Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/fatfingererr/macro-skillsnpx agentmods add skills/fatfingererr/macro-skills/analyze-us-bank-credit-deposit-decouplingWrote 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-us-bank-credit-deposit-decoupling)<a href="https://agentmods.dev/skills/fatfingererr/macro-skills/analyze-us-bank-credit-deposit-decoupling"><img src="https://agentmods.dev/badge/skills/fatfingererr/macro-skills/analyze-us-bank-credit-deposit-decoupling/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-us-bank-credit-deposit-decoupling"><img src="https://agentmods.dev/badge/skills/fatfingererr/macro-skills/analyze-us-bank-credit-deposit-decoupling.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 | $0.00076 | $0.02836 |
| Opus 5 | $0.00038 | $0.01418 |
| Sonnet 5 | $0.00015 | $0.00567 |
| Haiku 4.5 | $0.00008 | $0.00284 |
Grade A, and why
analyze-us-bank-credit-deposit-decoupling 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 — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<essential_principles>
傳統銀行體系下，貸款創造存款：
- 銀行發放貸款 → 借款人帳戶增加存款
- 理論上：新增貸款 ≈ 新增存款
當這個關係「脫鉤」時：
- 貸款持續擴張，但存款沒有等比例增加
- 代表有「力量」在抽走體系內的存款
- QT 環境下，資金流向貨幣市場基金、國債等
2022-2023 年 QT 週期的關鍵特徵：
-
存款絕對收縮期（2022 Q2 - 2023 Q1）
- 存款累積變化一度下探至 -1.2 兆美元
- 代表存款總量比基期（2022年6月）還少 1.2 兆
-
存款回升期（2023 Q2 至今）
- 存款逐步回升，但仍遠落後貸款增量
- 當前存款累積變化約 +0.5 兆美元
-
持續脫鉤
- 貸款累積增加約 +2.1 兆美元
- 落差（Gap）約 1.6 兆美元
| 指標 | 定義 | 意義 |
|---|---|---|
| 貸款累積變化 | loans(t) - loans(t0) | 銀行資產端擴張 |
| 存款累積變化 | deposits(t) - deposits(t0) | 銀行負債端變化 |
| Decoupling Gap | 貸款累積變化 - 存款累積變化 | 脫鉤程度 |
| 存款最大回撤 | min(存款累積變化) | 存款收縮最嚴重的程度 |
| 存款回撤恢復比率 | (當前存款變化 - 最低點) / | 最低點 |
| Deposit Stress Ratio | Gap / 貸款累積變化 | 每單位新增貸款的存款缺口比 |
| 指標 | FRED Series ID | 說明 | 公開 URL |
|---|---|---|---|
| 銀行貸款總量 | TOTLL | Loans and Leases in Bank Credit, All Commercial Banks | https://fred.stlouisfed.org/graph/fredgraph.csv?id=TOTLL |
| 銀行存款總量 | DPSACBW027SBOG | Deposits, All Commercial Banks | https://fred.stlouisfed.org/graph/fredgraph.csv?id=DPSACBW027SBOG |
資料頻率：Weekly（週頻） 對齊方式：以最新共同日期為準
</essential_principles>
輸出三層訊號：
- Cumulative Changes: 貸款與存款的累積變化量
- Deposit Dynamics: 存款的最大回撤、回升程度、當前狀態
- Decoupling Assessment: 脫鉤程度評估與宏觀解讀
<quick_start>
最快的方式：使用 FRED 公開 CSV（無需 API Key）
Step 1：安裝依賴
pip install pandas numpy requests matplotlib
Step 2：執行快速分析
cd scripts
python decoupling_analyzer.py --quick
Step 3：執行完整分析（含視覺化）
python decoupling_analyzer.py \
--start 2022-06-01 \
--output ../../output/decoupling_$(date +%Y-%m-%d).json
Step 4：生成視覺化圖表（Bloomberg 風格面積圖）
python visualize_decoupling.py \
--start 2022-06-01 \
--output ../../output/credit_deposit_decoupling_$(date +%Y-%m-%d).png
輸出範例：
{
"period": "2022-06 to 2026-01",
"cumulative_changes": {
"loans_billion_usd": 2070.5,
"deposits_billion_usd": 506.8,
"gap_billion_usd": 1563.7
},
"deposit_dynamics": {
"max_drawdown_billion_usd": -1200.0,
"max_drawdown_date": "2023-04-12",
"recovery_from_trough_billion_usd": 1706.8,
"recovery_ratio": 1.42
},
"assessment": {
"decoupling_status": "severe",
"deposit_stress_ratio": 0.755,
"phase": "recovery_but_lagging"
}
}
</quick_start>
- 快速檢查 - 查看最新的信貸-存款脫鉤狀態
- 完整分析 - 執行完整分析並生成視覺化圖表
- 方法論學習 - 了解信貸創造脫鉤的會計邏輯與宏觀意義
請選擇或直接提供分析參數。
路由後，執行對應腳本並生成視覺化圖表。
視覺化輸出：信貸-存款脫鉤面積圖
採用 Bloomberg Intelligence 風格，參考 FRED 原生圖表設計：
圖表特徵：
- 面積圖（Area Chart）：清楚顯示累積變化的體量
- 藍色面積：貸款累積變化（Loans & Leases）
- 紅色面積：存款累積變化（Deposits）
- 0 軸線：清楚標示基準線
- 數值標註：最新數值標示在圖表右側
What ships with it
12 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 1.9 KB
- manifest.json 1.9 KB
- references/data-sources.md 6.5 KB
- references/historical-episodes.md 4.5 KB
- references/methodology.md 5.2 KB
- scripts/decoupling_analyzer.py 22 KB runs code
- scripts/visualize_decoupling.py 13 KB runs code
- skill.yaml 28 KB
- templates/output-json.md 5.3 KB
- templates/output-markdown.md 4.1 KB
- workflows/analyze.md 3.8 KB
- workflows/quick-check.md 1.0 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 · 267 lines · 76 tokens per session scan A c1f1db4252ed
analyze-us-bank-credit-deposit-decoupling is a skill published in the GitHub repository fatfingererr/macro-skills (3 stars, last pushed 7mo ago), licensed MIT. It adds 76 tokens to every session and 2,836 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.