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-japan-debt-service-tax-burdenWrote 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-japan-debt-service-tax-burden)<a href="https://agentmods.dev/skills/fatfingererr/macro-skills/analyze-japan-debt-service-tax-burden"><img src="https://agentmods.dev/badge/skills/fatfingererr/macro-skills/analyze-japan-debt-service-tax-burden/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-japan-debt-service-tax-burden"><img src="https://agentmods.dev/badge/skills/fatfingererr/macro-skills/analyze-japan-debt-service-tax-burden.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 | $0.00074 | $0.04544 |
| Opus 5 | $0.00037 | $0.02272 |
| Sonnet 5 | $0.00015 | $0.00909 |
| Haiku 4.5 | $0.00007 | $0.00454 |
Grade A, and why
analyze-japan-debt-service-tax-burden 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 — 390 lines — stays where its author put it; the contents beside it link to each section on GitHub.
分析日本債務利息負擔 Skill
以公開數據量化日本「利息吃掉稅收」的敘事,提供可驗證的現況核對、敏感度分析與風險分級。
<essential_principles>
interest_tax_ratio = interest_payments / tax_revenue
這是影片敘事「利息吃掉 1/3 稅收」的可核驗版本。不同口徑(國稅 vs 一般會計稅收 vs 總收入)會產生不同數值,必須明示口徑選擇。
口徑對照(FY2025):
| 口徑 | 計算 | 比例 |
|---|---|---|
| 純利息/稅收 | 10.5兆/70兆 | 15.0% |
| 國債費/稅收 | 28.2兆/70兆 | 40.3% |
注意:媒體敘事「利息吃掉 1/3」通常誤用國債費(含本金)口徑。
implied_avg_rate = interest_payments / debt_stock
衡量存量債務的平均融資成本。對比當前市場利率可評估再融資壓力。
FY2025:10.5兆 / 1,324兆 = 0.79% vs 當前 10Y 殖利率 2.0%+ → 差距反映大量存量債務在低利率時期發行,未來再融資將推高利息負擔。
媒體常用「美國等效規模」表達日本債務以增強震撼效果。
公式(動態計算):
debt_to_gdp = japan_debt_stock / japan_gdp
debt_in_us_terms = us_gdp × debt_to_gdp
數據來源:GDP 從 FRED 實時抓取,非硬編碼。
範例:$30.6T × 250% = $76.5T ≈ $70T(媒體口語化)
用途:解釋影片/新聞中「$70T」數字的來源,用於跨國比較時統一規模感知。
把殖利率變動映射到利息支出增加:
additional_interest ≈ debt_stock × pass_through × delta_yield
其中 pass_through 是年度再定價/再融資比例(約 15%),delta_yield 以小數表示(200bp = 0.02)。
| 區間 | interest_tax_ratio | 含義 |
|---|---|---|
| 🟢 綠 | < 0.25 | 財政彈性充足 |
| 🟡 黃 | 0.25–0.40 | 財政彈性開始下降 |
| 🟠 橘 | 0.40–0.55 | 政策空間明顯受限 |
| 🔴 紅 | > 0.55 | 接近「2/3」敘事區域 |
所有輸出必須標示:
- 稅收口徑(national_tax / general_account_tax / total_revenue)
- 利息口徑(interest_only / debt_service)
- 資料年度與滯後(lag)
- 再定價假設(pass_through)
</essential_principles>
<quick_start>
最快的方式:執行快速檢查
cd skills/analyze-japan-debt-service-tax-burden
pip install pandas numpy requests matplotlib # 首次使用
python scripts/japan_debt_analyzer.py --quick
輸出範例:
{
"yield_stats": {"tenor": "10Y", "latest": 1.23, "percentile": 0.97},
"fiscal": {"interest_tax_ratio": 0.15, "risk_band": "green"},
"headline": "利息支出佔稅收 15.0%,處於🟢 GREEN 區",
"data_sources": {"jgb_10y": "FRED/IRLTLT01JPM156N", "fiscal": "config/FY2025"}
}
完整分析(含實時數據刷新):
python scripts/japan_debt_analyzer.py --full --refresh
生成視覺化 Dashboard:
python scripts/generate_charts.py --full --output-dir ../../output
輸出:output/japan_debt_dashboard_YYYYMMDD.png
Dashboard 包含:
- Interest/Tax Ratio 風險儀表盤
- 殖利率分位數指標
- 財政數據摘要
- 壓力測試情境比較圖
生成債務螺旋模擬圖表:
# 完整多情境螺旋模擬
python scripts/generate_spiral_chart.py --all --output-dir ../../output
# 單一壓力情境(如 +200bp)
python scripts/generate_spiral_chart.py --stress 200 --output-dir ../../output
# 自定義模擬年數
python scripts/generate_spiral_chart.py --years 15 --output-dir ../../output
輸出:output/japan_debt_spiral_YYYY-MM-DD.png
螺旋模擬包含:
- 多情境 Interest/Tax Ratio 10年演變曲線
- 風險區間背景(綠/黃/橙/紅)
- 利息支出分解堆疊圖
- 各情境最終風險評估
生成歷史趨勢分析圖表(NEW!):
# 完整歷史趨勢分析(2015-2025)
python scripts/generate_historical_trend.py --output-dir ../../output
# 自定義時間範圍
python scripts/generate_historical_trend.py --start-year 2018 --end-year 2025
輸出:output/japan_debt_trend_YYYYMMDD.png
歷史趨勢分析包含:
- Interest/Tax Ratio 11年完整走勢(2015-2025)
- 稅收、利息支出、債務存量趨勢
- 隱含平均利率演變
- 風險分級分布統計
- 階段性特徵分析(下降期/疫情期/反彈期)
單獨測試數據抓取:
python scripts/fetch_jgb_yields.py --tenor 10Y
python scripts/fetch_tic_holdings.py
</quick_start>
- 快速檢查 - 查看最新的利息/稅收比與殖利率狀態
- 完整分析 - 執行完整的財政壓力測試與風險評估
- 情境壓測 - 自定義利率衝擊情境進行壓力測試
- 生成圖表 - 生成視覺化 Dashboard(PNG 圖檔)
- 債務螺旋模擬 - 模擬多年累積效應,生成螺旋演變圖表
- 歷史趨勢分析 - 分析 2015-2025 年完整歷史趨勢(NEW!)
- 方法論學習 - 了解指標計算與風險分級邏輯
請選擇或直接提供分析參數。
What ships with it
22 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.
- config/fiscal_data.json 4.2 KB
- examples/sample-output.json 3.0 KB
- manifest.json 2.4 KB
- references/data-sources.md 5.7 KB
- references/japan-fiscal-structure.md 2.9 KB
- references/methodology.md 5.2 KB
- scripts/data_manager.py 11 KB runs code
- scripts/fetch_jgb_yields.py 11 KB runs code
- scripts/fetch_tic_holdings.py 9.5 KB runs code
- scripts/generate_charts.py 15 KB runs code
- scripts/generate_historical_trend.py 12 KB runs code
- scripts/generate_spiral_chart.py 21 KB runs code
- scripts/japan_debt_analyzer.py 20 KB runs code
- skill.yaml 26 KB
- templates/output-json.md 4.1 KB
- templates/output-markdown.md 3.6 KB
- workflows/full-analysis.md 2.3 KB
- workflows/generate-chart.md 3.2 KB
- workflows/historical-trend.md 6.6 KB
- workflows/quick-check.md 968 B
- workflows/spiral-simulate.md 2.9 KB
- workflows/stress-test.md 2.3 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 · 390 lines · 74 tokens per session scan A 682f1567929a
analyze-japan-debt-service-tax-burden is a skill published in the GitHub repository fatfingererr/macro-skills (3 stars, last pushed 7mo ago), licensed MIT. It adds 74 tokens to every session and 4,544 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.