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 demographic-fiscal-trap-analyzergit 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/demographic-fiscal-trap-analyzer)<a href="https://agentmods.dev/skills/fatfingererr/macro-skills/demographic-fiscal-trap-analyzer"><img src="https://agentmods.dev/badge/skills/fatfingererr/macro-skills/demographic-fiscal-trap-analyzer/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/demographic-fiscal-trap-analyzer"><img src="https://agentmods.dev/badge/skills/fatfingererr/macro-skills/demographic-fiscal-trap-analyzer.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 | $0.00082 | $0.03835 |
| Opus 5 | $0.00041 | $0.01917 |
| Sonnet 5 | $0.00016 | $0.00767 |
| Haiku 4.5 | $0.00008 | $0.00383 |
Grade A, and why
demographic-fiscal-trap-analyzer 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>
「人口-財政陷阱」(Demographic-Fiscal Trap) 是指：當高齡化撫養比持續攀升、政府債務/GDP 居高不下、官僚體系低效膨脹、且名義成長無法覆蓋利息支出時，政府傾向透過「金融抑制」(financial repression) 或「通膨稀釋」(inflation erosion) 來削減實質負債。
此陷阱的核心特徵：
- 人口結構剛性：老年撫養比上升是不可逆的長期趨勢
- 債務自我強化：r > g 時債務比率自動膨脹
- 政治阻力：削減福利支出的政治成本極高
- 貨幣出口：當財政改革無路可走，貨幣稀釋成為「最小阻力路徑」
本技能採用四維度評分框架：
| 支柱 | 權重(預設) | 核心指標 |
|---|---|---|
| 老化壓力 (Aging Pressure) | 35% | 老年撫養比水準 + 10年斜率 |
| 債務動態 (Debt Dynamics) | 35% | 債務/GDP + 5年斜率 + (r-g) |
| 官僚膨脹 (Bloat Index) | 15% | 政府消費/GDP + 政府支出/GDP |
| 成長拖累 (Growth Drag) | 15% | 名義GDP成長率（負向計分） |
最終 fiscal_trap_score = Σ(權重 × z-score) 加權總和
通膨激勵指數 (Inflation Incentive Score) 衡量政府選擇「通膨稀釋」路徑的動機強度：
inflation_incentive =
0.40 × zscore(debt_level) # 高債務 → 強動機
+ 0.20 × zscore(r - g) # r > g → 難以自然去槓桿
+ 0.20 × zscore(neg_real_rate_share) # 負實質利率持續 → 已在執行
+ 0.20 × zscore(bloat_index) # 高官僚膨脹 → 難以削減支出
當此指數 > 1.5 時，表示該經濟體有強烈動機維持負實質利率環境。
本技能採用公開可重現的資料源：
| 資料類型 | 首選來源 | 次選來源 | API/下載方式 |
|---|---|---|---|
| 撫養比 | World Bank WDI | UN WPP | API / CSV |
| 政府債務 | IMF WEO | World Bank | API / CSV |
| 政府支出 | IMF GFS | World Bank | API / CSV |
| 健康支出 | WHO GHED | World Bank | API / CSV |
| 名義GDP成長 | World Bank | IMF WEO | API |
| CPI通膨 | World Bank | IMF | API |
| 10年公債殖利率 | OECD / 各國央行 | Trading Economics | API / 爬蟲 |
所有指標均可透過 wbdata、imfpy 或直接 API 取得。
為使跨國比較有意義，所有原始指標均轉換為 z-score：
zscore(x) = (x - μ_cross_section) / σ_cross_section
其中 μ 和 σ 為同期跨國截面統計量。
這使得：
- z > 1.5 → 顯著高於平均（警戒）
- z > 2.0 → 極端值（紅燈）
- z < -1.0 → 顯著優於平均
根據 Aging Pressure 和 Debt Dynamics 兩主軸，將經濟體分為四象限：
| 象限 | 老化壓力 | 債務動態 | 典型國家 | 政策空間 |
|---|---|---|---|---|
| Q1: 雙高危機 | 高 (>1) | 高 (>1) | 日本、義大利、希臘 | 極窄 |
| Q2: 老化主導 | 高 (>1) | 低 (<1) | 德國、南韓 | 中等（債務可用） |
| Q3: 債務主導 | 低 (<1) | 高 (>1) | 美國、巴西 | 中等（人口紅利） |
| Q4: 相對健康 | 低 (<1) | 低 (<1) | 印度、印尼 | 寬廣 |
Q1 象限國家最可能進入「財政陷阱」並選擇通膨稀釋路徑。
</essential_principles>
- 量化財政脆弱度：計算各國/地區的
fiscal_trap_score與inflation_incentive_score - 識別結構風險：透過四支柱分解，診斷哪個維度貢獻最大風險
- 象限定位：將經濟體歸類至四象限，判斷其政策空間
- 趨勢預警：利用撫養比預測至 2050 年，前瞻性評估陷阱演化
- 跨國比較：支援多國並排比較，識別相對風險排序
<quick_start>
快速開始
單一國家分析
請分析日本的人口財政陷阱風險，使用 2010-2023 年資料，預測至 2050 年
多國比較
比較 G7 國家的財政陷阱分數，並按通膨激勵指數排序
自訂權重
分析台灣的財政陷阱，使用自訂權重：老化 40%、債務 40%、膨脹 10%、成長 10%
</quick_start>
What ships with it
18 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/g7-comparison-2023.json 7.6 KB
- examples/japan-full-analysis.json 8.0 KB
- manifest.json 3.4 KB
- references/data-sources.md 7.4 KB
- references/indicator-codes.md 5.7 KB
- references/input-schema.md 5.4 KB
- references/methodology.md 6.5 KB
- scripts/fiscal_trap_analyzer.py 21 KB runs code
- scripts/README.md 6.2 KB
- scripts/visualize_combined.py 17 KB runs code
- skill.yaml 15 KB
- templates/output-json.md 10 KB
- templates/output-markdown.md 7.5 KB
- workflows/aging-projection.md 4.2 KB
- workflows/cross-country.md 5.4 KB
- workflows/debt-dynamics.md 3.2 KB
- workflows/full-analysis.md 3.6 KB
- workflows/inflation-path.md 6.0 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 · 82 tokens per session scan A 54205170f08d
demographic-fiscal-trap-analyzer is a skill published in the GitHub repository fatfingererr/macro-skills (3 stars, last pushed 7mo ago), licensed MIT. It adds 82 tokens to every session and 3,835 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.