Skills

Macro Regime Detector

Detect structural macro regime transitions (1-2 year horizon) using cross-asset ratio...

Install

npx skills add tradermonty/claude-trading-skills --skill macro-regime-detector -g -a claude-code -y
Category
Engineering
Updated
3d ago
License
MIT
Context cost
Lightabout 1,086 tokens
Runs scripts
Yes, review before use

What it does

Detect structural macro regime transitions (1-2 year horizon) using cross-asset ratio analysis. Analyze RSP/SPY concentration, yield curve, credit conditions, size factor, equity-bond relationship, and sector rotation to identify regime shifts between Concentration, Broadening, Contraction, Inflationary, and Transitional states. Run when user asks about macro regime, market regime change, structural rotation, or long-term market positioning.

Macro Regime Detector

Detect structural macro regime transitions using monthly-frequency cross-asset ratio analysis. This skill identifies 1-2 year regime shifts that inform strategic portfolio positioning.

When to Use

  • User asks about current macro regime or regime transitions
  • User wants to understand structural market rotations (concentration vs broadening)
  • User asks about long-term positioning based on yield curve, credit, or cross-asset signals
  • User references RSP/SPY ratio, IWM/SPY, HYG/LQD, or other cross-asset ratios
  • User wants to assess whether a regime change is underway

Workflow

  1. Load reference documents for methodology context:

    • references/regime_detection_methodology.md
    • references/indicator_interpretation_guide.md
  2. Execute the main analysis script:

    python3 -m pip install -r skills/macro-regime-detector/requirements.txt
    uv run python3 skills/macro-regime-detector/scripts/macro_regime_detector.py --output-dir reports/
    

    This fetches 600 days of data for 9 ETFs. With an FMP key, the client tries FMP first and fetches Treasury rates (~10 API calls total), then falls back to yfinance for unavailable ETF history. Without an FMP key, it runs in yfinance-only mode and uses SHY/TLT as the yield-curve fallback.

    The detector fails closed and writes no report when none of its six components has usable data. Do not treat a missing report or non-zero exit as a valid low-transition regime.

  3. Read the generated Markdown report and present findings to user.

  4. Provide additional context using references/historical_regimes.md when user asks about historical parallels.

Prerequisites

Read the whole SKILL.md on GitHub

More in Engineering