douyin-viral-content

Original：🇨🇳 Chinese

Translated

Douyin Viral Copy Intelligent Generator. It is automatically triggered when the user says "generate new copy", "create Douyin content", or "write short video copy". It automatically executes: (1) Read and analyze historical data (2) Optimize with 9 viral factors (3) Multi-dimensional scoring evaluation (4) Automatic iterative optimization until it meets the 5-star standard (5) Intelligent play volume estimation (6) Output the fully optimized copy. Fully automated, no need to manually specify any analysis or optimization tasks.

7installs

Sourcevickyhan924/self-media-script

Added on2026-02-10

NPX Install

npx skill4agent add vickyhan924/self-media-script douyin-viral-content

SKILL.md Content (Chinese)

View Translation Comparison →

Douyin Viral Copy Generator

Core Concept

Users only need to say: "Generate new copy" and provide book excerpts or golden quotes.

All analysis, optimization, scoring, and estimation are automatically completed until a 5-star viral copy is output.

Fully Automated Workflow

When a copy generation request is received, it automatically executes the following steps:

Step 1: Automatic Reading and Analysis of Historical Data

Automatically scan all historical copies in the

Published/

folder:

Extract the estimated play volume, actual play volume, and scores of each dimension for each copy
Identify which copies with high scores in viral factors perform better in practice
Analyze whether the estimation model has systematic bias (always overestimates or underestimates)
Summarize the content characteristics of the account (which types of emotions, styles, and topics it is better at)

If historical data is insufficient (less than 3 copies): Use the general model, no need to adjust the strategy

Step 2: Automatic Strategy Calibration

Based on historical analysis results, automatically adjust:

Factor Weights: Increase the weight of factors that perform well (e.g., if copies with high scores in "Emotional Power Reversal" have good play volume, enhance this factor)
Estimation Parameters: Calibrate the play volume estimation model (e.g., if historical data always overestimates by 20%, automatically reduce the estimation coefficient)
Tag Strategy: Optimize tag selection (e.g., if certain tag combinations perform better, prioritize their use)
Content Direction: Strengthen the content types that the account is good at

Step 3: Generate Copy with 9 Viral Factors

Refer to

references/viral-factors.md

to ensure the copy includes key factors:

Emotional Power Reversal
Cognitive Restructuring
Authority Endorsement
Fatalistic Philosophy
Algorithm-friendly Tags
Golden Quote Spreadability
Completion Rate Optimization
Interactive Hook Design
BGM Adaptation Suggestions

Integrate Historical Learning: Based on the strategy adjustments in Step 2, strengthen successful factors.

Step 4: Multi-dimensional Scoring Evaluation

Refer to

references/scoring-system.md

to automatically calculate:

Content Quality Score (100 points): Coverage of viral factors, quality of golden quotes, emotional resonance
Algorithm Adaptation Score (100 points): Tag strategy, expected completion rate, interactive guidance
Innovation Score (100 points): Perspective innovation, differentiated expression
Comprehensive Viral Index (total 300 points, converted to 5-star system)

Step 5: Quality Control and Automatic Optimization Iteration

Quality Standard: Must reach 5 stars (240-300 points) to output

If the first generation does not meet the 5-star standard:

Identify the dimension with the lowest score (e.g., insufficient innovation)
Automatically optimize that dimension (e.g., change perspective, enhance golden quotes, optimize opening)
Re-score and evaluate
Repeat iteration until it meets the 5-star standard

Automatic Risk Avoidance: Automatically avoid potential risks during generation (e.g., overly long copy, unengaging opening, insufficiently positive tags, etc.) without notifying the user.

Automatic Application of Optimization Points: Directly optimize the copy during iteration without notifying the user of the changes.

Step 6: Intelligent Play Volume Estimation

Refer to

references/estimation-model.md

to estimate based on the following factors:

Content quality score (scoring results from Step 4)
Account historical performance (average play volume, number of followers)
Track competition (base traffic for emotional healing category)
Tag popularity and combination effects
Estimated completion rate

Use Calibrated Model: Apply the adjusted estimation parameters from Step 2 to improve estimation accuracy.

Step 7: Output Optimized Copy File

Output the copy to the

Unpublished/

folder with the file name format:

[Type]_[Topic]_[Date]_BatchX.md

The file includes the following content:

Copy body + selected tags (4-6 tags)
Comprehensive score (must be 5 stars)
Video analysis (only show advantages, risks have been automatically avoided)
Estimated play volume (base estimate + viral upper limit)
Actual play volume section (to be filled by the user the next day)

Output Template Structure

The generated copy file strictly follows the structure below:

markdown

# [Copy Topic]

## 📝 Copy Body

[Generated fully optimized copy]

## 🏷️ Recommended Tags

#tag1 #tag2 #tag3 #tag4

## 🎯 Comprehensive Score

- Content Quality Score: XX/100
- Algorithm Adaptation Score: XX/100
- Innovation Score: XX/100
- **Comprehensive Viral Index: ★★★★★ (XXX points)**

## 📊 Video Analysis

### ✅ Content Advantages
- Advantage 1: [Specific description]
- Advantage 2: [Specific description]
- Advantage 3: [Specific description]

### 💡 Creation Suggestions
- BGM Recommendation: [Music style suggestion]
- Visual Suggestions: [Footage/text animation suggestions]
- Rhythm Control: [Duration and rhythm suggestions]

## 📈 Estimated Play Volume

- **Base Estimate**: XX-XX0,000
- **Viral Upper Limit**: XX0,000+
- **Estimated Completion Rate**: XX-XX%

**Scoring Basis**:
[Detailed analysis based on current scores, historical data, and track characteristics]

## 📊 Actual Play Volume (To Be Filled)

- Actual Plays: _____
- Likes: _____
- Shares: _____
- Comments: _____
- Completion Rate: _____
- Publication Time: _____

## 🔍 Review Analysis

[When the user fills in the actual play volume, this data will be automatically analyzed in the next copy generation and integrated into strategy optimization]

Key Principles

✅ Automation Principle

All analysis, optimization, and iteration are fully automated
Users do not need to manually trigger any subtasks
Users do not need to understand the optimization process, only need to see the final 5-star copy

✅ Quality Control Principle

Must meet the 5-star standard before output
Automatically identify problems and iterate optimization
Automatically avoid risks without showing them to users

✅ Learning and Evolution Principle

Read historical data in each generation
Automatically identify successful patterns and strengthen them
Continuously calibrate and optimize the estimation model

✅ User Experience Principle

Minimal input: Only need to provide original content
Perfect output: Guarantee 5-star quality
Hidden process: Do not show intermediate steps

Reference Resources

This skill includes the following reference files, which are automatically read as needed:

```
references/viral-factors.md
```
: Detailed analysis and scoring standards for 9 viral factors
```
references/scoring-system.md
```
: 300-point scoring mechanism and 5-star conversion rules
```
references/estimation-model.md
```
: Play volume estimation algorithm and parameter adjustment methods
```
references/optimization-guide.md
```
: Automatic optimization rules and iteration strategies
```
references/learning-guide.md
```
: Historical data analysis methods and strategy calibration guidelines