# Macro Regime Detector

> 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, structu…

- **Type:** Skill
- **Install:** `agentstack add skill-xonevn-ai-xone-trading-skills-macro-regime-detector`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [xonevn-ai](https://agentstack.voostack.com/s/xonevn-ai)
- **Installs:** 0
- **Category:** [Finance & Payments](https://agentstack.voostack.com/c/finance-and-payments)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [xonevn-ai](https://github.com/xonevn-ai)
- **Source:** https://github.com/xonevn-ai/xone-trading-skills/tree/main/skills/macro-regime-detector
- **Website:** https://xone.vn

## Install

```sh
agentstack add skill-xonevn-ai-xone-trading-skills-macro-regime-detector
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# 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:
   ```bash
   python3 skills/macro-regime-detector/scripts/macro_regime_detector.py
   ```
   This fetches 600 days of data for 9 ETFs + Treasury rates (10 API calls total).

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

- **FMP API Key** (required): Set `FMP_API_KEY` environment variable or pass `--api-key`
- Free tier (250 calls/day) is sufficient (script uses ~10 calls)

## 6 Components

| # | Component | Ratio/Data | Weight | What It Detects |
|---|-----------|------------|--------|-----------------|
| 1 | Market Concentration | RSP/SPY | 25% | Mega-cap concentration vs market broadening |
| 2 | Yield Curve | 10Y-2Y spread | 20% | Interest rate cycle transitions |
| 3 | Credit Conditions | HYG/LQD | 15% | Credit cycle risk appetite |
| 4 | Size Factor | IWM/SPY | 15% | Small vs large cap rotation |
| 5 | Equity-Bond | SPY/TLT + correlation | 15% | Stock-bond relationship regime |
| 6 | Sector Rotation | XLY/XLP | 10% | Cyclical vs defensive appetite |

## 5 Regime Classifications

- **Concentration**: Mega-cap leadership, narrow market
- **Broadening**: Expanding participation, small-cap/value rotation
- **Contraction**: Credit tightening, defensive rotation, risk-off
- **Inflationary**: Positive stock-bond correlation, traditional hedging fails
- **Transitional**: Multiple signals but unclear pattern

## Output

- `macro_regime_YYYY-MM-DD_HHMMSS.json` — Structured data for programmatic use
- `macro_regime_YYYY-MM-DD_HHMMSS.md` — Human-readable report with:
  1. Current Regime Assessment
  2. Transition Signal Dashboard
  3. Component Details
  4. Regime Classification Evidence
  5. Portfolio Posture Recommendations

## Relationship to Other Skills

| Aspect | Macro Regime Detector | Market Top Detector | Market Breadth Analyzer |
|--------|----------------------|--------------------|-----------------------|
| Time Horizon | 1-2 years (structural) | 2-8 weeks (tactical) | Current snapshot |
| Data Granularity | Monthly (6M/12M SMA) | Daily (25 business days) | Daily CSV |
| Detection Target | Regime transitions | 10-20% corrections | Breadth health score |
| API Calls | ~10 | ~33 | 0 (Free CSV) |

## Script Arguments

```bash
python3 macro_regime_detector.py [options]

Options:
  --api-key KEY       FMP API key (default: $FMP_API_KEY)
  --output-dir DIR    Output directory (default: current directory)
  --days N            Days of history to fetch (default: 600)
```

## Resources

- `references/regime_detection_methodology.md` — Detection methodology and signal interpretation
- `references/indicator_interpretation_guide.md` — Guide for interpreting cross-asset ratios
- `references/historical_regimes.md` — Historical regime examples for context

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [xonevn-ai](https://github.com/xonevn-ai)
- **Source:** [xonevn-ai/xone-trading-skills](https://github.com/xonevn-ai/xone-trading-skills)
- **License:** MIT
- **Homepage:** https://xone.vn

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** yes
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-xonevn-ai-xone-trading-skills-macro-regime-detector
- Seller: https://agentstack.voostack.com/s/xonevn-ai
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.