PaperclipOrg
Claude Agent Skill · by Aradotso

Daily Stock Analysis

Install Daily Stock Analysis skill for Claude Code from aradotso/trending-skills.

Install
Terminal · npx
$npx skills add https://github.com/sugarforever/01coder-agent-skills --skill china-stock-analysis
Works with Paperclip

How Daily Stock Analysis fits into a Paperclip company.

Daily Stock Analysis drops into any Paperclip agent that handles this kind of work. Assign it to a specialist inside a pre-configured PaperclipOrg company and the skill becomes available on every heartbeat — no prompt engineering, no tool wiring.

S
SaaS FactoryPaired

Pre-configured AI company — 18 agents, 18 skills, one-time purchase.

$27$59
Explore pack
Source file
SKILL.md417 lines
Expand
---name: daily-stock-analysisdescription: LLM-powered A/H/US stock intelligent analysis system with multi-source data, real-time news, AI decision dashboards, and multi-channel push notifications via GitHub Actions.triggers:  - analyze stocks with AI  - set up daily stock analysis  - configure stock push notifications  - add stocks to watch list  - set up LLM stock analyzer  - deploy stock analysis GitHub Actions  - configure WeChat Telegram stock alerts  - backtest stock analysis accuracy--- # Daily Stock Analysis (股票智能分析系统) > Skill by [ara.so](https://ara.so) — Daily 2026 Skills collection. LLM-powered stock analysis system for A-share, Hong Kong, and US markets. Automatically fetches quotes, news, and fundamentals, generates AI decision dashboards with buy/sell targets, and pushes results to WeChat/Feishu/Telegram/Discord/Email on a schedule via GitHub Actions — zero server cost. ## What It Does - **AI Decision Dashboard**: One-line conclusion + precise buy/sell/stop-loss prices + checklist per stock- **Multi-market**: A-shares (CN), HK stocks, US stocks + indices (SPX, DJI, IXIC)- **Data sources**: AkShare, Tushare, YFinance for quotes; Tavily/SerpAPI/Brave for news- **LLM backends**: Gemini, OpenAI, Claude, DeepSeek, Qwen via LiteLLM (unified)- **Push channels**: WeChat Work, Feishu, Telegram, Discord, DingTalk, Email, PushPlus- **Automation**: GitHub Actions cron schedule, no server needed- **Web UI**: Portfolio management, history, backtesting, Agent Q&A- **Agent**: Multi-turn strategy Q&A with 11 built-in strategies (MA crossover, Elliott Wave, etc.) ## Installation ### Method 1: GitHub Actions (Recommended, Zero Cost) **Step 1: Fork the repository**```https://github.com/ZhuLinsen/daily_stock_analysis``` **Step 2: Configure Secrets** (`Settings → Secrets and variables → Actions`) **Required — at least one LLM key:**```GEMINI_API_KEY        # Google AI Studio (free tier available)OPENAI_API_KEY        # OpenAI or compatible (DeepSeek, Qwen, etc.)OPENAI_BASE_URL       # e.g. https://api.deepseek.com/v1OPENAI_MODEL          # e.g. deepseek-chat, gpt-4oAIHUBMIX_KEY          # AIHubMix (recommended, covers Gemini+GPT+Claude+DeepSeek)ANTHROPIC_API_KEY     # Claude``` **Required — stock list:**```STOCKS                # e.g. 600519,300750,AAPL,TSLA,00700.HK``` **Required — at least one notification channel:**```TELEGRAM_BOT_TOKENTELEGRAM_CHAT_IDFEISHU_WEBHOOK_URLWECHAT_WEBHOOK_URLEMAIL_SENDER / EMAIL_PASSWORD / EMAIL_RECEIVERSDISCORD_WEBHOOK_URL``` **Step 3: Trigger manually or wait for cron** Go to `Actions → stock_analysis → Run workflow` --- ### Method 2: Local / Docker ```bashgit clone https://github.com/ZhuLinsen/daily_stock_analysiscd daily_stock_analysiscp .env.example .env# Edit .env with your keyspip install -r requirements.txtpython main.py``` **Docker:**```bashdocker build -t stock-analysis .docker run --env-file .env stock-analysis``` **Docker Compose:**```bashdocker-compose up -d``` ## Configuration ### `.env` File (Local) ```env# LLM - pick one or moreGEMINI_API_KEY=your_gemini_keyOPENAI_API_KEY=your_openai_keyOPENAI_BASE_URL=https://api.deepseek.com/v1OPENAI_MODEL=deepseek-chatAIHUBMIX_KEY=your_aihubmix_key # Stock list (comma-separated)STOCKS=600519,300750,AAPL,TSLA,00700.HK # NotificationTELEGRAM_BOT_TOKEN=your_bot_tokenTELEGRAM_CHAT_ID=your_chat_id # Optional settingsREPORT_TYPE=full           # simple | full | briefANALYSIS_DELAY=10          # seconds between stocks (avoid rate limiting)MAX_WORKERS=3              # concurrent analysis threadsSINGLE_STOCK_NOTIFY=false  # push each stock immediately when doneNEWS_MAX_AGE_DAYS=3        # ignore news older than N days``` ### Multi-Channel LLM (Advanced) ```envLLM_CHANNELS=gemini,deepseek,claudeLLM_GEMINI_PROTOCOL=googleLLM_GEMINI_API_KEY=your_keyLLM_GEMINI_MODELS=gemini-2.0-flash,gemini-1.5-proLLM_GEMINI_ENABLED=true LLM_DEEPSEEK_PROTOCOL=openaiLLM_DEEPSEEK_BASE_URL=https://api.deepseek.com/v1LLM_DEEPSEEK_API_KEY=your_keyLLM_DEEPSEEK_MODELS=deepseek-chatLLM_DEEPSEEK_ENABLED=true``` ### Stock Grouping (Send Different Stocks to Different Emails) ```envSTOCK_GROUP_1=600519,300750,000858EMAIL_GROUP_1=investor1@example.com STOCK_GROUP_2=AAPL,TSLA,NVDAEMAIL_GROUP_2=investor2@example.com``` ### Market Review Mode ```envMARKET_REVIEW=cn      # cn | us | both# cn = A-share three-phase review strategy# us = US Regime Strategy (risk-on/neutral/risk-off)# both = both markets``` ## Key Commands (CLI) ```bash# Run full analysis immediatelypython main.py # Analyze specific stocks onlySTOCKS=600519,AAPL python main.py # Run web dashboardpython web_app.py# Access at http://localhost:5000 # Run with Docker (env file)docker run --env-file .env stock-analysis python main.py # Run schedule mode (waits for cron, then runs)SCHEDULE_RUN_IMMEDIATELY=true python main.py``` ## GitHub Actions Workflow The workflow file `.github/workflows/stock_analysis.yml` runs on schedule: ```yaml# Default schedule - customize in the workflow fileon:  schedule:    - cron: '30 1 * * 1-5'   # 9:30 AM CST (UTC+8) weekdays  workflow_dispatch:          # manual trigger``` **To change schedule:** Edit `.github/workflows/stock_analysis.yml` cron expression. **To add secrets via GitHub CLI:**```bashgh secret set GEMINI_API_KEY --body "$GEMINI_API_KEY"gh secret set STOCKS --body "600519,300750,AAPL,TSLA"gh secret set TELEGRAM_BOT_TOKEN --body "$TG_TOKEN"gh secret set TELEGRAM_CHAT_ID --body "$TG_CHAT_ID"``` ## Code Examples ### Programmatic Analysis (Python) ```python# Run analysis for specific stocks programmaticallyimport asynciofrom analyzer import StockAnalyzer async def analyze():    analyzer = StockAnalyzer()        # Analyze a single A-share stock    result = await analyzer.analyze_stock("600519")  # Moutai    print(result['conclusion'])    print(result['buy_price'])    print(result['stop_loss'])    print(result['target_price']) asyncio.run(analyze())``` ### Custom Notification Integration ```pythonfrom notifier import NotificationManager notifier = NotificationManager() # Send to Telegramawait notifier.send_telegram(    token=os.environ['TELEGRAM_BOT_TOKEN'],    chat_id=os.environ['TELEGRAM_CHAT_ID'],    message="📈 Analysis complete\n600519: BUY at 1680, SL: 1620, TP: 1800") # Send to Feishu webhookawait notifier.send_feishu(    webhook_url=os.environ['FEISHU_WEBHOOK_URL'],    content=analysis_report)``` ### Using the Agent API ```pythonimport requests # Ask the stock agent a strategy questionresponse = requests.post('http://localhost:5000/api/agent/chat', json={    "message": "600519现在适合买入吗？用均线金叉策略分析",    "stock_code": "600519",    "strategy": "ma_crossover"  # ma_crossover, elliott_wave, chan_theory, etc.}) print(response.json()['reply'])``` ### Backtest Analysis Accuracy ```pythonimport requests # Trigger backtest for a stockresponse = requests.post('http://localhost:5000/api/backtest', json={    "stock_code": "600519",    "days": 30  # evaluate last 30 days of AI predictions}) result = response.json()print(f"Direction accuracy: {result['direction_accuracy']}%")print(f"Take-profit hit rate: {result['tp_hit_rate']}%")print(f"Stop-loss hit rate: {result['sl_hit_rate']}%")``` ### Import Stocks from Image (Vision LLM) ```pythonimport requests # Upload screenshot of stock list for AI extractionwith open('watchlist_screenshot.png', 'rb') as f:    response = requests.post(        'http://localhost:5000/api/stocks/import/image',        files={'image': f}    ) stocks = response.json()['extracted_stocks']# Returns: [{"code": "600519", "name": "贵州茅台", "confidence": 0.98}, ...]``` ## Web Dashboard Features Start the web app:```bashpython web_app.py``` | Route | Feature ||-------|---------|| `/` | Today's analysis dashboard || `/portfolio` | Holdings management, P&L tracking || `/history` | Past analysis reports (bulk delete supported) || `/backtest` | AI prediction accuracy backtest || `/agent` | Multi-turn strategy Q&A || `/settings` | LLM channels, notification config || `/import` | Import stocks from image/CSV/clipboard | ## Supported Stock Formats ```# A-shares (6-digit code)600519    # 贵州茅台300750    # 宁德时代000858    # 五粮液 # HK stocks (5-digit + .HK)00700.HK  # 腾讯控股09988.HK  # 阿里巴巴 # US stocks (ticker)AAPLTSLANVDA # US indicesSPX       # S&P 500DJI       # Dow JonesIXIC      # NASDAQ``` ## Built-in Trading Rules | Rule | Config ||------|--------|| No chasing highs | `DEVIATION_THRESHOLD=5` (%, auto-relaxed for strong trend) || Trend trading | MA5 > MA10 > MA20 bullish alignment required || Precise targets | Buy price, stop-loss, take-profit per stock || News freshness | `NEWS_MAX_AGE_DAYS=3` (skip stale news) || Checklist | Each condition marked: ✅ Satisfied / ⚠️ Caution / ❌ Not Met | ## Troubleshooting **Analysis runs but no push received:**```bash# Check notification configpython -c "from notifier import test_all_channels; test_all_channels()" # Verify secrets are set (GitHub Actions)gh secret list``` **LLM API errors / rate limiting:**```envANALYSIS_DELAY=15        # increase delay between stocksMAX_WORKERS=1            # reduce concurrencyLITELLM_FALLBACK_MODELS=gemini-1.5-flash,deepseek-chat  # add fallbacks``` **AkShare data fetch fails (A-shares):**```bashpip install akshare --upgrade# A-share data requires Chinese network or proxy``` **YFinance US stock data issues:**```bashpip install yfinance --upgrade# US stocks use YFinance exclusively for consistency``` **GitHub Actions not triggering:**- Check Actions are enabled: `Settings → Actions → General → Allow all actions`- Verify cron syntax at [crontab.guru](https://crontab.guru)- Check workflow file exists: `.github/workflows/stock_analysis.yml` **Web auth issues (admin password):**```env# If auth was disabled and re-enabled, current password required# Reset via environment variableWEB_ADMIN_PASSWORD=new_password``` **Multi-worker deployment auth state:**```bash# Auth toggle only applies to current process# Must restart all workers to sync statedocker-compose restart``` ## Report Types ```envREPORT_TYPE=simple   # Concise: conclusion + key prices onlyREPORT_TYPE=full     # Complete: all technical + fundamental + news analysisREPORT_TYPE=brief    # 3-5 sentence summary``` **Full report includes:**- 一句话核心结论 (one-line core conclusion)- 技术面分析 (technical: MA alignment, chip distribution)- 基本面 (valuation, growth, earnings, institutional holdings)- 舆情情报 (news sentiment, social media — US stocks)- 精确买卖点位 (precise entry/exit levels)- 操作检查清单 (action checklist)- 板块涨跌榜 (sector performance boards) ## LLM Priority Order ```Gemini → Anthropic → OpenAI/AIHubMix/Compatible``` AIHubMix is recommended for single-key access to all major models without VPN:```envAIHUBMIX_KEY=$AIHUBMIX_KEY  # covers Gemini, GPT, Claude, DeepSeek# No OPENAI_BASE_URL needed — auto-configured```