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-move-risk-gauges-leadlaggit 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-move-risk-gauges-leadlag)<a href="https://agentmods.dev/skills/fatfingererr/macro-skills/analyze-move-risk-gauges-leadlag"><img src="https://agentmods.dev/badge/skills/fatfingererr/macro-skills/analyze-move-risk-gauges-leadlag/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-move-risk-gauges-leadlag"><img src="https://agentmods.dev/badge/skills/fatfingererr/macro-skills/analyze-move-risk-gauges-leadlag.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 | $0.00068 | $0.05318 |
| Opus 5 | $0.00034 | $0.02659 |
| Sonnet 5 | $0.00014 | $0.01064 |
| Haiku 4.5 | $0.00007 | $0.00532 |
Grade A, and why
analyze-move-risk-gauges-leadlag scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://127.0.0.1:9222/json How it starts
The opening of the file, as written. The whole thing — 458 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<essential_principles>
MOVE Index(美林期權波動率指數)是衡量美國國債選擇權隱含波動率的指標:
- MOVE 低/下降:利率市場對未來波動預期降低,風險偏好上升
- MOVE 高/上升:利率市場恐慌,避險需求增加
MOVE 常被視為「債市的 VIX」,可作為其他風險指標的領先訊號。
使用 Cross-Correlation 判斷兩序列的領先/落後關係:
- 在 [-L, +L] 位移範圍內計算相關係數
- 最大相關出現在 lag > 0:X 領先 Y
- 最大相關出現在 lag < 0:X 落後 Y
- 最大相關出現在 lag ≈ 0:同步移動
典型設定:L = 20(交易日),配合平滑處理降低噪音。
檢驗「利率事件(如 JGB 殖利率跳升)發生時,MOVE 是否恐慌」:
- 定義衝擊事件:|ΔY[t-k:t]| ≥ threshold(如 15bp)
- 檢查事件窗內 MOVE 變化
- 若 MOVE 反應 < 歷史分布中位數 → "not spooked"
此邏輯可驗證「利率波動率對某事件不敏感」的敘事。
本 skill 使用 Chrome CDP 連接到 MacroMicro 抓取真實數據:
- MOVE Index: MacroMicro (CDP) - https://en.macromicro.me/charts/35584/us-treasury-move-index
- JGB 10Y: MacroMicro (CDP) - https://en.macromicro.me/charts/944/jp-10-year-goverment-bond-yield
- VIX: Yahoo Finance (yfinance)
- Credit (IG OAS): FRED (BAMLC0A0CM)
重要:MOVE 和 JGB 需要透過 Chrome CDP 爬蟲取得,請參照 <quick_start> 的步驟啟動 Chrome。
</essential_principles>
- 數據抓取:從公開來源取得 MOVE、VIX、信用利差、JGB 殖利率
- 標準化處理:Z 分數、平滑處理、頻率對齊
- 領先落後分析:交叉相關找出 MOVE vs VIX / 信用利差的 lead/lag
- 事件窗檢定:JGB 衝擊事件中 MOVE 是否「不恐慌」
- 方向一致性:MOVE 下行時,其他風險指標是否同步下行
輸出:領先落後判定、恐慌檢定結果、方向一致性比例、量化證據。
<quick_start>
執行分析前,必須先啟動 Chrome 調試模式
Step 1:關閉所有 Chrome 視窗
Step 2:用調試端口啟動 Chrome(Windows)
"C:\Program Files\Google\Chrome\Application\chrome.exe" ^
--remote-debugging-port=9222 ^
--remote-allow-origins=* ^
--user-data-dir="%USERPROFILE%\.chrome-debug-profile" ^
"https://en.macromicro.me/charts/35584/us-treasury-move-index"
Step 3:在瀏覽器中開啟第二個分頁,載入 JGB 頁面
https://en.macromicro.me/charts/944/jp-10-year-goverment-bond-yield
Step 4:等待兩個頁面的圖表都完全載入(約 30-40 秒)
Step 5:執行分析
cd .claude/skills/analyze-move-risk-gauges-leadlag/scripts
pip install pandas numpy yfinance requests websocket-client matplotlib # 首次使用
python analyze.py --start 2024-01-01 --end 2026-01-31 --output-mode markdown
Step 6(可選):生成 Bloomberg 風格視覺化圖表
# 方式一:分析時同時生成圖表
python analyze.py --start 2024-01-01 --end 2026-01-31 --output-mode markdown --chart
# 方式二:單獨生成圖表(自動使用快取數據)
python visualize.py --start 2024-01-01 --end 2026-01-31
圖表預設輸出路徑:{專案根目錄}/output/move-leadlag-YYYY-MM-DD.png
輸出範例:
## 結論
- 利率波動率(MOVE)對「JGB 殖利率衝擊」反應偏弱 / 未顯著升溫 → **not spooked**
- MOVE 的變化在統計上呈現 **領先 4-6 天** 的特徵
- MOVE 下行時,VIX / 信用利差同步走低的比例:VIX = 62%、Credit = 60%
</quick_start>
- 快速檢查 - 查看目前 MOVE 的領先落後狀態與恐慌程度
- 完整分析 - 執行完整的領先落後與事件窗分析
- 視覺化圖表 - 生成多面板分析結果圖表
- 方法論學習 - 了解 Lead/Lag 分析與事件窗檢定的邏輯
請選擇或直接提供分析參數。
重要:執行分析前必須確保 Chrome CDP 已啟動並載入 MOVE 和 JGB 頁面。
<directory_structure>
analyze-move-risk-gauges-leadlag/
├── SKILL.md # 本文件(路由器)
├── skill.yaml # 前端展示元數據
├── manifest.json # 技能元數據
├── cache/ # 數據快取目錄
├── workflows/
│ ├── analyze.md # 完整分析工作流
│ └── visualize.md # 視覺化工作流
├── references/
│ ├── data-sources.md # 資料來源與替代方案
│ ├── methodology.md # Lead/Lag 與事件窗方法論
│ └── 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 (CDP + FRED + Yahoo)
├── visualize.py # Lead/Lag 綜合圖表繪圖工具
└── visualize_rates_move.py # 利率 vs MOVE 恐慌專題圖表(可帶入任何國家債券)
</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.
- manifest.json 2.9 KB
- references/data-sources.md 7.3 KB
- references/input-schema.md 6.9 KB
- references/methodology.md 11 KB
- scripts/analyze.py 18 KB runs code
- scripts/fetch_data.py 19 KB runs code
- scripts/visualize_rates_move.py 24 KB runs code
- scripts/visualize.py 18 KB runs code
- skill.yaml 13 KB
- templates/output-json.md 8.0 KB
- templates/output-markdown.md 7.0 KB
- workflows/analyze.md 7.6 KB
- workflows/visualize.md 5.5 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 · 458 lines · 68 tokens per session scan A 1bde5b429faf
analyze-move-risk-gauges-leadlag is a skill published in the GitHub repository fatfingererr/macro-skills (3 stars, last pushed 7mo ago), licensed MIT. It adds 68 tokens to every session and 5,318 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.