nickel-concentration-risk-analyzer
以全球鎳供給結構為核心，量化各國的主導程度（例如印尼）、主要礦區供給量、以及政策配額/減產情境對全球供需平衡與價格非對稱的影響。
npx skills add majiayu000/claude-skill-registry --skill nickel-concentration-risk-analyzer --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> **鎳供給集中度分析 核心原則** <principle name="unit_enforcement"> **口徑先行（Unit Enforcement）** 所有分析必須先確定口徑，不同口徑會導致數量級差異： | 口徑 | 說明 | 典型數值差異 | |-----------------|-----------------------------|--------------| | `t_Ni_content` | 鎳金屬含量（本 Skill 預設） | 基準值 | | `t_ore_wet` | 礦石濕噸 | 可達 50-100x | | `t_NPI_product` | NPI 產品噸 | 約 10-15% Ni | | `t_matte` | 鎳鋶噸 | 約 75% Ni | **強制規則**： - 若輸入數據口徑不明確，必須標記為 `model_estimate` - 同一分析中不得混用不同口徑數據 - 輸出必須包含 `unit` 欄位 </principle> <principle name="supply_type_clarity"> **供給類型區分（Supply Type Clarity）** 鎳供給鏈各階段必須分開計算： ``` Mine Production (mined) → Intermediate (NPI/Matte/MHP) → Refined (class1/class2) ``` - **mined**: 礦場產量（鎳金屬含量） - **refined**: 精煉產量（含冶煉） - 「印尼 60% 市佔」通常指 **mined nickel content** </principle> <principle name="data_tiering"> **數據分層策略（Data Tiering）** | Tier | 特性 | 來源 | 用途 | |------|----------------------|----------------|--------------------| | 0 | 免費、穩定、口徑一致 | USGS MCS, INSG | Baseline 主幹 | | 1 | 免費但分散、需整合 | 公司年報、財報 | Mine-level 錨點 | | 2 | 付費、更即時完整 | S&P Global MI | 精度驗證、對齊口徑 | | 3 | 政策/配額近期訊息 | 新聞、官方公告 | 情境輸入 | **優先順序**：Tier 0 建立 baseline → Tier 1 補充 mine-level → Tier 2 驗證精度 </principle> <principle name="execution_probability"> **政策執行機率
python scripts/nickel_pipeline.py analyze --asof=2026-01-16 --scope=mined python scripts/visualize_concentration.py python scripts/nickel_pipeline.py scenario --cut=20 --target=Indonesia --exec-prob=0.5 python scripts/visualize_scenario.py python scripts/nickel_pipeline.py validate --claim="Indonesia 60% share"
What does the nickel-concentration-risk-analyzer skill do?
以全球鎳供給結構為核心，量化各國的主導程度（例如印尼）、主要礦區供給量、以及政策配額/減產情境對全球供需平衡與價格非對稱的影響。
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill nickel-concentration-risk-analyzer --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.