SuperAPI AI Directory
Partner with us中文AI newsFavorites
Skillswetrace

wetrace

Data & analytics

View repository

Updated 10-15 10:11

About this skill

WeChat Data Analysis Assistant

Query, analyze, and export WeChat chat data, providing AI-driven smart insights and beautifully visualized pages.

⚠️ Important Notice

  • This Skill depends on Wetrace service
  • Only supports the Windows platform(the WeChat database is located on the Windows system)
  • The Wetrace service must be installed and running before this Skill can be used

Prerequisites

  • Wetrace service: must first be installed and running Wetrace
  • Service address: The Wetrace service runs at http://127.0.0.1:5200
  • WeChat database: decrypted and loaded
  • Operating system：Windows 10/11
  • If the service is not running, first prompt the user to start the Wetrace service

Core Workflow

1. Understand user intent

Classify the user request into the following categories:

  • Query: view messages, sessions, contacts, group chats
  • Search: find messages by keyword
  • Analysis: analyze patterns, generate statistics
  • Export: export data in multiple formats
  • Insight: comprehensive analysis and recommendations
  • Visualization: generate beautiful HTML pages

2. Extract parameters

Identify key parameters from the user request:

  • Contact name: extract the person or group name
  • Time range: extract the time period
  • Keyword: extract the search term
  • Format: extract the export format

3. Call the API

This Skill provides a Python script tool to call the Wetrace API, which is more convenient than using WebFetch directly.

Method 1: Use the Python script (recommended)

Use wetrace_api.py script, located at scripts/wetrace_api.py：

# 查询会话
python scripts/wetrace_api.py sessions --keyword "张三" --limit 20

# 获取消息
python scripts/wetrace_api.py messages --talker wxid_abc123 --limit 50

# 搜索关键词
python scripts/wetrace_api.py search --keyword "项目" --limit 30

# 分析数据
python scripts/wetrace_api.py analysis hourly wxid_abc123
python scripts/wetrace_api.py analysis daily wxid_abc123

# 导出聊天记录
python scripts/wetrace_api.py export chat --talker wxid_abc123 --format html

Full script documentation: see scripts/README.md

Method 2: Call the API directly

Base URL:http://127.0.0.1:5200/api/v1

Full API documentation: refer to references/api.md

Common API Patterns

GET /sessions?keyword={名称}&limit=50
GET /messages?talker_id={id}&time_range={范围}&limit=100
GET /search?keyword={关键词}&time_range={范围}&limit=50
GET /analysis/hourly/{session_id}
GET /analysis/daily/{session_id}
GET /export/chat?talker={id}&format={格式}&time_range={范围}

4. Process and present data

Simple query/search

Present the data in a clear, structured format.

Analysis tasks

  1. Get raw data from the analysis API
  2. Use references/analysis-prompts.md template in to generate an AI summary
  3. Present in a clear structure

Export tasks

Call the export API and inform the user of the download information.

Insight tasks

  1. Collect data from multiple APIs
  2. Synthesize the information
  3. Generate comprehensive insights and recommendations
  4. Use the appropriate template in analysis-prompts.md

5. Error handling

  • API returned 404: The database may not be loaded, or the contact/conversation may not exist
  • API returned 500: Server error; it is recommended to check the logs
  • No data returned: Verify the time range and contact name
  • Server not responding: Prompt the user to start the Wetrace service

🎨 Intelligent Web Page Generation Feature

Wetrace provides 8 core visualization features, and each feature will:

  1. Call the Wetrace API to retrieve data
  2. Use AI analysis to generate a summary
  3. Use a unified design system to generate a polished HTML page
  4. Save the HTML file to ~/wetrace-exports/ and provide an access link

Available Visualization Features

When the user requests generation of a visualization page, select the corresponding feature based on the trigger keywords:

  1. Intelligent Summary Generation - Trigger words: summarize chat history, generate summary, intelligent summary

  2. To-Do Item Extraction - Trigger words: extract to-dos, find tasks, to-do items

  3. Chat Activity Heatmap - Trigger words: activity heatmap, chat time distribution

  4. Interaction Trend Analysis - Trigger words: trend analysis, interaction trends

  5. Intelligent Weekly and Monthly Reports - Trigger words: generate weekly report, generate monthly report

  6. Data Dashboard - Trigger words: generate dashboard, data overview

  7. Intelligent Conversation Summary - Trigger words: conversation summary, intelligent summary, categorized summary

  8. Customer Relationship Health - Trigger words: customer health, CRM dashboard

Design System

All generated HTML pages follow a unified design system, see references/design-system.md, including:

  • Color system: HSL-based CSS variables
  • Component library: Card, Badge, Button, Separator, Input, etc.
  • Layout system: responsive containers and unified spacing
  • Data visualization: Chart.js configuration and color schemes

HTML Page Features

All generated HTML pages:

  • ✅ Standalone operation: No server required; double-click to open in a browser
  • ✅ Responsive design: Adapts to all devices (desktop/tablet/mobile)
  • ✅ Modern styling: Uses Tailwind CSS
  • ✅ Interactive charts: Uses Chart.js for data visualization
  • ✅ Clear hierarchy: Card layout, unified spacing, semantic colors
  • ✅ Easy to share: Can be sent directly to others for viewing

Usage Workflow

When the user requests web page generation:

  1. Identify the feature: Match the corresponding feature based on trigger keywords
  2. Read the detailed documentation: Read the corresponding .md file from the references directory
  3. Collect parameters: Ask the user for the necessary parameters (session ID, time range, etc.)
  4. Call API: Retrieve the required data
  5. AI analysis: Use the templates in analysis-prompts.md to generate a summary
  6. Generate HTML: Use the design-system.md style to generate a polished page
  7. Save file: Save to ~/wetrace-exports/ directory
  8. Provide link: Return the file path and access link

Advanced features

Time range parsing

Supports multiple formats:

  • Chinese: last week, last month, this year
  • English: last week, last month, this year
  • Absolute time: 2024-01-01~2024-01-31
  • Relative days: last 7 days, last 30 days

Convert to API format:YYYY-MM-DD~YYYY-MM-DD

Contact name matching

  1. First try an exact match in the session
  2. If not found, search in contacts
  3. If there are multiple matches, ask the user to clarify
  4. Supports both the NickName and Remark fields

Pagination strategy

For large datasets:

  1. From limit=50 start
  2. If the user needs more, increase limit or use offset
  3. Inform the user of the total count
  4. If the dataset is very large, suggest exporting

Usage tips

  • Always verify the server is running before calling the API
  • Use the appropriate analysis template to keep output consistent
  • Provide actionable insights, not just raw statistics
  • Respect user privacy - do not make assumptions about relationships
  • Provide next steps or follow-up actions
  • Handle Chinese and English queries equally
  • When generating an HTML page: Always refer to the design system in design-system.md
  • File save location: Save uniformly to ~/wetrace-exports/ directory
  • Provide access link: After generation, provide the full path with the file:// protocol

🐍 Python script tools

Quick start

Script location:scripts/wetrace_api.py

Install dependencies

cd scripts
pip install -r requirements.txt

Common commands

# 查看帮助
python wetrace_api.py --help

# 查询会话
python wetrace_api.py sessions --keyword "张三" --limit 20

# 获取消息（需要会话ID）
python wetrace_api.py messages --talker wxid_abc123 --limit 50

# 按时间范围查询
python wetrace_api.py messages --talker wxid_abc123 --time-range "2024-01-01~2024-01-31"

# 全文搜索
python wetrace_api.py search --keyword "项目" --limit 30

# 数据分析
python wetrace_api.py analysis hourly wxid_abc123
python wetrace_api.py analysis daily wxid_abc123
python wetrace_api.py analysis type wxid_abc123

# 获取总览
python wetrace_api.py dashboard

# 导出聊天记录
python wetrace_api.py export chat --talker wxid_abc123 --format html

Use in code

from scripts.wetrace_api import WetraceAPI

# 创建API客户端
api = WetraceAPI()

# 查询会话
sessions = api.get_sessions(keyword="张三", limit=10)
for session in sessions:
    print(f"{session['NickName']}: {session['MessageCount']} 条消息")

# 获取消息
messages = api.get_messages(talker_id="wxid_abc123", limit=50)
for msg in messages:
    print(f"[{msg['CreateTime']}] {msg['Content']}")

# 搜索
result = api.search(keyword="项目", limit=20)
print(f"找到 {result['Total']} 条相关消息")

Full documentation: View scripts/README.md