Mystock

MyStock - 我的股票智能助手。Use when user asks about stock quotes, market analysis, limit-up tracking, shareholder dynamics, investment research, or portfolio managem...

Security Scan

The package appears to be a coherent local stock-analysis web app: its code, docs, and runtime instructions align with the described purpose, but you should review the included install/start scripts and be cautious about granting API keys or running global installers.

Purpose & Capability

Name/description (stock quotes, limit-up analysis, shareholder dynamics, portfolio UI) matches the code and files: FastAPI backend, Vue front-end, pywencai usage, local JSON/SQLite data and an AI chat bridge. The presence of optional AI provider env vars (AI_PROVIDER, AI_API_KEY) is consistent with the AI chat capability described.

Instruction Scope

SKILL.md instructs running scripts/install.sh and start.sh to install dependencies, set NODE_PATH, and start backend + frontend. The runtime instructions call local APIs and external data sources (qt.gtimg.cn, pywencai) which is expected. There are no instructions to read unrelated system secrets or arbitrarily exfiltrate local files; however the skill will forward user messages and optional history to configured external AI providers if you set AI_API_KEY.

Install Mechanism

There is no registry-level install spec but the repo includes scripts/install.sh and start.sh that the README and SKILL.md recommend running. The docs instruct installing Node.js and globally installing jsdom (npm -g jsdom), and pip installing backend requirements. Global npm installs and install scripts can modify system state and require elevated privileges; you should review scripts/install.sh and start.sh before running. The presence of install scripts increases risk compared with pure instruction-only skills.

Credentials

Registry metadata lists no required env vars; the code treats AI_PROVIDER and AI_API_KEY as optional (defaults to rule-based 'silence' provider). Requesting an AI API key is proportionate to the described AI chat feature. No other unrelated credentials are requested. Be aware that any API key you supply will be sent to the chosen provider via network calls, and chat history/messages may be transmitted.

Persistence & Privilege

The skill does not request always:true and does not modify other skills. It runs a local server and web UI when started; these are confined to the host where you run the scripts. No evidence of attempts to persist beyond the project files or to change system-wide agent settings.

Assessment

This repo is internally consistent with its stated purpose (local stock web UI + AI assistant). Before installing or running anything: 1) Manually inspect scripts/install.sh and start.sh (they run installers and may perform global npm installs); don't run unknown install scripts with sudo without review. 2) If you provide an AI API key (AI_API_KEY), understand the skill will send user messages and history to that provider — only use keys for providers you trust or run with AI_PROVIDER=silence to avoid external calls. 3) Run the app in a sandbox/container or on a throwaway VM if you want extra safety. 4) Review network endpoints used (qt.gtimg.cn, pywencai, and configured AI providers) and the scripts that may download resources. 5) If you need higher assurance, request the full contents of scripts/install.sh/start.sh and any code that the install script fetches so you can review or audit them before execution.

---

name: my-stock description: MyStock - 我的股票智能助手。Use when user asks about stock quotes, market analysis, limit-up tracking, shareholder dynamics, investment research, or portfolio management. Handles real-time prices, technical analysis, and financial data queries. metadata: version: 1.1.6 author: wangz license: MIT category: finance

MyStock - 我的股票智能助手

🎨 MyStock is a full-featured stock analysis assistant with a beautiful Web UI, providing real-time quotes, limit-up tracking, shareholder dynamics monitoring, and more!


✨ Capabilities

1. Real-time Quotes - Query stock prices and percentage changes
2. Limit-up Analysis - Track daily limit-up boards and first-board opportunities
3. Shareholder Dynamics - Monitor shareholder increases, buybacks, and executive transactions
4. Portfolio Management - Manage watchlists and investment notes
5. AI Assistant - Get AI-powered investment insights
6. 🎨 Beautiful Web UI - Modern Vue 3 + Element Plus interface

🎨 Web UI Features

The skill includes a complete web interface that users can interact with:

• Watchlist Management - Add/remove stocks with one click
• Real-time Data Display - Live price updates with color-coded changes
• Limit-up Analysis - Visual tracking of daily limit-up stocks
• Shareholder Activity - Detailed tabs for different activity types
• AI Chat Assistant - Built-in AI assistant for stock questions
• Responsive Design - Works on desktop and mobile

When to Use

Invoke this skill when the user:

• Asks about stock prices, quotes, or market data
• Mentions specific stock codes or names
• Asks about limit-up (涨停) stocks or trading opportunities
• Needs shareholder/investor activity information
• Wants to track investment portfolio
• Asks for stock analysis or research
• Wants to see a visual interface for stock analysis
• Mentions terms like: 打板, 涨停, 股东增持, 回购, 高管增持

Architecture

./
├── start.sh           # ⭐ One-click startup (UI + Backend)
├── backend/           # FastAPI backend server
│   ├── main.py       # Main API server
│   ├── ai_service.py # AI service integration
│   └── requirements.txt
├── frontend/         # Web interface
│   └── index.html    # Vue 3 single-page app ⭐
├── scripts/          # Helper scripts
│   ├── install.sh    # One-click installation script
│   ├── check_api.py  # API health check
│   └── test_skill.py # Skill trigger test
└── references/       # Documentation
    └── usage_examples.md

Quick Start

1. One-Click Installation (Recommended)

bash scripts/install.sh

This will automatically:

• ✅ Install Node.js dependencies (jsdom for pywencai)
• ✅ Install Python dependencies
• ✅ Configure environment variables
• ✅ Prepare data directories

2. ⚡ Start Everything (Recommended)

./start.sh

This one script starts:

• ✅ Backend API server (port 8000)
• ✅ Frontend web interface (port 5000)
• ✅ Automatically opens browser with UI

Or start separately:

3. Start Backend Server

cd backend
pip install -r requirements.txt
./start.sh

The backend server runs on http://localhost:8000

Important: The start.sh script automatically sets NODE_PATH for pywencai jsdom dependency.

4. Start Frontend UI

cd frontend
python -m http.server 5000

Access the web interface at http://localhost:5001

The UI will open automatically when using ./start.sh

⚠️ Important Dependencies

Node.js (Required for pywencai)

pywencai uses jsdom for web scraping, which requires Node.js:

# Install Node.js (if not installed)
# Download from: https://nodejs.org/

# Install jsdom globally
npm install -g jsdom

# Verify installation
node -e "require('jsdom')"

The startup script automatically sets NODE_PATH to find jsdom.

4. API Endpoints

Endpoint	Method	Description
/api/stocks	GET	Get stock quotes
/api/limit-up-analysis	GET	Get limit-up board analysis
/api/shareholder-activity	GET	Get shareholder dynamics
/api/portfolio	GET/POST	Manage portfolio
/api/chat	POST	AI chat assistant

Usage Examples

Example 1: Query Stock Price

User says: "查询贵州茅台的股价"

The assistant should:

1. Call API: GET /api/stocks?code=600519.SH
2. Return formatted response with price, change %, etc.

Example 2: Limit-up Analysis

User says: "查看今天的打板分析"

The assistant should:

1. Call API: GET /api/limit-up-analysis
2. Analyze and present limit-up candidates
3. Highlight first-board opportunities

Example 3: Shareholder Dynamics

User says: "最近有哪些股东增持"

The assistant should:

1. Call API: GET /api/shareholder-activity
2. Present shareholder increase data
3. Include buyback and executive transaction info

Data Sources

• Real-time quotes: Via pywencai library (同花顺问财)
• Shareholder data: Via pywencai queries
• Historical data: Stored in local JSON files

Important Notes

Investment Disclaimer

⚠️ DISCLAIMER: This tool is for educational and research purposes only. All investment decisions should be made at your own risk. Past performance does not guarantee future results.

Rate Limiting

• API calls should be throttled to avoid overwhelming the data source
• Cache frequently accessed data locally
• Maximum 1 request per second recommended

Data Accuracy

• Real-time data may have slight delays
• Historical data is cached locally
• Verify critical information through official sources

Troubleshooting

API Server Won't Start

1. Check if port 8000 is in use:

   lsof -i:8000
   

2. Verify Python dependencies:

   pip install -r requirements.txt
   

3. Check environment variables:

   cp .env.example .env
   # Edit .env with your API keys if needed
   

Data Not Loading

1. Verify API server is running:

   curl http://localhost:8000/
   

2. Check network connectivity
3. Review server logs for errors

Frontend Not Displaying

1. Ensure backend API is accessible
2. Check browser console for errors
3. Verify CORS settings in backend

Development

Project Structure

./
├── backend/
│   ├── main.py          # FastAPI application
│   ├── ai_service.py    # AI integration
│   ├── ai_config.py     # AI configuration
│   ├── sync_all_stocks.py # Stock data sync
│   └── requirements.txt  # Python dependencies
├── frontend/
│   └── index.html       # Single-file Vue 3 app
├── scripts/
│   ├── install.sh       # One-click installation script
│   ├── check_api.py     # API health check
│   └── test_skill.py    # Skill trigger test
├── references/
│   └── usage_examples.md # Detailed usage examples
└── README.md            # Project documentation

Adding New Features

1. Backend changes: Add new endpoints in main.py
2. Frontend changes: Edit frontend/index.html
3. Test thoroughly before committing

Integration with Claude Code

This skill can be used alongside Claude Code for:

• Automated stock research
• Portfolio analysis workflows
• Investment strategy discussions
• Market trend analysis

When Claude Code detects stock-related queries, it can:

1. Invoke this skill automatically
2. Use backend APIs for data
3. Provide AI-powered insights
4. Generate analysis reports

License

MIT License - See LICENSE file for details

Support

For issues or feature requests, please open an issue on the GitHub repository.