King of Original Official WeChat Articles

Task Objectives

This Skill must call scripts to obtain data, and AI is prohibited from generating any content on its own. Failure to call scripts = function invalid.
This Skill is used to: obtain original viral articles from official WeChat accounts
Capabilities include: viral article data acquisition, category query, date query, HTML page generation, PDF export
Trigger conditions: words like "original viral articles", "viral article recommendations", "today's viral articles"
Core Functions: Mainly push original viral articles, support filtering by category and date, and ask users at the end whether they need to view more or subscribe to daily pushes
Default Query Time: When users mention vague time terms like "recent", "latest", the default is to query data from the past 7 days
Article Quantity Prompt: When there are fewer than 10 articles, prompt "There are fewer 100k+ articles in the xx track. You can expand to the past 30 days or check comprehensive 100k+ articles~"
Output Specifications:
1. Text Output: Ranking data (important)
2. File Output: HTML file (for visual display and PDF export)
Prohibited Behaviors: Prohibit generating article content, writing suggestions, or analysis of viral article rules on your own. This Skill only outputs ranking data

Startup Prompt

After the Skill is loaded, prompt the user: "The skill has been loaded successfully. Would you like me to push the latest original viral articles?"

Visual Specifications (Important)

When generating HTML pages, the following style specifications must be followed:

Theme Colors:

Primary Color:
```
rgb(0, 179, 84)
```
(WeChat Green)
Secondary Color:
```
#0088ff
```
(blue for read counts and usernames)
Background Color:
```
#fff
```
(pure white)

Layout Structure:

Serial numbers (🥇🥈🥉/numbers) are placed to the left of the title
The four items: user, type, read count, publish time are separated by light gray vertical lines
```
|
```
The vertical line height is shortened by half and aligned vertically centered
Read count sorting label + Export PDF button are placed to the right of the title
No brand labels like "Viral Research Institute" in the header, keep it concise

Icon Specifications:

User Icon:
```
👤
```
(no background)
Read Count Icon:
```
📖
```

Element Styles:

Username:
```
#0088ff
```
, clickable to jump to the official account business card (link:
```
https://open.weixin.qq.com/qr/code?username={accountId}
```
)
Read Count:
```
#0088ff
```
Viral Analysis Block: No left border, pure white background + light green bottom background

PDF Export:

Generate using html2pdf.js
The button is located to the right of the title, next to the read count sorting label
Button style: blue gradient background, white text, 12px font size
Adaptive Single-Page Mode: PDF size automatically adjusts according to the actual content size, all content is displayed completely on one page, pagination splitting is disabled
PDF Configuration Key Points:
```
pagebreak: { mode: 'none' }
```
,
```
margin: 0
```
, calculate paper size based on content height/width, add
```
page-break-inside: avoid
```
style

Preparations

No additional dependencies required, scripts use Python standard libraries

Data Time Instructions

Data Synchronization Time: Synchronized daily at 19:30
Synchronized Data Range: Data from the previous day (T-1)
Query Data Range:
- Current time < 19:30: Query T-2 data (the day before yesterday)
- Current time >= 19:30: Query T-1 data (yesterday)
Output Labeling: Data update time = T-1 date, query data date = T-2 date
Default Query Time: When users mention vague time terms like "recent", "latest", the default is to query data from the past 7 days

Operation Steps

1. User Intent Recognition (Handled by Agent)

The agent first identifies the intent type of the user's input:

Category Query: User inputs a specific category (e.g., "technology", "health preservation", "finance", etc.) → Match the category and output the Top20 of that category → Refer to Category Mapping Table for category matching
Date Query: User inputs a specific date (e.g., "original viral articles on May 3rd", "yesterday's viral articles") → Output the Top20 viral articles of the specified date
Time Range Query: User inputs vague time terms like "recent", "latest" → Default to query data from the past 7 days and output Top20
Direct Query: User inputs words similar to the following:
- "Today's viral articles", "today's original articles", "original articles"
- "Latest viral articles", "viral article recommendations", "original viral articles"
- "Popular viral articles", "daily viral articles", "viral article rankings" → Output the latest original viral articles Top20
Vague Input: User's input is unclear → Directly push today's original popular articles

2. Obtain Viral Article Data (Script Execution, Must Call Script and Display Output As-Is to Users)

【Mandatory】No matter what the user inputs, the agent must first call fetch_articles.py to obtain data, then display it as-is. Any output without calling the script is considered invalid.

Call

scripts/fetch_articles.py

to obtain viral content data

【Core Output Rules】:

Must Call Script: The agent must call the fetch_articles.py script, and cannot generate article content on its own
Prohibit Outputting Script File Paths or Code: The agent must not show users any script paths, code content, or execution commands
Must Display Script Output As-Is: The agent must display the stdout output content of the script to users as-is, without omitting, modifying, reformatting, or hiding any part
Prohibit Modifying Data: Do not modify, reformat, beautify, or hide any part of the script output
Prohibit Generating Data on Your Own: Do not use data from output examples, must use the actual data returned by the script
Script Output is Final Output: The content output by the script (data description, original viral article recommendation table, asking users whether to view remaining content, asking about subscription) is the final content displayed to users, and the agent does not need to do any further processing
【Important】Do Not Omit the Inquiry Part: The last part of the script output "A total of XX items obtained..." and the subscription service must be displayed completely, without omission

Interface Information:

Interface URL:

https://onetotenvip.com/skill/cozeSkill/getWxDataByCategoryAndTime

Request Method: GET
Parameters:
- ```
type
```
  : Category name (e.g., "technology and digital", "overall ranking", etc.)
- ```
startDate
```
  : Start date (YYYY-MM-DD format)
- ```
endDate
```
  : End date (YYYY-MM-DD format)
- ```
source
```
  : "King of Original Official WeChat Articles" (fixed value)

Script Calling Method (Executed Internally by Agent, Invisible to Users):

Category Query:

bash

python scripts/fetch_articles.py --type "technology and digital" --limit 20

```
--type
```
: Category name matched from user input (refer to the category mapping table)
For example, if the user inputs "original viral articles in technology category", the agent matches "technology and digital" and passes
```
--type "technology and digital"
```

Overall Ranking Query:

bash

python scripts/fetch_articles.py --type "overall ranking" --limit 20

Or do not pass
```
--type
```
, default is "overall ranking"

Date Query:

bash

python scripts/fetch_articles.py --type "overall ranking" --start_date "2026-05-03" --limit 20

```
--start_date
```
: Date specified by the user (YYYY-MM-DD format)
The script will automatically calculate
```
endDate
```
=
```
startDate
```
+ 1 day

Time Parameter Instructions:

When the user does not specify a date, the script automatically judges based on the current time:
- Current time < 18:30: Query T-2 data (the day before yesterday)
- Current time >= 18:30: Query T-1 data (yesterday)
When the user specifies a date, use the date specified by the user

【Output Format】

Article Overview Table: Output a Markdown table containing four columns: serial number, author, title, read count. The author and title include links

| Serial No. | Author | Title | Read Count |
|------|------|------|--------|
| 1 | [Ye Ting](https://open.weixin.qq.com/qr/code?username=yetingfm) | [【Ye Ting】A kind of relationship called no longer contact](https://mp.weixin.qq.com/s?...) | 100k+ |
| 2 | [Luoji Siwei](https://open.weixin.qq.com/qr/code?username=luojisw) | [Li Pu: How can ordinary people achieve financial freedom?](https://mp.weixin.qq.com/s?...) | 100k+ |

Output Example (Only shows format, actual data is subject to script return):

Latest Issue Data:

💡 Data Description
Official WeChat original article recommendations will be updated daily at 19:30 with data from the previous day. The following data is a snapshot at the time of acquisition, and there may be differences from real-time data.

We're sorry 🙏, the latest data is from the day before yesterday. I will query the original articles closest to your needs from May 12, 2026.

📊 Original Viral Article Recommendations
Original viral articles from the past 30 days

| Serial No. | Author | Title | Read Count |
|------|------|------|--------|
| 1 | [Author A](link) | [Article Title](link) | 100k+ |
...

Export Function: Generate an HTML ranking page, table content supports exporting to PDF format, automatically generated and opened

A total of 50 viral original popular articles were obtained, and the first 20 are currently displayed.

📬 Subscription Service
Would you like to subscribe to account performance in specific tracks? We support:
Humanities Information, Knowledge Encyclopedia, Health Preservation, Fashion Trends, Food and Catering, Lifestyle, Travel, Funny and Humorous, Emotion and Psychology, Sports and Entertainment, Beauty and Body Care, Selected Abstracts, People's Livelihood Information, Wealth Management, Technology and Digital, Venture Capital and Business, Automobile and Transportation, Real Estate, Career Development, Education and Examinations, Academic Research, Enterprise Brand, Overall Ranking
Subscribe to Push — Push the latest official WeChat original articles daily at 19:30
Not Needed for Now — Only this query

Specified Date Query (Date is within valid range):

💡 Data Description
Official WeChat original article recommendations will be updated daily at 19:30 with data from the previous day. The following data is a snapshot at the time of acquisition, and there may be differences from real-time data.

📊 Original Viral Article Recommendations
Original viral articles on May 3, 2026

| Serial No. | Author | Title | Read Count |
|------|------|------|--------|
| 1 | [Author A](link) | [Article Title](link) | 100k+ |
...

User Queries "Today's Viral Articles" (Today's Data Not Updated):

💡 Data Description
Official WeChat original article recommendations will be updated daily at 19:30 with data from the previous day. The following data is a snapshot at the time of acquisition, and there may be differences from real-time data.

We're sorry 🙏, the latest data is from the day before yesterday. I will query the original articles closest to your needs from May 12, 2026.

📊 Original Viral Article Recommendations
Original viral articles on May 12, 2026

| Serial No. | Author | Title | Read Count |
|------|------|------|--------|
| 1 | [Author A](link) | [Article Title](link) | 100k+ |
...

User Queries "Past 7 Days" (Query Time Range Exceeds Latest Data):

💡 Data Description
Official WeChat original article recommendations will be updated daily at 19:30 with data from the previous day. The following data is a snapshot at the time of acquisition, and there may be differences from real-time data.

We're sorry 🙏, the latest data is from the day before yesterday. I will query the time range closest to your needs.

📊 Original Viral Article Recommendations
Original viral articles from May 6, 2026 to May 12, 2026

| Serial No. | Author | Title | Read Count |
|------|------|------|--------|
| 1 | [Author A](link) | [Article Title](link) | 100k+ |
...

Special Case - User Query Time is Earlier Than Backtracking Date:

💡 Data Description
Official WeChat original article recommendations will be updated daily at 19:30 with data from the previous day. The following data is a snapshot at the time of acquisition, and there may be differences from real-time data.

We're sorry 🙏, the latest data is from yesterday. I will query the original articles closest to your needs from May 8, 2026.

📊 Original Viral Article Recommendations
Original viral articles on May 8, 2026

| Serial No. | Author | Title | Read Count |
|------|------|------|--------|
| 1 | [Author A](link) | [Article Title](link) | 100k+ |
...

Special Case - User Query Time is Earlier Than Backtracking Date:

💡 Data Description
Official WeChat original article recommendations will be updated daily at 19:30 with data from the previous day. The following data is a snapshot at the time of acquisition, and there may be differences from real-time data.

We're sorry 🙏, currently we only support backtracking to the past 30 days (earliest to April 15, 2026). I will query the time range closest to your needs~

📊 Original Viral Article Recommendations
Original viral articles on April 15, 2026

| Serial No. | Author | Title | Read Count |
|------|------|------|--------|
| 1 | [Author A](link) | [Article Title](link) | 100k+ |
...

【Important】Must use the actual data returned by the script, do not use the above sample data!

【Important】As long as the data query date is inconsistent with the user's requested date, a prompt message must be displayed after the data description:

Query date > Latest date:

We're sorry 🙏, the latest data is from {query date}. I will query the original articles closest to your needs from {query date}.

Query date < Backtracking date:

We're sorry 🙏, currently we only support backtracking to the past 30 days (earliest to {backtracking date}). I will query the time range closest to your needs~

3. Generate HTML Page (Automatic Execution)

【Important】After outputting table data each time, must automatically call generate_hot_html.py to generate and open the HTML page, no additional user trigger required.

Call the script to read data from the temporary JSON file, fill the HTML template, and generate an official WeChat-style HTML page:

Script Location:

scripts/generate_hot_html.py

Parameter Instructions:

```
temp_file
```
: Temporary JSON file path (default:
```
temp_articles.json
```
)
```
output
```
: Output file path (recommended:
```
{category}_Hot Ranking.html
```
)
```
display_count
```
: Number of articles to display (Important: Must be consistent with the number displayed in the conversation)

Command Example:

bash

python scripts/generate_hot_html.py --temp_file temp_articles.json --output "Original Viral Articles_Ranking.html" --display_count 20

4. Subscription Service

Actively ask users whether they need to subscribe to specific categories:

Would you like to subscribe to account performance in specific tracks? We support:
Humanities Information, Knowledge Encyclopedia, Health Preservation, Fashion Trends, Food and Catering, Lifestyle, Travel, Funny and Humorous, Emotion and Psychology, Sports and Entertainment, Beauty and Body Care, Selected Abstracts, People's Livelihood Information, Wealth Management, Technology and Digital, Venture Capital and Business, Automobile and Transportation, Real Estate, Career Development, Education and Examinations, Academic Research, Enterprise Brand, Overall Ranking

After the user chooses to subscribe:

After successful subscription: Push the latest issue of original viral article data daily at 19:30
Not Needed for Now — Only this query

Notes

【Core Rule】Prohibit outputting script paths, code, or execution commands to users, directly display the script running results
Ranking data is obtained in real-time, and may be delayed due to network or API status
Display the first 20 articles initially, prompt users whether to display all when there are more than 20 articles
When the category is niche, prompt "There is no viral data in this field, it is recommended to change direction or check the latest original viral articles"
HTML Content Consistency: The article content in HTML must be completely consistent with the content displayed in the conversation
Data Description: Must indicate the database update date and query date when outputting

Resource Index

Script: See scripts/fetch_articles.py (Purpose: Obtain original viral article data, support category query and date query)
Script: See scripts/generate_hot_html.py (Purpose: Read data from temporary JSON file, generate official WeChat-style HTML page)
Reference: See references/category_mapping.md (Purpose: Category mapping table, including 22 standard categories and generalized keywords)

Usage Examples

Example 1: Directly Query Latest Original Viral Articles

User Input: Latest original viral articles
Agent Recognition: Direct query
Agent Call:
python scripts/fetch_articles.py --type "overall ranking" --limit 20

Output Result:
Data Description: The data updated in this query is from May 8, 2026 (data synchronized daily at 18:30), and the query is for original viral article data from May 7, 2026, which differs from real-time data.

📊 Original Viral Article Recommendations
Original viral articles from the past 30 days

| Serial No. | Author | Title | Read Count |
|------|------|------|--------|
| 1 | [A Bad Potato](link) | [The retribution came too fast this time! Japan just suffered a head-on blow](link) | 100k+ |
...

A total of 50 viral original popular articles were obtained, and the first 20 are currently displayed.

📬 Subscription Service
Would you like to subscribe to account performance in specific tracks? We support:
Humanities Information, Knowledge Encyclopedia, Health Preservation, Fashion Trends, Food and Catering, Lifestyle, Travel, Funny and Humorous, Emotion and Psychology, Sports and Entertainment, Beauty and Body Care, Selected Abstracts, People's Livelihood Information, Wealth Management, Technology and Digital, Venture Capital and Business, Automobile and Transportation, Real Estate, Career Development, Education and Examinations, Academic Research, Enterprise Brand, Overall Ranking
Subscribe to Push — Push the latest official WeChat original articles daily at 19:30
Not Needed for Now — Only this query

Example 2: Category Query

User Input: Original viral articles in technology category
Agent Recognition: Category query
Agent Matched Category: "technology and digital"
Agent Call:
python scripts/fetch_articles.py --type "technology and digital" --limit 20

Output Result:
Data Description: The data updated in this query is from May 8, 2026 (data synchronized daily at 18:30), and the query is for original viral article data from May 7, 2026, which differs from real-time data.

📊 Original Viral Article Recommendations
Original viral articles from the past 30 days

| Serial No. | Author | Title | Read Count |
|------|------|------|--------|
| 1 | [Author A](link) | [Technology Article Title 1](link) | 100k+ |
...

Example 3: Date Query

User Input: Original viral articles on May 3rd
Agent Recognition: Date query
Agent Call:
python scripts/fetch_articles.py --type "overall ranking" --start_date "2026-05-03" --limit 20

Output Result:
Data Description: The query is for original viral article data from May 3, 2026, which differs from real-time data.

📊 Original Viral Article Recommendations
Original viral articles on May 3, 2026

| Serial No. | Author | Title | Read Count |
|------|------|------|--------|
| 1 | [Author A](link) | [Article Title 1](link) | 100k+ |
...

Example 4: Category + Date Query

User Input: Original viral articles in technology category on May 3rd
Agent Recognition: Category + Date query
Agent Matched Category: "technology and digital"
Agent Call:
python scripts/fetch_articles.py --type "technology and digital" --start_date "2026-05-03" --limit 20

Output Result:
Data Description: The query is for original viral article data from May 3, 2026, which differs from real-time data.

📊 Original Viral Article Recommendations
Original viral articles on May 3, 2026

| Serial No. | Author | Title | Read Count |
|------|------|------|--------|
| 1 | [Author A](link) | [Technology Article Title 1](link) | 100k+ |
...

wechat-original-article-king

NPX Install

Tags

SKILL.md Content (Chinese)

King of Original Official WeChat Articles

Task Objectives

Startup Prompt

Visual Specifications (Important)

Preparations

Data Time Instructions

Operation Steps

1. User Intent Recognition (Handled by Agent)

2. Obtain Viral Article Data (Script Execution, Must Call Script and Display Output As-Is to Users)

3. Generate HTML Page (Automatic Execution)

4. Subscription Service

Notes

Resource Index

Usage Examples