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 zeberg-salomon-rotatorgit 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/zeberg-salomon-rotator)<a href="https://agentmods.dev/skills/fatfingererr/macro-skills/zeberg-salomon-rotator"><img src="https://agentmods.dev/badge/skills/fatfingererr/macro-skills/zeberg-salomon-rotator/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/zeberg-salomon-rotator"><img src="https://agentmods.dev/badge/skills/fatfingererr/macro-skills/zeberg-salomon-rotator.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 | $0.00077 | $0.02652 |
| Opus 5 | $0.00039 | $0.01326 |
| Sonnet 5 | $0.00015 | $0.00530 |
| Haiku 4.5 | $0.00008 | $0.00265 |
Grade A, and why
zeberg-salomon-rotator 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 — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<essential_principles>
Zeberg–Salomon 模型將市場簡化為兩種狀態:
- RISK_ON: 持有股票(SPY),景氣擴張期
- RISK_OFF: 持有長債(TLT),景氣收縮期
切換邏輯基於「領先指標先轉弱,同時指標後確認」的景氣循環規律。
| 類型 | 作用 | 典型成分 | 領先時間 |
|---|---|---|---|
| Leading | 預警 | 殖利率曲線、新訂單、房市許可 | 6-12 月 |
| Coincident | 確認 | 就業、工業生產、實質收入 | 同步 |
合成方式:
- 各序列做 transform(yoy/mom/diff)
- 統一方向(direction +1/-1)
- Rolling z-score 標準化
- EMA 平滑
- 加權合成
Iceberg Event: LeadingIndex < iceberg_threshold
→ 預警:景氣開始轉弱
→ 搭配「領先指標下降」+ 可選「市場亢奮」濾鏡
Sinking Event: CoincidentIndex < sinking_threshold
→ 確認:實體經濟收縮
→ 通常在 Iceberg 之後數月發生
狀態機邏輯:
- RISK_ON → RISK_OFF:Iceberg 連續確認 + 斜率為負
- RISK_OFF → RISK_ON:領先指標回升超過 (threshold + hysteresis)
本 skill 使用無需 API key 的資料來源:
- FRED CSV:
https://fred.stlouisfed.org/graph/fredgraph.csv?id={SERIES_ID} - Yahoo Finance:
yfinance套件抓取 SPY, TLT, VIX
腳本位於 scripts/ 目錄,可直接執行。
</essential_principles>
- 建構指標:從 FRED 數據合成 LeadingIndex 與 CoincidentIndex
- 偵測事件:識別「冰山」(領先轉弱)與「下沉」(同時確認)
- 切換訊號:產生 RISK_ON ↔ RISK_OFF 切換事件
- 回測績效:計算累積報酬、MaxDD、CAGR、與 benchmark 比較
輸出:切換事件清單、指標時間序列、回測摘要、診斷資訊。
<quick_start>
最快的方式:執行預設回測
cd skills/zeberg-salomon-rotator
pip install pandas numpy yfinance pandas-datareader # 首次使用
python scripts/rotator.py --quick
輸出範例:
{
"state": "RISK_ON",
"latest_indices": {"LeadingIndex": 0.41, "CoincidentIndex": 0.22},
"iceberg_event": false,
"sinking_event": false,
"last_switch": {"date": "2023-06-30", "action": "EXIT_LONG_BOND_ENTER_EQUITY"}
}
完整回測:
python scripts/rotator.py --start 2000-01-01 --end 2026-01-01 --output result.json
</quick_start>
- 快速檢查 - 查看目前的景氣狀態與最新指標
- 完整回測 - 執行完整的歷史回測與績效分析
- 視覺化圖表 - 生成多面板回測結果圖表
- 監控模式 - 設定持續監控與切換警報
- 方法論學習 - 了解 Zeberg-Salomon 模型的邏輯
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>
zeberg-salomon-rotator/
├── SKILL.md # 本文件(路由器)
├── skill.yaml # 前端展示元數據
├── manifest.json # 技能元數據
├── workflows/
│ ├── backtest.md # 完整回測工作流
│ ├── visualize.md # 視覺化工作流
│ ├── monitor.md # 持續監控工作流
│ └── analyze.md # 深度分析工作流
├── references/
│ ├── data-sources.md # FRED 系列代碼與資料來源
│ ├── methodology.md # Zeberg-Salomon 方法論解析
│ └── 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/
├── rotator.py # 主輪動腳本
├── visualize.py # 視覺化繪圖工具
└── fetch_data.py # 數據抓取工具
</directory_structure>
<reference_index>
方法論: references/methodology.md
- Zeberg-Salomon 模型概念
- 冰山/下沉事件定義
- 兩態切換邏輯
資料來源: references/data-sources.md
- FRED 系列代碼(領先/同時)
- Yahoo Finance 資產代碼
- 數據頻率與對齊
輸入參數: references/input-schema.md
- 完整參數定義
- 預設值與建議範圍
What ships with it
14 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.
- manifest.json 3.8 KB
- references/data-sources.md 5.0 KB
- references/input-schema.md 7.6 KB
- references/methodology.md 6.4 KB
- scripts/fetch_data.py 9.4 KB runs code
- scripts/rotator.py 24 KB runs code
- scripts/visualize.py 12 KB runs code
- skill.yaml 15 KB
- templates/output-json.md 7.6 KB
- templates/output-markdown.md 4.5 KB
- workflows/analyze.md 4.9 KB
- workflows/backtest.md 4.1 KB
- workflows/monitor.md 3.7 KB
- workflows/visualize.md 2.0 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 · 257 lines · 77 tokens per session scan A fc51d1699ceb
zeberg-salomon-rotator is a skill published in the GitHub repository fatfingererr/macro-skills (3 stars, last pushed 7mo ago), licensed MIT. It adds 77 tokens to every session and 2,652 once invoked, about $0.0004 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.