investment-committee

Original：🇨🇳 Chinese
Translated
2 scripts

Form a high-level investment committee consisting of three virtual experts modeled after legendary investors (Buffett, Wood, Druckenmiller) to conduct independent multi-round adversarial debates. True independent thinking is achieved through physically isolated Gemini API calls, and final resolutions are formed via voting. Use when evaluating investment decisions, reviewing stock research reports, or seeking multi-perspective analysis on public companies.

7installs
Sourcez1993/alphamao_skills
Added on

NPX Install

npx skill4agent add z1993/alphamao_skills investment-committee

Tags

Translated version includes tags in frontmatter
multi-agent-systeminvestment-analysisgemini-apiadversarial-debatellm-application

SKILL.md Content (Chinese)

View Translation Comparison →

Investment Committee (Multi-Agent Adversarial V3)

Launch a virtual committee modeled after three top investors to conduct rigorous independent reviews, adversarial debates, and voting resolutions on target companies.

⚔️ Core Design Principles

  1. Physical Isolation: Each Agent is an independent Gemini API call with a complete Persona system prompt.
  2. In-Depth Persona: Generalized investment philosophy framework, not dependent on specific cases.
  3. Data Injection: Automatically fetch real-time macro data (interest rates, exchange rates, VIX), and use forward fill (
    ffill
    ) to handle holidays/missing data, ensuring Druckenmiller always receives valid intelligence.
  4. Intelligent Retry: Built-in Exponential Backoff mechanism to automatically handle API 429 rate-limiting errors.
  5. Resolution Mechanism: Debate ends --> automatically extract votes --> Chairman Agent forms resolution.

👥 Committee Members

RoleCore Investment PhilosophyData Injection
Buffett"Business" mindset, moat, margin of safetyStandard research reports
WoodWright's Law, S-curve inflection point, technology integrationStandard research reports
DruckenmillerLiquidity first, price action, asymmetric oddsReal-time macro snapshot (U.S. Treasuries/USD/VIX)
Detailed personas can be found in: 
references/personas/
directory.

🔄 Execution Process

Pre-Flight: Data Fetching

The script automatically fetches from Yahoo Finance:
  • 10-year U.S. Treasury Yield (
    ^TNX
    )
  • U.S. Dollar Index (
    DX-Y.NYB
    )
  • VIX (
    ^VIX
    )
  • S&P/Nasdaq trends (
    SPY
    , 
    QQQ
    )

Phase 1: Independent Review

Each expert reads the research report (Druckenmiller additionally receives macro data) and provides an independent judgment.

Phase 2: Adversarial Debate

Multi-round debates with targeted rebuttals and position updates.

Phase 3: Voting & Decision

  • Extract each expert's vote (Buy/Reject/Hold) and confidence level.
  • Generate the Final Resolution of the Investment Committee combined with the macro background.

🛠️ Tech Stack

  • LLM: Google Gemini 2.0 Flash (
    google-genai
    )
  • Data: Yahoo Finance (
    yfinance
    )
  • Env: Supports HTTP proxy

🚀 Usage

1. Install Dependencies

bash
pip install -r requirements.txt

2. Set Up Environment

bash
# Windows PowerShell
$env:GEMINI_API_KEY='<YOUR_API_KEY>'  # Replace with your Gemini API Key

# Optional proxy (e.g., using Clash/V2Ray, etc.)
$env:HTTP_PROXY='http://127.0.0.1:<PORT>'  # Replace with your proxy port
$env:HTTPS_PROXY='http://127.0.0.1:<PORT>'
Get API Key: Visit Google AI Studio to create an API Key

3. Run

bash
python scripts/run_committee.py <path_to_report.md> --rounds 3 --output ./output

📁 Skill Directory Structure

investment-committee/
├── SKILL.md                      # This file (architecture description)
├── TROUBLESHOOTING.md            # Troubleshooting
├── requirements.txt              # Dependencies (google-genai, yfinance)
├── scripts/
│   └── run_committee.py          # Core execution script (includes data fetching logic)
└── references/
    └── personas/                 # Generalized persona prompts
        ├── buffett.md
        ├── wood.md
        └── druckenmiller.md