analyze-copper-stock-resilience-dependency

<essential_principles>

<principle name="cross_asset_dependency"> **Core Logic of Cross-Asset Dependency**

Breakouts and back-and-fill pullbacks of copper prices are not solely determined by copper itself, but highly dependent on stock market resilience:

Copper Price Trend = f(Technical Level Status) × f(Stock Market Resilience) × f(Chinese Interest Rate Environment)

Key Insights:

High stock market resilience: Higher probability of copper sustaining its breakout after breaking key levels
Low stock market resilience: Copper is more likely to experience a "back-and-fill" pullback to support zones
China 10Y Yield: Serves as a dual signal of risk pressure/policy easing </principle>

<principle name="round_levels"> **Psychological Levels and Trend Status**

Important psychological integer levels for copper prices (e.g., 10,000 / 13,000 USD/ton) are key to judging breakouts and back-and-fill pullbacks:

State	Condition	Meaning
up	close > SMA(60) with positive slope	Uptrend
down	close < SMA(60) with negative slope	Downtrend
range	Otherwise	Sideways trading

Level Determination:

```
near_resistance
```
: Approaching upper resistance level
```
near_support
```
: Approaching lower support level </principle>

<principle name="equity_resilience_score"> **Equity Resilience Score (0-100)**

Quantify "stock market resilience" into a calculable score:

Factor	Weight	Calculation Method
12-month Momentum	40%	12m return quantile (vs. historical data)
Moving Average Position	40%	100 if above 12-month MA, 0 otherwise
Recent Drawdown	20%	Smaller 3m drawdown = higher score (reverse scoring)

Score Interpretation:

70-100: High resilience, higher probability of copper sustaining breakout
30-70: Neutral, need to observe other factors
0-30: Low resilience, significantly increased back-and-fill risk </principle>

<principle name="rolling_beta"> **Rolling Regression: Quantify Dependency Strength**

Calculate rolling beta coefficients of copper prices to stock market and Chinese yields:

Δcopper ~ β1 × Δequity + β2 × Δchina_yield + ε

Larger positive β1 (equity beta): Copper behaves more like a risk asset, more dependent on stock market
High quantile of β1: Market is trading copper as a risk asset alongside stocks
β1 < 0 (negative correlation): Copper decouples from stock market, showing independent logic (safe-haven/supply/energy transition narrative)
β2 (yield beta): Positive = rising yields are bullish for copper (inflation narrative), Negative = opposite </principle>

<principle name="data_access"> **Data Acquisition Methods**

This skill uses the following public data sources:

Data Type	Code/Source	Acquisition Method
Copper Futures Price	COMEX Copper (HG=F)	Yahoo Finance
Global Stock Market Cap	VT (Vanguard Total World Stock ETF)	Yahoo Finance
China 10Y Yield	MacroMicro	Selenium + Highcharts

Unit Conversion:

HG=F is in $/lb, automatically multiplied by 2204.62262 to convert to $/ton
VT ETF price multiplied by coefficient to estimate global market cap (trillion USD)
China 10Y Yield is in percentage (%) </principle>

</essential_principles>

<objective> Implement copper price-stock market resilience dependency analysis:

Data Extraction: Fetch copper prices, global stock market data, China 10Y yield
Trend and Level Determination: Calculate SMA, trend status, and which levels are being approached
Equity Resilience Score: Compute the equity_resilience_score
Dependency Quantification: Calculate β coefficients via rolling regression
Back-and-Fill Probability Estimation: Historical statistics of back-and-fill frequency (high vs. low resilience)
Scenario Interpretation: Output current "sustain breakout" or "back-and-fill" scenario

Output: Current status, dependency strength, back-and-fill probability, actionable alert flags. </objective>

<quick_start>

Fastest Way: Run Default Analysis

bash

cd skills/analyze-copper-stock-resilience-dependency
pip install pandas numpy yfinance scipy statsmodels matplotlib  # First-time use
python scripts/copper_stock_analyzer.py --quick

Sample Output:

json

{
  "as_of": "2026-01-22",
  "latest_state": {
    "copper_price_usd_per_ton": 12727,
    "copper_trend": "up",
    "equity_resilience_score": 83,
    "rolling_beta_equity_24m": -0.80
  },
  "diagnosis": {
    "narrative": "Copper is in an uptrend, approaching the 13,000 level, with high stock market resilience."
  }
}

Generate Bloomberg-Style Charts:

bash

python scripts/visualize.py \
  --start 2015-01-01 \
  -o output/copper_resilience_2026-01-22.png

Charts Include:

Copper monthly price + SMA60 (right axis, orange/red-yellow)
Global stock market cap (left axis, orange area chart)
China 10Y Yield (left axis, yellow line)
Level lines (10,000 / 13,000)

Generate Dependency Analysis Chart (Three-Panel Composite Chart):

bash

python scripts/plot_dependency_analysis.py \
  --start 2015-01-01 \
  -o ../../output/copper-dependency-analysis-2026-01-22.png

Charts Include Three Panels:

Copper Price Panel: Copper price + SMA60 + trend background color (green=uptrend, red=downtrend) + level lines
β Coefficient Panel: Rolling β time series + ±1σ interval + current quantile + negative value alert
Resilience Panel: Equity resilience score + high/low threshold lines

Full Analysis:

bash

python scripts/copper_stock_analyzer.py \
  --start 2015-01-01 \
  --end 2026-01-22 \
  --copper HG=F \
  --equity ACWI \
  --output result.json

</quick_start>

<intake> What operation do you need to perform?

Quick Check - View current copper price, stock market resilience, and level status
Full Analysis - Analyze dependency relationships and back-and-fill probability over a time period
Visualization Charts - Generate visual charts of copper prices and dependency factors
Dependency Analysis Chart - Generate three-panel dependency analysis chart (copper price + β coefficient + resilience)
Methodology Learning - Understand the logic of the cross-asset dependency model

Please select or directly provide analysis parameters. </intake>

<routing> | Response | Action | |------------------------------|--------------------------------------------------------| | 1, "quick", "check" | Execute `python scripts/copper_stock_analyzer.py --quick` | | 2, "full", "analyze" | Read `workflows/analyze.md` and execute | | 3, "visualize", "chart", "plot" | Read `workflows/visualize.md` and execute | | 4, "dependency" | Execute `python scripts/plot_dependency_analysis.py` | | 5, "learn", "methodology", "why" | Read `references/methodology.md` | | Provide parameters (e.g., date range) | Read `workflows/analyze.md` and execute with parameters |

After routing, read the corresponding document and execute. </routing>

<directory_structure>

analyze-copper-stock-resilience-dependency/
├── SKILL.md                           # This document (router)
├── skill.yaml                         # Frontend display metadata
├── manifest.json                      # Skill metadata
├── workflows/
│   ├── analyze.md                     # Full analysis workflow
│   ├── quick-check.md                 # Quick check workflow
│   └── visualize.md                   # Visualization workflow
├── references/
│   ├── methodology.md                 # Cross-asset dependency methodology
│   ├── data-sources.md                # Data sources and web scraping instructions
│   └── input-schema.md                # Complete input parameter definition
├── templates/
│   ├── output-json.md                 # JSON output template
│   └── output-markdown.md             # Markdown report template
├── scripts/
│   ├── copper_stock_analyzer.py       # Main analysis script
│   ├── fetch_data.py                  # Data fetching tool
│   ├── visualize.py                   # Bloomberg-style chart generator
│   └── plot_dependency_analysis.py    # Three-panel dependency analysis chart generator
├── data/
│   └── cache/                         # Data cache directory
└── examples/
    └── sample-output.json             # Sample output

</directory_structure>

<reference_index>

Methodology: references/methodology.md

Cross-asset dependency concept and research report alignment
Equity resilience score design
Rolling regression and beta interpretation
Back-and-fill pullback determination logic

Data Sources: references/data-sources.md

Yahoo Finance (yfinance) usage instructions
China 10Y Yield web scraping design
Data frequency and alignment methods

Input Parameters: references/input-schema.md

Complete parameter definitions
Default values and recommended ranges

</reference_index>

<workflows_index>

Workflow	Purpose	Usage Scenario
analyze.md	Full Analysis	Need detailed dependency and back-and-fill analysis
quick-check.md	Quick Check	Only want to view current status
visualize.md	Generate Visualizations	Need chart presentations
</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
copper_stock_analyzer.py	`--quick`	Quick check of current status
copper_stock_analyzer.py	`--start DATE --end DATE`	Full analysis
fetch_data.py	`--series HG=F,ACWI`	Fetch market data
visualize.py	`--start 2015-01-01 -o output/chart.png`	Generate Bloomberg-style charts
plot_dependency_analysis.py	`--start 2015-01-01 -o output/chart.png`	Generate three-panel dependency analysis chart
</scripts_index>

<input_schema_summary>

Core Parameters

Parameter	Type	Default Value	Description
start_date	string	2020-01-01	Analysis start date
end_date	string	today	Analysis end date
freq	string	1mo	Frequency (monthly)
copper_series	string	HG=F	Copper price series code
equity_proxy_series	string	ACWI	Equity proxy series code
china_10y_yield_series	string	Scraped	China 10Y Yield series

Model Parameters

Parameter	Type	Default Value	Description
ma_window	int	60	Moving average window
rolling_window	int	24	Rolling regression window (months)
round_levels	list	[10000, 13000]	Key level positions
backfill_max_drawdown	float	0.25	Maximum back-and-fill drawdown

Complete parameter definitions can be found in

references/input-schema.md

</input_schema_summary>

<output_schema_summary>

json

{
  "skill": "analyze-copper-stock-resilience-dependency",
  "as_of": "2026-01-22",
  "inputs": {
    "copper_series": "HG=F (converted to USD/ton)",
    "equity_proxy_series": "ACWI",
    "ma_window": 60,
    "rolling_window": 24
  },
  "latest_state": {
    "copper_price_usd_per_ton": 12727,
    "copper_sma_60": 9355,
    "copper_trend": "up",
    "near_resistance_levels": [13000],
    "near_support_levels": [],
    "equity_resilience_score": 91,
    "rolling_beta_equity_24m": -0.80,
    "rolling_beta_yield_24m": -0.05
  },
  "diagnosis": {
    "narrative": "Copper is in an uptrend, approaching the 13,000 level, with high stock market resilience.",
    "scenario": "Higher probability of sustaining breakout",
    "dependency_status": "Rolling β is negative (-0.80), copper has an inverse relationship with the stock market, deviating from traditional risk asset patterns"
  },
  "actionable_flags": [
    {
      "flag": "APPROACHING_RESISTANCE",
      "meaning": "Approaching key resistance level, focus on breakout potential"
    },
    {
      "flag": "NEGATIVE_BETA_REGIME",
      "meaning": "Copper has an inverse relationship with the stock market, deviating from traditional risk asset patterns"
    },
    {
      "flag": "LOW_BETA_ANOMALY",
      "meaning": "β is at an extreme historical low, copper is showing independent bullish logic decoupled from the stock market"
    }
  ]
}

Complete output structure can be found in

templates/output-json.md

. </output_schema_summary>

<success_criteria> Successful execution should produce:

Current copper price and trend status (up/down/range)
Approached key levels (resistance/support)
Equity resilience score (0-100)
Rolling beta coefficients (β_equity, β_yield)
Back-and-fill probability estimate (overall / high_resilience / low_resilience)
Scenario interpretation narrative
Actionable alert flags
Visualization charts (optional, output to
```
output/
```
directory) </success_criteria>

analyze-copper-stock-resilience-dependency

NPX Install

Tags

SKILL.md Content (Chinese)