USMetrics

Pulls 68 US economic and social indicators from five government APIs (FRED, EIA, Treasury, BLS, Census) across 10 categories — GDP, Inflation, Employment, Housing, Consumer Finance, Markets, Trade, Government/Fiscal, Demographics, Health — and analyzes them. Two workflows: UpdateData fetches live values into the Substrate dataset; GetCurrentState produces a multi-timeframe (10y/5y/2y/1y) trend overview with cross-metric correlation, pattern detection, and research recommendations.

The numbers that tell you how the economy is actually doing are scattered across five federal agencies, each with its own API, its own update cadence, and its own publication lag. Pulling "how is the economy?" together by hand means hitting FRED, EIA, Treasury, BLS, and Census separately, normalizing the results, and lining up trends across different timeframes — slow, error-prone, and easy to present stale or preliminary data as if it were final. This skill collects all 68 indicators into one dataset and reads the trends across four timeframes at once.

It analyzes U.S. economic and social metrics using the Substrate US-Common-Metrics dataset and provides trend analysis, cross-metric correlation, pattern detection, and research recommendations. UpdateData must run first so the dataset is current; GetCurrentState then reads the dataset and computes the trends.

All metrics sourced from:

• Location: Configure your data directory path (e.g., ${PAI_DIR}/data/US-Common-Metrics/)
• Master Document: US-Common-Metrics.md (68 metrics across 10 categories)
• Source Documentation: source.md (full methodology)
• Underlying APIs: FRED, EIA, Treasury FiscalData, BLS, Census, CDC, EPA

UpdateData

Full documentation: Workflows/UpdateData.md

Purpose: Fetch live data from FRED, EIA, Treasury APIs and populate the Substrate US-Common-Metrics dataset files. This must run before GetCurrentState to ensure data is current.

Execution:

bun ${CLAUDE_SKILL_DIR}/Tools/UpdateSubstrateMetrics.ts

Outputs:

• US-Common-Metrics.md - Updated with current values
• us-metrics-current.csv - Machine-readable snapshot
• us-metrics-historical.csv - Appended time series

Trigger phrases:

• "Update the US metrics"
• "Refresh the economic data"
• "Pull latest metrics"
• "Update Substrate dataset"

---

GetCurrentState

Full documentation: Workflows/GetCurrentState.md

Produces: A comprehensive overview document analyzing:

• 10-year, 5-year, 2-year, and 1-year trends for all major metrics
• Cross-category interplay analysis
• Pattern detection and anomalies
• Research recommendations

Trigger phrases:

• "How is the US economy doing?"
• "Give me an economic overview"
• "What's the current state of US metrics?"
• "Analyze economic trends"
• "US metrics report"

1. Economic Output & Growth - GDP, industrial production, retail sales
2. Inflation & Prices - CPI, PCE, gas prices, oil prices
3. Employment & Labor - Unemployment, payrolls, jobless claims, quit rate
4. Housing - Home prices, mortgage rates, housing starts
5. Consumer & Personal Finance - Sentiment, saving rate, credit
6. Financial Markets - Interest rates, Treasury yields, volatility
7. Trade & International - Trade balance, USD index
8. Government & Fiscal - Federal debt, budget deficit, spending
9. Demographics & Social - Population, inequality, poverty
10. Health & Crisis - Deaths of despair, air quality, life expectancy

For live data fetching:

• FRED_API_KEY - Federal Reserve Economic Data
• EIA_API_KEY - Energy Information Administration

Tool	Purpose
tools/UpdateSubstrateMetrics.ts	Primary - Fetch all metrics, update Substrate files
Tools/FetchFredSeries.ts	Fetch historical data from FRED API
tools/GenerateAnalysis.ts	Generate analysis report from Substrate data

User: "How is the US economy doing? Give me a full analysis."

→ Invoke GetCurrentState workflow
→ Fetch current + historical data for all metrics
→ Calculate 10y/5y/2y/1y trends
→ Analyze cross-metric correlations
→ Identify patterns and anomalies
→ Generate research recommendations
→ Output comprehensive markdown report

[Key findings in 3-5 bullets]

Economic Output

[10y/5y/2y/1y trends with analysis] ...

[Correlations, leading indicators, divergences]

[Anomalies, regime changes, emerging trends]

[Suggested areas for deeper investigation] ```

• 68 indicators from 5 agencies (FRED, EIA, Treasury, BLS, Census). Each has its own API rate limits and data freshness.
• Economic data has publication lag. GDP is quarterly with revisions. Jobs data is monthly. Don't present preliminary data as final.
• Cross-metric correlation is suggestive, not causal. Never claim one metric caused another.