us-cpi-pce-comparator

<essential_principles>

CPI (fixed weights): BLS Relative Importance, updated annually or every two years, reflecting a "fixed basket"
PCE (dynamic/chained weights): BEA nominal expenditure shares, adjusted monthly with actual consumer behavior

Key insight: When consumers spend money on items whose "prices are less volatile," if inflation in these items rises, PCE will reflect this upward pressure more sensitively than CPI.

Identification logic:

Find consumer spending buckets with higher PCE weights
Within these buckets, screen for those with lower price volatility
If inflation in these buckets has recently turned positive or accelerated, flag as PCE upside risk

PCE covers a broader set of items than CPI:

Employer-paid healthcare
Services provided by nonprofit institutions to households
Implicit fees for certain financial services

These scope differences also cause CPI/PCE divergence. See references/cpi-pce-methodology.md。

This skill usesno API key required data sources:

FRED CSV: https://fred.stlouisfed.org/graph/fredgraph.csv?id={SERIES_ID}
BLS Public API: https://api.bls.gov/publicAPI/v2/timeseries/data/

The script is located in the scripts/ directory and can be run directly.

</essential_principles>

Output three layers of signals:

Headline level: CPI vs PCE divergence（bps）
Attribution: which buckets are driving PCE (weighted contribution)
Risk framing: observation points and continuity risk assessment

<quick_start>

Fastest way: run a quick check

cd skills/us-cpi-pce-comparator
pip install pandas numpy requests  # 首次使用
python scripts/cpi_pce_analyzer.py --quick

Example output:

{
  "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}
}

Full analysis：

python scripts/cpi_pce_analyzer.py --start 2020-01-01 --measure yoy

</quick_start>

Quick check - view the latest CPI/PCE divergence data
Full analysis - run the complete three-step analysis workflow
Methodology learning - understand the deeper reasons for CPI/PCE differences

Please choose or directly provide analysis parameters.

After routing, read the corresponding document and execute.

<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>

Methodology: references/cpi-pce-methodology.md

The five major differences between CPI vs PCE (weights, scope, formula, housing, population)
Divergence patterns and trading implications
How the Fed interprets the two indicators

Data sources: references/data-sources.md

FRED CSV endpoint (no API key required)
FRED series code mapping table
Bucket definitions and approximate calculations

Implementation guide: references/implementation.md

Inflation calculation formulas (YoY, MoM SAAR, QoQ SAAR)
Weight effect calculation
Volatility analysis

</reference_index>

<workflows_index>

Workflow	Purpose	When to use
analyze.md	Complete three-step analysis	When in-depth analysis is needed
quick-check.md	Quick check of divergence	Daily monitoring or quick answers
</workflows_index>

<templates_index>

Template	Purpose
output-json.md	JSON output structure definition
output-markdown.md	Markdown report template
</templates_index>

<scripts_index>

Script	Command	Purpose
cpi_pce_analyzer.py	`--quick`	Quick check of the latest divergence
cpi_pce_analyzer.py	`--start DATE --measure yoy`	Full analysis
fetch_fred_data.py	`--series CPIAUCSL,PCEPI`	Fetch FRED data
fetch_bls_data.py	`--full`	Fetch BLS CPI data
</scripts_index>

<input_schema>

</input_schema>

<output_schema> See templates/output-json.md for the complete structure definition.

Summary：

{
  "headline": {"cpi_yoy": 2.65, "pce_yoy": 2.79, "gap_bps": 14},
  "low_vol_high_weight_buckets": [{"bucket": "...", "signal": "upside"}],
  "attribution": {"top_contributors": [...], "weight_effect_bps": 12},
  "interpretation": ["..."],
  "caveats": ["..."]
}

</output_schema>

<success_criteria> A successful analysis should produce:

CPI/PCE divergence value at the headline level (bps)
Identify low-volatility, high PCE weight buckets
Weighted inflation contribution by bucket (attribution)
If a baseline exists, produce the 'less baseline' deviation
Actionable interpretation and risk alerts
Clearly annotate data limitations and approximation handling </success_criteria>

About this skill