# AI use cases for Daily Stock Analysis (ZhuLinsen/daily_stock_analysis) Repo: [ZhuLinsen/daily_stock_analysis](https://github.com/ZhuLinsen/daily_stock_analysis) | Use cases: 3 | Page: https://dedupedai.com/use-cases/zhulinsen-daily-stock-analysis/ daily_stock_analysis is an LLM powered stock analysis system for China A-shares, Hong Kong, US, Japanese, Korean and Taiwan stocks. It pulls quotes, candles, indicators, news and fundamentals, has a model write a decision dashboard with a score, trend, price levels, risk alerts and a checklist for each stock on your watchlist, and pushes it to Telegram, Discord, Slack, email, WeChat Work or Feishu. It can run free on GitHub Actions, in Docker, locally or as a web workbench. Not financial advice: paper trade first, and remember you can lose money. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Get a daily AI stock dashboard on Telegram for free: https://dedupedai.com/use-cases/zhulinsen-daily-stock-analysis/get-a-daily-ai-stock-dashboard-on-telegram/ - Analyse a few stocks on demand from your terminal: https://dedupedai.com/use-cases/zhulinsen-daily-stock-analysis/analyze-a-few-stocks-on-demand/ - Ask an AI agent about a stock in a web workbench: https://dedupedai.com/use-cases/zhulinsen-daily-stock-analysis/ask-an-agent-about-a-stock-in-the-web-workbench/ ## How to get a daily AI stock dashboard on Telegram for free with Daily Stock Analysis Repo: [ZhuLinsen/daily_stock_analysis](https://github.com/ZhuLinsen/daily_stock_analysis) | Difficulty: Beginner | Time: 30 minutes | Basis: From the README Fork the repo, add a few GitHub secrets, and GitHub Actions sends your watchlist analysis every weekday. **Who it is for:** An investor with a handful of stocks who wants an automatic evening summary without paying for a server. **The problem:** Checking news, charts and fundamentals for every stock you hold every day takes time you do not have. **The outcome:** A decision dashboard per stock with a score, trend view, buy and sell levels, risk alerts and catalysts, delivered to your chat app. ### Steps 1. Fork the repository on GitHub 2. Under Settings, Secrets and variables, Actions, add one AI key (for example GEMINI_API_KEY) and your watchlist as STOCK_LIST, such as AAPL 3. Add a notification channel, for example TELEGRAM_BOT_TOKEN and TELEGRAM_CHAT_ID 4. Enable workflows on the Actions tab, then run the daily analysis workflow once by hand to test 5. It then runs every weekday at 18:00 Beijing time and skips market holidays ### Prompt to paste into your agent ```text Set up ZhuLinsen/daily_stock_analysis on GitHub Actions in my fork with STOCK_LIST=, and Telegram delivery. Trigger one manual run and tell me whether the dashboard arrived and which data sources it fell back to. ``` ### Caveat The free default data sources can be rate limited or change, and the project says it is for study and research only, not investment advice. Not financial advice: paper trade first, and remember you can lose money. Risk, credentials: API keys and bot tokens go in GitHub Actions secrets, never in the repo files of your fork. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/zhulinsen-daily-stock-analysis/get-a-daily-ai-stock-dashboard-on-telegram/ ## How to analyse a few stocks on demand from your terminal with Daily Stock Analysis Repo: [ZhuLinsen/daily_stock_analysis](https://github.com/ZhuLinsen/daily_stock_analysis) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Run the analysis locally for any tickers you pass, or get a market review, whenever you want. **Who it is for:** A developer who wants a quick AI read on a few names across markets before the open. **The problem:** Waiting for a scheduled run is too slow when one stock suddenly moves. **The outcome:** A fresh analysis of the tickers you chose, or a market wide review, printed and pushed to your channels. ### Steps 1. Clone the repo, then run `pip install -r requirements.txt` 2. Run `cp .env.example .env` and fill in your AI key and notification settings 3. Test without sending anything with `python main.py --dry-run` 4. Analyse specific stocks with `python main.py --stocks 600519,hk00700,AAPL,2330.TW` 5. Get a market review with `python main.py --market-review` ### Prompt to paste into your agent ```text Install ZhuLinsen/daily_stock_analysis locally, configure .env with and run python main.py with --stocks . Show me the score, trend and risk alerts for each stock, and note any data source that failed. ``` ### Caveat AI written price levels are model output on free data, so check them against your broker. Not financial advice: paper trade first, and remember you can lose money. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/zhulinsen-daily-stock-analysis/analyze-a-few-stocks-on-demand/ ## How to ask an AI agent about a stock in a web workbench with Daily Stock Analysis Repo: [ZhuLinsen/daily_stock_analysis](https://github.com/ZhuLinsen/daily_stock_analysis) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Start the local web UI and use the chat page to question a stock with built-in strategies, backtests and holdings. **Who it is for:** An investor who prefers asking follow-up questions in a browser over reading a fixed report. **The problem:** A one-shot report cannot answer your next question about the same stock. **The outcome:** A local workbench with history, full reports, backtests, holdings and an agent you can question in several turns. ### Steps 1. Configure .env with any working AI key 2. Start the workbench with `python main.py --webui` 3. Open http://127.0.0.1:8000 in your browser 4. Use the /chat page to ask about a stock with one of the built-in strategies, and follow up in several turns 5. Set AGENT_MODE=false if you want to turn the agent off ### Prompt to paste into your agent ```text Run ZhuLinsen/daily_stock_analysis with python main.py --webui, open the /chat page and ask about using the trend strategy. Summarise the answer and list which data tools the agent called. ``` ### Caveat Custom strategy files and multi-agent mode are marked experimental. Not financial advice: paper trade first, and remember you can lose money. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/zhulinsen-daily-stock-analysis/ask-an-agent-about-a-stock-in-the-web-workbench/