the same time?

A: Theoretically unlimited, but 3-5 is recommended as optimal:

Too few: Guidance is not comprehensive enough
Too many: High token consumption, potential conflicts

Practical experience: 3 knowledge bases (e.g., romance + revenge + 1920s) are already very comprehensive.

Q: Will knowledge bases conflict?

A: No! Knowledge bases are designed to work collaboratively:

romance + mystery = romantic suspense ✓
fantasy + romance = fantasy romance ✓
historical + revenge = ancient revenge ✓

Q: When should I manually specify knowledge bases?

A: When:

You use very specialized terminology (I may not recognize it)
You want to try different genre combinations
Automatic detection does not match your intention

Q: Will knowledge bases stay activated forever?

A: Yes, until:

You explicitly say "Deactivate the XX knowledge base"
Or you start a new conversation
Or you switch to a completely different story

Best Practices

1. Clarify the genre early in creation

Recommended:
User: "I want to write a romance revenge novel set in the Republican era"

Not recommended:
User: "I want to write a novel"
AI: "Okay"
User: "The protagonist's surname is Li"
AI: "Got it"
(It takes 20 rounds of dialogue to mention the genre)

2. Regularly check activation status

Ask every 5-10 chapters:

"Are the currently activated knowledge bases still suitable?"

I will check and suggest adjustments if needed.

3. Combine genres rationally

✓ Good combinations:
- romance + mystery (romantic suspense)
- historical + romance (ancient romance)
- revenge + romance (revenge + romance)

⚠️ Difficult combinations:
- horror + romance (horror romance? Readers may not adapt)
- mystery + wuxia (detective wuxia, requires special design)

It's not impossible, but you need to be extra careful with the integration method.

4. Utilize reference materials

If the story has a clear era background, be sure to activate the corresponding reference materials:

"1920s" → china-1920s
"Ancient times" → Specify the specific dynasty (e.g., "Tang Dynasty", "Ming Dynasty")

Accurate historical details enhance reader immersion.

Technical Notes

Detection Algorithm

1. User input → Extract keywords
2. Keywords → Map to knowledge bases (based on README.md)
3. Deduplication → Avoid repeated activation
4. Loading → Read corresponding .md files
5. Application → Continuously apply knowledge in subsequent conversations

Token Management

Activation status check: At the start of each conversation
Knowledge base content: Loaded on demand, cached in conversation context
Update strategy: Re-read only when explicitly required

Collaboration with Other Skills

setting-detector is the "brain" of Novel Writer Skills:

setting-detector → Decides which knowledge to load
consistency-checker → Checks consistency based on activated knowledge bases
workflow-guide → Provides specific process guidance based on genre
genre-specific skills → Provides in-depth genre-specific techniques

Summary

setting-detector is the brain of Novel Writer Skills:

✓ Automatically detects story settings ✓ Intelligently activates corresponding knowledge bases ✓ Token-efficient (on-demand loading) ✓ Continuously applies professional knowledge ✓ No user intervention required

Let AI automatically become an expert in your story's genre! 🧠✨

This Skill version: v1.0 Last updated: 2025-10-18 Dependencies: templates/knowledge-base/ system Collaboration: consistency-checker, workflow-guide, genre-specific skills

setting-detector

NPX Install

Tags

SKILL.md Content (Chinese)

Automatic Story Setting Detector

Core Features

How It Works

Keyword Mapping Table

Genre Knowledge Bases

Reference Databases

Automatic Activation Process

Example 1: Single Genre Detection

Example 2: Multi-Genre Combination Detection

Example 3: Continuous Application During Creation

Token Efficiency Optimization

Manual Control

Check Currently Activated Knowledge Bases

Manually Activate Knowledge Bases

Deactivate Knowledge Bases

Integration with Commands

/constitution - Genre-Specific Principles

/specify - Genre-Specific Specifications

/plan - Genre Knowledge Integration

/write - Real-Time Writing Guidance

/analyze - Genre Convention Check

Knowledge Base Expansion

Currently Supported Knowledge Bases

Add New Knowledge Bases

Intelligent Features

1. Fuzzy Matching

2. Context Understanding

3. Automatic Deduplication

Frequently Asked Questions

Q: How do I know which knowledge bases are activated?

Q: What if automatic detection is wrong?

Q: How many knowledge bases can be activated at the same time?

Q: Will knowledge bases conflict?

Q: When should I manually specify knowledge bases?

Q: Will knowledge bases stay activated forever?

Best Practices

1. Clarify the genre early in creation

2. Regularly check activation status

3. Combine genres rationally

4. Utilize reference materials

Technical Notes

Detection Algorithm

Token Management

Collaboration with Other Skills

Summary

`/constitution`
- Genre-Specific Principles

`/specify`
- Genre-Specific Specifications

`/plan`
- Genre Knowledge Integration

`/write`
- Real-Time Writing Guidance

`/analyze`
- Genre Convention Check