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-platinum-to-brazil-equities-transmissiongit 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-platinum-to-brazil-equities-transmission)<a href="https://agentmods.dev/skills/fatfingererr/macro-skills/analyze-platinum-to-brazil-equities-transmission"><img src="https://agentmods.dev/badge/skills/fatfingererr/macro-skills/analyze-platinum-to-brazil-equities-transmission/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-platinum-to-brazil-equities-transmission"><img src="https://agentmods.dev/badge/skills/fatfingererr/macro-skills/analyze-platinum-to-brazil-equities-transmission.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 | $0.00070 | $0.03201 |
| Opus 5 | $0.00035 | $0.01600 |
| Sonnet 5 | $0.00014 | $0.00640 |
| Haiku 4.5 | $0.00007 | $0.00320 |
Grade A, and why
analyze-platinum-to-brazil-equities-transmission 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 — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<essential_principles>
本技能專注於「用數據驗證敘事」:
- 輸入:社群/新聞宣稱「白金走勢可能領先或驅動巴西股市」
- 輸出:長週期時間序列上的傳導假說檢驗結果
不做價格預測,只回答:「白金→巴西股市的傳導結構在數據上是否存在?」
使用 Cross-Correlation 掃描 [-lead_lag_max, +lead_lag_max] 範圍:
corr(r_ewz, r_platinum.shift(lag))- lag > 0:白金領先 EWZ(platinum leads)
- lag < 0:EWZ 領先白金
- lag ≈ 0:同步移動
典型設定:週頻 lag max = 52(一年),找 |corr| 最大的 lag。
白金與巴西股市的關聯具有週期性特徵:
- linked_upcycle:兩者趨勢同向上行,傳導結構穩固
- decoupled:關聯斷裂,各走各的
- brazil_idiosyncratic:巴西特有風險(政治/匯率/商品結構)主導
長期 regime 判斷使用 regime_window(預設 104 週 ≈ 2 年)內的趨勢一致性。
綜合三個維度量化傳導可信度:
| 維度 | 權重 | 說明 |
|---|---|---|
| best_lead_lag_corr | 30% | 最佳領先落後相關係數 |
| rolling_corr_stability | 30% | rolling corr > 0 的佔比與連續性 |
| trend_agreement | 40% | 長期趨勢一致程度 |
分數解讀:≥70 強傳導、50-69 中等、<50 弱/不穩定。
主要使用 Yahoo Finance(免費、無需 API key):
- 白金期貨:
PL=F - 巴西股市 ETF:
EWZ
頻率建議:1wk(週頻)用於長週期分析,避免日頻噪音干擾。 對齊方式:inner join(只保留共同交易日),避免補值造成假相關。
</essential_principles>
- 數據取得:從 Yahoo Finance 取得白金期貨與 EWZ 歷史價格
- 雙軸圖與正規化圖:Bloomberg 風格原值雙軸圖 + 正規化同軸對比
- 領先落後分析:交叉相關找出白金是否領先 EWZ 及滯後期數
- Rolling Correlation:滾動相關觀察關聯的時變結構
- Regime 判斷:長期趨勢一致性判斷當前處於哪種傳導體制
- 傳導強度分數:綜合評分(0-100)量化傳導可信度
輸出:傳導強度分數、領先落後判定、regime label、監控清單、Bloomberg 風格圖表。
<quick_start>
Step 1:安裝依賴
pip install yfinance pandas numpy matplotlib scipy
Step 2:執行完整分析
cd scripts
python analyze.py --start 2003-01-01
Step 3:生成 Bloomberg 風格視覺化圖表
python visualize.py --start 2003-01-01
# 輸出到: output/platinum_vs_ewz_YYYY-MM-DD.png
輸出範例:
{
"signal": "transmission_moderate",
"confidence": "medium",
"transmission_strength_score": 74,
"best_lead_lag": {
"lag_weeks": 12,
"meaning": "Platinum leads EWZ by ~12 weeks",
"corr": 0.52
},
"rolling_corr": {
"window": 52,
"latest": 0.41,
"positive_share_5y": 0.68
},
"regime_label": "linked_upcycle",
"monitoring_notes": [
"若 PL=F 突破長期區間,觀察 EWZ 在 8-16 週內是否趨勢翻多",
"要求 52 週 rolling corr 維持正值至少 26 週作為確認",
"若白金大漲而 EWZ 不動且 corr 轉負,視為 regime break"
]
}
</quick_start>
- 快速檢查 - 查看白金與巴西股市目前的傳導狀態
- 完整分析 - 執行完整傳導檢驗並生成報告
- 視覺化圖表 - 生成 Bloomberg 風格雙軸圖與相關分析圖表
- 方法論學習 - 了解傳導分析、交叉相關與 regime 判斷的原理
請選擇或直接提供分析參數。
路由後,閱讀對應文件並執行。
<directory_structure>
analyze-platinum-to-brazil-equities-transmission/
├── SKILL.md # 本文件(路由器)
├── skill.yaml # 前端展示元數據
├── manifest.json # 技能元資料
├── workflows/
│ ├── analyze.md # 完整傳導分析工作流
│ └── visualize.md # 視覺化工作流
├── references/
│ ├── data-sources.md # 資料來源與替代方案
│ ├── methodology.md # 傳導分析方法論
│ └── input-schema.md # 完整輸入參數定義
├── templates/
│ ├── output-json.md # JSON 輸出模板
│ └── output-markdown.md # Markdown 報告模板
├── scripts/
│ ├── analyze.py # 主分析腳本
│ ├── fetch_data.py # 數據抓取工具(Yahoo Finance)
│ └── visualize.py # Bloomberg 風格視覺化
└── examples/
└── sample_output.json # 範例輸出
</directory_structure>
What ships with it
13 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 2.1 KB
- manifest.json 1.8 KB
- references/data-sources.md 2.2 KB
- references/input-schema.md 1.9 KB
- references/methodology.md 5.1 KB
- scripts/analyze.py 18 KB runs code
- scripts/fetch_data.py 7.3 KB runs code
- scripts/visualize.py 11 KB runs code
- skill.yaml 17 KB
- templates/output-json.md 2.8 KB
- templates/output-markdown.md 2.5 KB
- workflows/analyze.md 4.6 KB
- workflows/visualize.md 3.4 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 · 322 lines · 70 tokens per session scan A a0bbe6c99f05
analyze-platinum-to-brazil-equities-transmission is a skill published in the GitHub repository fatfingererr/macro-skills (3 stars, last pushed 7mo ago), licensed MIT. It adds 70 tokens to every session and 3,201 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.