Financial Researcher - Claude Code Skill
Autonomous financial analysis engine. Given a stock ticker, runs 10 AI investment agents and generates an IB-grade Excel report.
How to invoke
When the user asks to analyze a stock, run:
python run.py <TICKER>
With custom peer universe
python run.py <TICKER> --peers MSFT GOOGL AMZN META
Terminal summary only (no Excel)
python run.py <TICKER> --no-excel
Custom output path
python run.py <TICKER> --output path/to/report.xlsx
Suppress terminal output
python run.py <TICKER> --quiet
What it does
- Fetches data from yfinance, SEC EDGAR, Alpha Vantage, and FRED
- Runs 10 AI investment agents sequentially:
- Ben Graham, Warren Buffett, Aswath Damodaran, Cathie Wood, Michael Burry
- Fundamentals Analyst, Technical Analyst, Valuation Analyst, Risk Manager
- Portfolio Manager (synthesizes all 9 signals into a final recommendation)
- Prints a terminal summary (consensus, agent breakdown, risk snapshot)
- Generates an Excel workbook in
output/<TICKER>_<date>.xlsx
Excel output (5 sheets)
| Sheet |
Contents |
| Financials |
Income statement, cash flow, balance sheet (5-year historical) |
| Multiples |
Peer comparables with user-editable weights |
| DCF Model |
IB-style DCF with Excel formulas and sensitivity table |
| Analyst Panel |
All 10 agents - signal, score, reasoning, key risks |
| Summary |
Investment decision, consensus, PM thesis, risk snapshot |
Web UI alternative
For interactive browser-based exploration, suggest starting the Streamlit app instead of the CLI:
python -m streamlit run app.py
Opens at http://localhost:8501. The web UI displays:
- Key valuation metrics with data disclaimer for missing API values
- Consensus + Portfolio Manager decision and full reasoning
- Agent breakdown table (signal, confidence, score, action)
- Full agent reasoning & key risks (expandable section)
- Peer comparables table (P/S, P/E, Fwd P/E, EV/EBITDA, P/FCF, Beta)
- Risk snapshot (Beta, Sharpe, Max Drawdown, Volatility, Kelly sizing)
- One-click Excel report download
Suggest this when the user wants to:
- Explore results visually in a browser
- Share the tool with someone who doesn't use the terminal
- Download the Excel from a UI instead of the command line
Notes
- Analysis takes 2–5 minutes (Groq rate limits cause automatic retries)
- Data is cached for 24 hours in
cache/financial_data.db
- Excel is saved to
output/ (gitignored, directory tracked)
- Requires
.env with GROQ_API_KEY (see INSTALL.md)
1---2name: financial-researcher3description: Financial Researcher - Claude Code Skill4---5# Financial Researcher - Claude Code Skill67Autonomous financial analysis engine. Given a stock ticker, runs 10 AI investment agents and generates an IB-grade Excel report.89## How to invoke1011When the user asks to analyze a stock, run:1213```bash14python run.py <TICKER>15```1617### With custom peer universe18```bash19python run.py <TICKER> --peers MSFT GOOGL AMZN META20```2122### Terminal summary only (no Excel)23```bash24python run.py <TICKER> --no-excel25```2627### Custom output path28```bash29python run.py <TICKER> --output path/to/report.xlsx30```3132### Suppress terminal output33```bash34python run.py <TICKER> --quiet35```3637## What it does38391. Fetches data from yfinance, SEC EDGAR, Alpha Vantage, and FRED402. Runs 10 AI investment agents sequentially:41 - Ben Graham, Warren Buffett, Aswath Damodaran, Cathie Wood, Michael Burry42 - Fundamentals Analyst, Technical Analyst, Valuation Analyst, Risk Manager43 - Portfolio Manager (synthesizes all 9 signals into a final recommendation)443. Prints a terminal summary (consensus, agent breakdown, risk snapshot)454. Generates an Excel workbook in `output/<TICKER>_<date>.xlsx`4647## Excel output (5 sheets)4849| Sheet | Contents |50|-------|----------|51| Financials | Income statement, cash flow, balance sheet (5-year historical) |52| Multiples | Peer comparables with user-editable weights |53| DCF Model | IB-style DCF with Excel formulas and sensitivity table |54| Analyst Panel | All 10 agents - signal, score, reasoning, key risks |55| Summary | Investment decision, consensus, PM thesis, risk snapshot |5657## Web UI alternative5859For interactive browser-based exploration, suggest starting the Streamlit app instead of the CLI:6061```bash62python -m streamlit run app.py63```6465Opens at `http://localhost:8501`. The web UI displays:66- Key valuation metrics with data disclaimer for missing API values67- Consensus + Portfolio Manager decision and full reasoning68- Agent breakdown table (signal, confidence, score, action)69- Full agent reasoning & key risks (expandable section)70- Peer comparables table (P/S, P/E, Fwd P/E, EV/EBITDA, P/FCF, Beta)71- Risk snapshot (Beta, Sharpe, Max Drawdown, Volatility, Kelly sizing)72- One-click Excel report download7374Suggest this when the user wants to:75- Explore results visually in a browser76- Share the tool with someone who doesn't use the terminal77- Download the Excel from a UI instead of the command line7879## Notes8081- Analysis takes 2–5 minutes (Groq rate limits cause automatic retries)82- Data is cached for 24 hours in `cache/financial_data.db`83- Excel is saved to `output/` (gitignored, directory tracked)84- Requires `.env` with GROQ_API_KEY (see INSTALL.md)
jabondanoaraoz