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 us-cpi-pce-comparatorgit 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/us-cpi-pce-comparator)<a href="https://agentmods.dev/skills/fatfingererr/macro-skills/us-cpi-pce-comparator"><img src="https://agentmods.dev/badge/skills/fatfingererr/macro-skills/us-cpi-pce-comparator/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/us-cpi-pce-comparator"><img src="https://agentmods.dev/badge/skills/fatfingererr/macro-skills/us-cpi-pce-comparator.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 | $0.00078 | $0.02246 |
| Opus 5 | $0.00039 | $0.01123 |
| Sonnet 5 | $0.00016 | $0.00449 |
| Haiku 4.5 | $0.00008 | $0.00225 |
Grade A, and why
us-cpi-pce-comparator 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 11d 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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<essential_principles>
- CPI(固定權重): BLS Relative Importance,每年或每兩年更新,反映「固定籃子」
- PCE(動態/鏈結權重): BEA 名目支出占比,每月隨實際消費行為調整
關鍵洞見:當消費者把錢花在「價格較不波動」的品項時,若這些品項的通膨走高,PCE 會比 CPI 更敏感地反映這個上行壓力。
識別邏輯:
- 找出 PCE 權重較高的消費桶(consumer spending buckets)
- 在這些桶中,篩選價格波動度較低者
- 若這些桶的通膨近期轉正或加速,標記為 PCE upside risk
PCE 涵蓋項目比 CPI 更廣:
- 第三方支付的醫療費用(employer-paid healthcare)
- 非營利機構對家庭的服務
- 某些金融服務的隱含費用
這些 scope 差異也會造成 CPI/PCE 分歧。詳見 references/cpi-pce-methodology.md。
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} - BLS Public API:
https://api.bls.gov/publicAPI/v2/timeseries/data/
腳本位於 scripts/ 目錄,可直接執行。
</essential_principles>
輸出三層訊號:
- Headline level: CPI vs PCE divergence(bps)
- Attribution: 哪些 buckets 在推升 PCE(weighted contribution)
- Risk framing: 觀察點與延續性風險評估
<quick_start>
最快的方式:執行快速檢查
cd skills/us-cpi-pce-comparator
pip install pandas numpy requests # 首次使用
python scripts/cpi_pce_analyzer.py --quick
輸出範例:
{
"headline": {"cpi_yoy": 2.65, "pce_yoy": 2.79, "gap_bps": 14},
"core": {"cpi_core_yoy": 2.65, "pce_core_yoy": 2.83, "gap_bps": 18},
"momentum": {"cpi_3m_saar": 2.07, "pce_3m_saar": 2.82}
}
完整分析:
python scripts/cpi_pce_analyzer.py --start 2020-01-01 --measure yoy
</quick_start>
- 快速檢查 - 查看最新的 CPI/PCE 分歧數據
- 完整分析 - 執行完整的三步驟分析工作流
- 方法論學習 - 了解 CPI/PCE 差異的深層原因
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>
us-cpi-pce-comparator/
├── SKILL.md # 本文件(路由器)
├── skill.yaml # 前端展示元數據
├── workflows/
│ ├── analyze.md # 完整分析工作流
│ └── quick-check.md # 快速檢查工作流
├── references/
│ ├── data-sources.md # FRED/BLS 系列代碼與資料來源
│ ├── cpi-pce-methodology.md # CPI/PCE 方法論深度解析
│ └── implementation.md # 計算公式與程式碼範例
├── templates/
│ ├── output-json.md # JSON 輸出模板
│ └── output-markdown.md # Markdown 報告模板
└── scripts/
├── fetch_fred_data.py # FRED 資料抓取(無需 API key)
├── fetch_bls_data.py # BLS 資料抓取
└── cpi_pce_analyzer.py # 主分析腳本
</directory_structure>
<reference_index>
方法論: references/cpi-pce-methodology.md
- CPI vs PCE 的五大差異(權重、範圍、公式、住房、人口)
- 分歧模式與交易含義
- Fed 如何解讀兩指標
資料來源: references/data-sources.md
- FRED CSV endpoint(無需 API key)
- FRED 系列代碼對照表
- 桶位定義與近似計算
實作指南: references/implementation.md
- 通膨計算公式(YoY, MoM SAAR, QoQ SAAR)
- 權重效應計算
- 波動度分析
</reference_index>
<workflows_index>
| Workflow | Purpose | 使用時機 |
|---|---|---|
| analyze.md | 完整三步驟分析 | 需要深度分析時 |
| quick-check.md | 快速檢查分歧 | 日常監控或快速回答 |
| </workflows_index> |
<templates_index>
| Template | Purpose |
|---|---|
| output-json.md | JSON 輸出結構定義 |
| output-markdown.md | Markdown 報告模板 |
| </templates_index> |
<scripts_index>
| Script | Command | Purpose |
|---|---|---|
| cpi_pce_analyzer.py | --quick |
快速檢查最新分歧 |
| cpi_pce_analyzer.py | --start DATE --measure yoy |
完整分析 |
| fetch_fred_data.py | --series CPIAUCSL,PCEPI |
抓取 FRED 資料 |
| fetch_bls_data.py | --full |
抓取 BLS CPI 資料 |
| </scripts_index> |
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.
- manifest.json 1.8 KB
- references/cpi-pce-methodology.md 5.9 KB
- references/data-sources.md 6.2 KB
- references/implementation.md 13 KB
- scripts/cpi_pce_analyzer.py 21 KB runs code
- scripts/fetch_bls_data.py 11 KB runs code
- scripts/fetch_fred_data.py 10 KB runs code
- skill.yaml 5.3 KB
- templates/output-json.md 4.4 KB
- templates/output-markdown.md 5.0 KB
- workflows/analyze.md 4.3 KB
- workflows/quick-check.md 2.7 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.
- 11d ago First seen · 219 lines · 78 tokens per session scan A a93c5a291690
us-cpi-pce-comparator is a skill published in the GitHub repository fatfingererr/macro-skills (3 stars, last pushed 7mo ago), licensed MIT. It adds 78 tokens to every session and 2,246 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.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
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.