Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/fatfingererr/macro-skillsnpx agentmods add skills/fatfingererr/macro-skills/analyze-copper-stock-resilience-dependencyWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/fatfingererr/macro-skills/analyze-copper-stock-resilience-dependency)<a href="https://agentmods.dev/skills/fatfingererr/macro-skills/analyze-copper-stock-resilience-dependency"><img src="https://agentmods.dev/badge/skills/fatfingererr/macro-skills/analyze-copper-stock-resilience-dependency/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/fatfingererr/macro-skills/analyze-copper-stock-resilience-dependency"><img src="https://agentmods.dev/badge/skills/fatfingererr/macro-skills/analyze-copper-stock-resilience-dependency.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00063 | $0.04004 |
| Opus 5 | $0.00032 | $0.02002 |
| Sonnet 5 | $0.00013 | $0.00801 |
| Haiku 4.5 | $0.00006 | $0.00400 |
Grade A, and why
analyze-copper-stock-resilience-dependency scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 348 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<essential_principles>
銅價的關卡突破與回補,並非單純由銅本身決定,而是高度依賴股市韌性:
銅價走勢 = f(技術面關卡狀態) × f(股市韌性) × f(中國利率環境)
關鍵洞察:
- 股市韌性高時:銅突破關卡後「續航」機率更高
- 股市韌性低時:銅更容易出現「back-and-fill」回補到支撐區
- 中國10Y殖利率:作為風險壓力/政策寬鬆的雙面訊號
銅價的重要心理整數位(如 10,000 / 13,000 USD/ton)是判斷突破與回補的關鍵:
| 狀態 | 條件 | 含義 |
|---|---|---|
| up | close > SMA(60) 且斜率為正 | 上升趨勢 |
| down | close < SMA(60) 且斜率為負 | 下降趨勢 |
| range | 其他 | 區間整理 |
關卡判定:
near_resistance: 接近上方關卡near_support: 接近下方支撐
將「股市韌性」量化為可計算的分數:
| 因子 | 權重 | 計算方式 |
|---|---|---|
| 12個月動能 | 40% | 12m 報酬分位數(vs 歷史) |
| 均線位置 | 40% | 是否站上 12 月均線(是=100,否=0) |
| 近期回撤 | 20% | 近 3m 回撤越小越好(反向計分) |
評分解讀:
- 70-100:高韌性,銅突破關卡後續航機率較高
- 30-70:中性,需觀察其他因子
- 0-30:低韌性,回補風險顯著上升
計算銅價對股市與中國殖利率的滾動貝塔係數:
Δcopper ~ β1 × Δequity + β2 × Δchina_yield + ε
- β1(股市貝塔)越大越正:銅越像風險資產,越依賴股市
- β1 高分位:市場正在把銅當風險資產一起交易
- β1 < 0(負相關):銅與股市脫鉤,展現獨立邏輯(避險/供給/能源轉型敘事)
- β2(殖利率貝塔):正 = 殖利率上升利好銅(通膨敘事),負 = 反之
本 skill 使用以下公開數據來源:
| 數據 | 代碼/來源 | 取得方式 |
|---|---|---|
| 銅期貨價格 | COMEX Copper (HG=F) | Yahoo Finance |
| 全球股市市值 | VT (Vanguard Total World Stock ETF) | Yahoo Finance |
| 中國10Y殖利率 | MacroMicro | Selenium + Highcharts |
單位換算:
- HG=F 為 $/lb,自動乘以 2204.62262 轉換為 $/ton
- VT ETF 價格乘以係數轉換為全球市值估計(兆美元)
- 中國10Y 為百分比(%)
</essential_principles>
- 資料擷取:抓取銅價、全球股市、中國10Y殖利率
- 趨勢與關卡判定:計算 SMA、趨勢狀態、接近哪個關卡
- 股市韌性評分:計算 equity_resilience_score
- 依賴關係量化:滾動迴歸計算 β 係數
- 回補機率估計:歷史統計回補頻率(高韌性 vs 低韌性)
- 情境判讀:輸出當前是「續航」還是「回補」情境
輸出:當前狀態、依賴強度、回補機率、可執行警報旗標。
<quick_start>
最快的方式:執行預設分析
cd skills/analyze-copper-stock-resilience-dependency
pip install pandas numpy yfinance scipy statsmodels matplotlib # 首次使用
python scripts/copper_stock_analyzer.py --quick
輸出範例:
{
"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": "銅價上升趨勢中,接近 13,000 關卡,股市韌性高檔。"
}
}
生成 Bloomberg 風格圖表:
python scripts/visualize.py \
--start 2015-01-01 \
-o output/copper_resilience_2026-01-22.png
圖表包含:
- 銅價月線 + SMA60(右軸,橙紅/黃色)
- 全球股市市值(左軸,橙色面積圖)
- 中國 10Y 殖利率(左軸,黃線)
- 關卡線(10,000 / 13,000)
生成依賴度分析圖表(三面板綜合圖):
python scripts/plot_dependency_analysis.py \
--start 2015-01-01 \
-o ../../output/copper-dependency-analysis-2026-01-22.png
圖表包含三個面板:
- 銅價面板:銅價 + SMA60 + 趨勢背景色(綠=上升,紅=下降)+ 關卡線
- β係數面板:滾動 β 時間序列 + ±1σ 區間 + 當前分位數 + 負值警示
- 韌性面板:股市韌性評分 + 高/低閾值線
完整分析:
python scripts/copper_stock_analyzer.py \
--start 2015-01-01 \
--end 2026-01-22 \
--copper HG=F \
--equity ACWI \
--output result.json
</quick_start>
- 快速檢查 - 查看目前銅價、股市韌性、關卡狀態
- 完整分析 - 分析時間區間內的依賴關係與回補機率
- 視覺化圖表 - 生成銅價與依賴因子的視覺化圖表
- 依賴度分析圖 - 生成三面板依賴度分析圖表(銅價+β係數+韌性)
- 方法論學習 - 了解跨資產依賴模型的邏輯
請選擇或直接提供分析參數。
What ships with it
15 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- examples/sample-output.json 2.7 KB
- manifest.json 3.0 KB
- references/data-sources.md 7.6 KB
- references/input-schema.md 5.6 KB
- references/methodology.md 5.4 KB
- scripts/copper_stock_analyzer.py 22 KB runs code
- scripts/fetch_data.py 20 KB runs code
- scripts/plot_dependency_analysis.py 15 KB runs code
- scripts/visualize.py 14 KB runs code
- skill.yaml 20 KB
- templates/output-json.md 6.8 KB
- templates/output-markdown.md 4.7 KB
- workflows/analyze.md 6.9 KB
- workflows/quick-check.md 2.4 KB
- workflows/visualize.md 3.5 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 348 lines · 63 tokens per session scan A 35c656329a5f
analyze-copper-stock-resilience-dependency is a skill published in the GitHub repository fatfingererr/macro-skills (3 stars, last pushed 7mo ago), licensed MIT. It adds 63 tokens to every session and 4,004 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.
reading-receipt
An image-reading workflow for extracting structured information from receipts, invoices, and hometown-tax donation certificates. It can first extract text from PDFs and otherwise read their images.