
Daily Stock Analysis
Schedule LLM-powered A/H/US stock dashboards with buy/sell targets and push alerts via GitHub Actions without running your own server.
Overview
daily-stock-analysis is an agent skill most often used in Grow (also Build) that sets up scheduled multi-market stock analysis and push notifications via GitHub Actions and LiteLLM.
Install
npx skills add https://github.com/aradotso/trending-skills --skill daily-stock-analysisWhat is this skill?
- AI decision dashboard: one-line conclusion plus buy/sell/stop-loss and checklist per symbol
- Multi-market coverage: A-shares, HK, US equities and major indices
- Data from AkShare, Tushare, YFinance plus Tavily/SerpAPI/Brave for news
- LiteLLM-unified LLM backends and multi-channel push (WeChat Work, Feishu, Telegram, Discord, email, and more)
- GitHub Actions cron automation with stated zero-server-cost deployment model
- Multi-channel push list (WeChat Work, Feishu, Telegram, Discord, DingTalk, Email, PushPlus)
- Zero server cost positioning via GitHub Actions automation
Adoption & trust: 1.6k installs on skills.sh; 31 GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You cannot reliably synthesize multi-market quotes, news, and trade levels before the open without manual tab hopping or a always-on server.
Who is it for?
Solo builders tracking A/H/US watchlists who want cron-driven AI briefings and mobile push without maintaining VPS infrastructure.
Skip if: Users who need licensed investment advice, regulated execution, or markets outside the documented CN/HK/US coverage.
When should I use this skill?
User wants to analyze stocks with AI, set up daily analysis, configure push notifications, manage a watch list, deploy GitHub Actions, or backtest analysis accuracy.
What do I get? / Deliverables
You deploy a scheduled pipeline that produces AI stock dashboards and pushes them to your chosen channels with zero self-hosted server in the documented model.
- Scheduled AI stock decision dashboards
- Configured multi-channel alert delivery
- Portfolio web UI with history and backtest views
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Grow is the primary shelf because the system compounds decision support—watchlists, scheduled analysis, and notification loops for portfolio attention. Analytics fits AI-generated dashboards, fundamentals, news synthesis, and backtesting views rather than one-off trades.
Where it fits
Add symbols to the watchlist and receive morning AI dashboards with target prices before market open.
Wire AkShare or YFinance plus Tavily news keys and LiteLLM model routing in GitHub Actions secrets.
Tune cron and push channels when a notification provider rate-limits or fails overnight runs.
How it compares
Opinionated scheduled analysis kit with push channels, not a single-shot “analyze this ticker” chat prompt.
Common Questions / FAQ
Who is daily-stock-analysis for?
Indie developers and active retail investors comfortable configuring API keys, GitHub Actions, and LiteLLM for automated equity briefings.
When should I use daily-stock-analysis?
In Grow when standing up watchlist analytics and alerts; in Build when wiring data providers, LLM keys, and GitHub Actions for the first time.
Is daily-stock-analysis safe to install?
It uses many third-party APIs and stores secrets in CI; review the Security Audits panel on this page and never commit brokerage or LLM keys to public repos.
SKILL.md
READMESKILL.md - Daily Stock Analysis
# 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/v1 OPENAI_MODEL # e.g. deepseek-chat, gpt-4o AIHUBMIX_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_TOKEN TELEGRAM_CHAT_ID FEISHU_WEBHOOK_URL WECHAT_WEBHOOK_URL EMAIL_SENDER / EMAIL_PASSWORD / EMAIL_RECEIVERS DISCORD_WEBHOOK_URL ``` **Step 3: Trigger manually or wait for cron** Go to `Actions → stock_analysis → Run workflow` --- ### Method 2: Local / Docker ```bash git clone https://github.com/ZhuLinsen/daily_stock_analysis cd daily_stock_analysis cp .env.example .env # Edit .env with your keys pip install -r requirements.txt python main.py ``` **Docker:** ```bash docker build -t stock-analysis . docker run --env-file .env stock-analysis ``` **Docker Compose:** ```bash docker-compose up -d ``` ## Configuration ### `.env` File (Local) ```env # LLM - pick one or more GEMINI_API_KEY=your_gemini_key OPENAI_API_KEY=your_openai_key OPENAI_BASE_URL=https://api.deepseek.com/v1 OPENAI_MODEL=deepseek-chat AIHUBMIX_KEY=your_aihubmix_key # Stock list (comma-separated) STOCKS=600519,300750,AAPL,TSLA,00700.HK # Notification TELEGRAM_BOT_TOKEN=your_bot_token TELEGRAM_CHAT_ID=your_chat_id # Optional settings REPORT_TYPE=full # simple | full | brief ANALYSIS_DELAY=10 # seconds between stocks (avoid rate limiting) MAX_WORKERS=3 # concurrent analysis threads SINGLE_STOCK_NOTIFY=false # push each stock immediately when done NEWS_MAX_AGE_DAYS=3 # ignore news older than N days ``` ### Multi-Channel LLM (Advanced) ```env LLM_CHANNELS=gemini,deepseek,claude LLM_GEMINI_PROTOCOL=google LLM_GEMINI_API_KEY=your_key LLM_GEMINI_MODELS=gemini-2.0-flash,gemini-1.5-pro LLM_GEMINI_ENABLED=true LLM_DEEPSEEK_PROTOCOL=openai LLM_DEEPSEEK_B