analyze-copper-supply-concentration-risk
用公開資料量化「銅供應是否過度集中、主要產地是否結構性衰退、替代增量是否依賴少數國家」,並輸出可行的中期供應風險結論與情境推演。
npx skills add majiayu000/claude-skill-registry --skill analyze-copper-supply-concentration-risk --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
<essential_principles> <principle name="narrative_to_metrics"> **敘事轉指標(Narrative to Metrics)** 市場敘事必須可量化驗證。三大命題對應三組指標: | 命題 | 核心問題 | 量化指標 | |------|----------|----------| | A. 集中度 | 供應是否過度集中? | CR4, CR5, 份額排名 | | B. 結構衰退 | 智利是否結構性衰退? | 峰值年份、峰值回撤 | | C. 替代依賴 | 是否依賴秘魯/DRC? | 秘魯+DRC 合計份額 vs 智利份額 | **注意**:由於 MacroMicro 只提供 5 個國家的細分數據,HHI 指標不適用於本分析。 </principle> <principle name="data_source"> **數據來源:MacroMicro (WBMS)** 唯一主要來源,使用 Chrome CDP **全自動**抓取 Highcharts 圖表數據。 - URL: https://en.macromicro.me/charts/91500/wbms-copper-mine-production-total-world - 口徑: mined copper content(礦場產量的銅金屬含量) - 可用序列: World, Chile, Peru, DRC, China, US </principle> </essential_principles> <objective> 分析全球銅供應的國家集中度與結構性風險。 輸出兩層分析: 1. **Concentration**: 國家份額排名、CR4/CR5 2. **Chile vs Replacers**: 智利 vs 新興替代國(Peru + DRC)份額對比 </objective> <quick_start> **全自動執行(無需手動操作 Chrome)** **Step 1:安裝依賴** ```bash pip install requests websocket-client pandas numpy matplotlib ``` **Step 2:一鍵抓取數據(自動啟動/關閉 Chrome)** ```bash cd scripts python fetch_copper_production.py ``` 腳本會自動: - 啟動 Chrome 調試模式 - 等待頁面載入(~40 秒) - 提取 Highcharts 數據 - 儲存到 `cache/copper_production.csv` - 關閉 Chrome **Step 3:生成 Bloomberg 風格視覺化圖表** ```bash python visualize_
pip install requests websocket-client pandas numpy matplotlib cd scripts python fetch_copper_production.py python visualize_copper_concentration.py
What does the analyze-copper-supply-concentration-risk skill do?
用公開資料量化「銅供應是否過度集中、主要產地是否結構性衰退、替代增量是否依賴少數國家」,並輸出可行的中期供應風險結論與情境推演。
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill analyze-copper-supply-concentration-risk --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.
