zeberg-salomon-rotator

<essential_principles>

The Zeberg–Salomon model simplifies the market into two states:

RISK_ON: hold stocks (SPY), expansion phase
RISK_OFF: hold long bonds (TLT), contraction phase

The switching logic is based on the business cycle pattern that "leading indicators weaken first, coincident indicators confirm later".

Type	Function	Typical components	Lead time
Leading	Early warning	Yield curve, new orders, housing permits	6-12 months
Coincident	Confirmation	Employment, industrial production, real income	Coincident

Composition method：

Apply transform to each series (yoy/mom/diff)
Unify direction (direction +1/-1)
Rolling z-score standardization
EMA smoothing
Weighted composition

Iceberg Event: LeadingIndex < iceberg_threshold
  → 預警：景氣開始轉弱
  → 搭配「領先指標下降」+ 可選「市場亢奮」濾鏡

Sinking Event: CoincidentIndex < sinking_threshold
  → 確認：實體經濟收縮
  → 通常在 Iceberg 之後數月發生

State machine logic：

RISK_ON → RISK_OFF: Iceberg continuous confirmation + negative slope
RISK_OFF → RISK_ON: leading indicators rebound above (threshold + hysteresis)

This skill usesNo API key required data sources:

FRED CSV: https://fred.stlouisfed.org/graph/fredgraph.csv?id={SERIES_ID}
Yahoo Finance: yfinance package to fetch SPY, TLT, VIX

The script is located in the scripts/ directory and can be run directly.

</essential_principles>

Construct indicators: synthesize LeadingIndex and CoincidentIndex from FRED data
Detect events: identify "Iceberg" (leading indicators weakening) and "Sinking" (coincident confirmation)
Switch signals: generate RISK_ON ↔ RISK_OFF switching events
Backtest performance: calculate cumulative return, MaxDD, CAGR, and compare with benchmark

Output: switch event list, indicator time series, backtest summary, diagnostic information.

<quick_start>

The fastest way: run the default backtest

cd skills/zeberg-salomon-rotator
pip install pandas numpy yfinance pandas-datareader  # 首次使用
python scripts/rotator.py --quick

Example output:

{
  "state": "RISK_ON",
  "latest_indices": {"LeadingIndex": 0.41, "CoincidentIndex": 0.22},
  "iceberg_event": false,
  "sinking_event": false,
  "last_switch": {"date": "2023-06-30", "action": "EXIT_LONG_BOND_ENTER_EQUITY"}
}

Full backtest：

python scripts/rotator.py --start 2000-01-01 --end 2026-01-01 --output result.json

</quick_start>

Quick check - view the current business cycle state and latest indicators
Full backtest - run a complete historical backtest and performance analysis
Visualization charts - generate multi-panel backtest result charts
Monitoring mode - set up continuous monitoring and switching alerts
Methodology learning - understand the logic of the Zeberg-Salomon model

Please choose or directly provide analysis parameters.

After routing, read the corresponding document and execute.

<directory_structure>

zeberg-salomon-rotator/
├── SKILL.md                           # 本文件（路由器）
├── skill.yaml                         # 前端展示元數據
├── manifest.json                      # 技能元數據
├── workflows/
│   ├── backtest.md                    # 完整回測工作流
│   ├── visualize.md                   # 視覺化工作流
│   ├── monitor.md                     # 持續監控工作流
│   └── analyze.md                     # 深度分析工作流
├── references/
│   ├── data-sources.md                # FRED 系列代碼與資料來源
│   ├── methodology.md                 # Zeberg-Salomon 方法論解析
│   └── input-schema.md                # 完整輸入參數定義
├── templates/
│   ├── output-json.md                 # JSON 輸出模板
│   └── output-markdown.md             # Markdown 報告模板
└── scripts/
    ├── rotator.py                     # 主輪動腳本
    ├── visualize.py                   # 視覺化繪圖工具
    └── fetch_data.py                  # 數據抓取工具

</directory_structure>

<reference_index>

Methodology: references/methodology.md

Zeberg-Salomon model concepts
Iceberg/Sinking event definitions
Two-state switching logic

Data sources: references/data-sources.md

FRED series codes (leading/coincident)
Yahoo Finance asset codes
Data frequency and alignment

Input parameters: references/input-schema.md

Complete parameter definitions
Default values and recommended ranges

</reference_index>

<workflows_index>

Workflow	Purpose	When to use
backtest.md	Full historical backtest	When performance analysis is needed
visualize.md	Generate visualization charts	When chart presentation is needed
monitor.md	Continuous monitoring status	Daily monitoring or alerts
analyze.md	In-depth indicator analysis	Understand the current market state
</workflows_index>

<templates_index>

Template	Purpose
output-json.md	JSON output structure definition
output-markdown.md	Markdown report template
</templates_index>

<scripts_index>

Script	Command	Purpose
rotator.py	`--quick`	Quick check of the current state
rotator.py	`--start DATE --end DATE`	Full backtest
visualize.py	`-i result.json -o chart.png`	Generate visualization charts
fetch_data.py	`--series T10Y3M,PAYEMS`	Fetch FRED data
</scripts_index>

<input_schema_summary>

Core parameters

Parameter	Type	Default value	Description
start_date	string	2000-01-01	Backtest start date
end_date	string	today	Backtest end date
freq	string	M	Frequency (M=monthly)
equity_proxy	string	SPY	Risk asset proxy
bond_proxy	string	TLT	Long bond proxy

Threshold parameters

Parameter	Type	Default value	Description
iceberg_threshold	number	-0.3	Leading indicator threshold
sinking_threshold	number	-0.5	Coincident indicator threshold
confirm_periods	int	2	Number of consecutive confirmation periods
hysteresis	number	0.15	Entry/exit spacing

Full parameter definitions are in references/input-schema.md。

</input_schema_summary>

<output_schema_summary>

{
  "skill": "zeberg-salomon-rotator",
  "as_of": "2026-01-14",
  "state": "RISK_ON",
  "latest_indices": {
    "LeadingIndex": 0.41,
    "CoincidentIndex": 0.22,
    "iceberg_event": false,
    "sinking_event": false
  },
  "switch_events": [...],
  "backtest_summary": {
    "cagr": 0.123,
    "max_drawdown": -0.27,
    "turnovers": 10
  }
}

Full output structure is in templates/output-json.md。 </output_schema_summary>

<success_criteria> Successful execution should produce:

Current state (RISK_ON or RISK_OFF)
LeadingIndex and CoincidentIndex values
Iceberg/sinking event determination
List of switch events (including date and reason)
Backtest performance summary (CAGR, MaxDD, number of turnovers)
Comparison with benchmarks (buy-and-hold, 60/40)
Diagnostic information (contribution of each indicator)
Visualization charts (optional, output to output/ directory) </success_criteria>

About this skill