Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add fatfingererr/macro-skills --skill analyze-copper-inventory-rebuild-signalgit clone --depth 1 https://github.com/fatfingererr/macro-skillsWrote 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-inventory-rebuild-signal)<a href="https://agentmods.dev/skills/fatfingererr/macro-skills/analyze-copper-inventory-rebuild-signal"><img src="https://agentmods.dev/badge/skills/fatfingererr/macro-skills/analyze-copper-inventory-rebuild-signal/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-inventory-rebuild-signal"><img src="https://agentmods.dev/badge/skills/fatfingererr/macro-skills/analyze-copper-inventory-rebuild-signal.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 | $0.03821 |
| Opus 5 | $0.00032 | $0.01911 |
| Sonnet 5 | $0.00013 | $0.00764 |
| Haiku 4.5 | $0.00006 | $0.00382 |
Grade A, and why
analyze-copper-inventory-rebuild-signal 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 — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<essential_principles>
本技能將「肉眼看圖」轉換為可量化、可自動更新的雙層訊號系統:
| 層次 | 問題 | 核心指標 | 決策輸出 |
|---|---|---|---|
| 短線 | 是否「有點超前」? | SHFE 回補速度 z-score + 庫存水位 | CAUTION / NEUTRAL / SUPPORTIVE |
| 長線 | 是否「仍偏便宜」? | 銅價歷史分位數(10 年) | CHEAP / FAIR / RICH |
關鍵洞察:SHFE 庫存快速回補 + 水位偏高 → 常常貼近價格局部高點。
使用 Chrome CDP 全自動抓取 Highcharts 圖表數據,共需三類數據:
| 數據 | 來源 | URL |
|---|---|---|
| SHFE 銅庫存 | MacroMicro (CDP) | https://en.macromicro.me/series/8743/copper-shfe-warehouse-stock |
| COMEX 銅庫存 | MacroMicro (CDP) | https://www.macromicro.me/series/8742/copper-comex-warehouse-stock |
| 銅期貨價格 | Yahoo Finance | HG=F(COMEX 銅期貨連續近月) |
口徑:庫存為可交割銅庫存(噸)、價格為收盤價(USD/lb)
將主觀「回補很快」轉化為客觀可比較的標準化指標:
rebuild_W = inv_t - inv_{t-W} (W = 4 週)
z_score = (rebuild_W - μ) / σ (μ, σ 為 3 年滾動)
- z-score > 1.5:回補速度「異常快」
- z-score > 2.0:回補速度「極端快」
- z-score < -1.5:去庫存速度「異常快」
</essential_principles>
<quick_start>
全自動執行(無需手動操作 Chrome)
Step 1:安裝依賴
pip install requests websocket-client pandas numpy yfinance matplotlib
Step 2:一鍵抓取所有數據(SHFE + COMEX 庫存 + 銅價)
cd skills/analyze-copper-inventory-rebuild-signal/scripts
python fetch_copper_data.py
腳本會自動:
- 啟動 Chrome 調試模式
- 依序抓取 SHFE 和 COMEX 庫存(~80 秒)
- 抓取銅期貨價格(Yahoo Finance)
- 儲存到
cache/shfe_inventory.csv、cache/comex_inventory.csv、cache/copper_price.csv - 關閉 Chrome
Step 3:執行庫存訊號分析
python inventory_signal_analyzer.py
Step 4:生成視覺化圖表
python visualize_inventory_signal.py
輸出:{專案根目錄}/output/copper_inventory_signal_YYYY-MM-DD.png
</quick_start>
- 快速檢查 - 查看當前 SHFE 庫存回補訊號狀態
- 完整分析 - 執行回補訊號與價格高點的歷史驗證
- 長期分位數 - 銅價歷史分位數判讀(10 年)
- 視覺化 - 生成 Bloomberg 風格分析圖表
請選擇或直接提供分析參數。
路由後,執行對應命令。
<directory_structure>
analyze-copper-inventory-rebuild-signal/
├── SKILL.md # 本文件(路由器)
├── manifest.json # 技能元資料
├── skill.yaml # 前端展示元數據
├── scripts/
│ ├── fetch_copper_data.py # 全自動 CDP 數據爬蟲(SHFE + COMEX + 價格)
│ ├── fetch_shfe_inventory.py # SHFE 專用爬蟲(向下相容)
│ ├── inventory_signal_analyzer.py # 核心分析邏輯
│ └── visualize_inventory_signal.py # Bloomberg 風格視覺化
├── references/
│ ├── data-sources.md # 數據來源說明
│ ├── methodology.md # 方法論說明
│ └── historical-episodes.md # 歷史事件對照
├── templates/
│ ├── output-json.md # JSON 輸出格式
│ └── output-markdown.md # Markdown 輸出格式
├── workflows/
│ ├── quick-check.md # 快速檢查流程
│ ├── full-analysis.md # 完整分析流程
│ └── visualize.md # 視覺化流程
├── cache/
│ ├── shfe_inventory.csv # SHFE 庫存快取
│ ├── comex_inventory.csv # COMEX 庫存快取
│ └── copper_price.csv # 銅價快取
└── examples/
└── sample_output.json # 範例輸出
# 視覺化輸出位置(專案根目錄)
{專案根目錄}/output/
└── copper_inventory_signal_YYYY-MM-DD.png # 輸出圖表(含日期)
</directory_structure>
<scripts_index>
| Script | Command | Purpose |
|---|---|---|
| fetch_copper_data.py | python fetch_copper_data.py |
全自動抓取所有數據(SHFE + COMEX + 價格) |
| fetch_copper_data.py | --force-refresh |
強制重新抓取(忽略快取) |
| fetch_copper_data.py | --source shfe |
只抓取 SHFE 庫存 |
| fetch_copper_data.py | --source comex |
只抓取 COMEX 庫存 |
| fetch_copper_data.py | --source price |
只抓取銅價 |
| inventory_signal_analyzer.py | --quick |
快速檢查當前訊號狀態 |
| inventory_signal_analyzer.py | --full |
完整歷史驗證分析 |
| inventory_signal_analyzer.py | --long-term |
長期價格分位數分析 |
| visualize_inventory_signal.py | 無參數 | 生成 Bloomberg 風格圖表(輸出到專案根目錄 output/) |
| visualize_inventory_signal.py | -o path.png |
指定輸出路徑 |
| </scripts_index> |
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 2.8 KB
- manifest.json 2.3 KB
- references/data-sources.md 6.3 KB
- references/historical-episodes.md 5.7 KB
- references/methodology.md 11 KB
- scripts/fetch_copper_data.py 24 KB runs code
- scripts/fetch_shfe_inventory.py 15 KB runs code
- scripts/inventory_signal_analyzer.py 21 KB runs code
- scripts/visualize_inventory_signal.py 14 KB runs code
- skill.yaml 20 KB
- templates/output-json.md 4.5 KB
- templates/output-markdown.md 4.6 KB
- workflows/full-analysis.md 2.2 KB
- workflows/quick-check.md 1.7 KB
- workflows/visualize.md 1.8 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 · 327 lines · 63 tokens per session scan A 406da9770804
analyze-copper-inventory-rebuild-signal 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 3,821 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.