Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Interpret macroeconomic indicators including GDP, inflation, unemployment, interest rates, and exchange rates to assess economic health and predict trends. Use this skill when the user needs to evaluate a country's economic outlook, understand monetary/fiscal policy impacts, or contextualize business decisions within the macroeconomic environment — even if they say 'is the economy doing well', 'what do rising interest rates mean for us', or 'explain today's economic data'.
.claude/skills/asgard-ai-platform-econ-macro-indicators/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -1% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -5% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 29% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 47% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 103% | 0% |
Macroeconomic indicators measure aggregate economic performance. They divide into leading (predict future), coincident (reflect current), and lagging (confirm past) indicators. Understanding these helps contextualize business decisions within the broader economic environment.
IRON LAW: Leading, Coincident, or Lagging — Know Which Type
GDP growth is LAGGING — by the time it's published, the economy has already
changed. Stock markets and PMI are LEADING — they predict future direction.
Unemployment is LAGGING — it rises after a recession starts.
Using a lagging indicator to predict the future is looking in the rearview mirror.
Match the indicator type to your analysis purpose.GDP (Gross Domestic Product)
Inflation (CPI/PPI)
Unemployment Rate
Interest Rates
Exchange Rate
PMI (Purchasing Managers' Index)
Central bank raises rates
→ Borrowing costs rise
→ Consumer spending slows + Business investment slows
→ GDP growth slows
→ Unemployment rises (with lag)
→ Inflation falls (the goal)markdown# Macroeconomic Assessment: {Country/Region} ## Indicator Dashboard | Indicator | Current | Previous | Trend | Type | |-----------|---------|----------|-------|------| | GDP Growth | X% | X% | ↑/↓/→ | Lagging | | CPI Inflation | X% | X% | ↑/↓/→ | Coincident | | Unemployment | X% | X% | ↑/↓/→ | Lagging | | Policy Rate | X% | X% | ↑/↓/→ | — | | PMI | XX | XX | ↑/↓/→ | Leading | | Exchange Rate | X.XX | X.XX | ↑/↓/→ | — | ## Economic Phase {Expansion / Peak / Contraction / Trough} ## Key Signals - Leading indicators suggest: {direction} - Divergence: {if any — e.g., PMI falling while GDP still positive = slowdown ahead} ## Business Implications - For {industry}: {specific impact}
Scenario: Taiwan macro assessment Q4 2025 | Indicator | Value | Signal | |-----------|-------|--------| | GDP Growth | 3.2% YoY | Solid but decelerating from 4.1% | | CPI | 2.1% | Near target, stable | | Unemployment | 3.6% | Near full employment | | Policy Rate | 2.0% | Held steady for 3 quarters | | PMI | 48.5 | Below 50 — leading indicator of slowdown |
Diagnosis: GDP looks healthy (lagging) but PMI signals contraction ahead. The economy is likely at or near peak phase ✓
references/taiwan-data-sources.md| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 21,000 | 19,185 | -9% | 1 | 1 | 0% | 3,878 | 3,852 | -1% | 0 | 0 | — |
case-02 | fail→fail | 22,763 | 19,275 | -15% | 1 | 1 | 0% | 3,095 | 3,935 | +27% | 0 | 0 | — |
case-03 | fail→pass | 24,970 | 10,777 | -57% | 1 | 1 | 0% | 3,405 | 3,234 | -5% | 0 | 0 | — |
case-04 | pass→pass | 33,989 | 54,331 | +60% | 1 | 1 | 0% | 6,176 | 5,929 | -4% | 0 | 0 | — |
case-05 | pass→fail | 23,043 | 23,260 | +1% | 1 | 1 | 0% | 4,084 | 5,214 | +28% | 0 | 0 | — |
case-06 | pass→pass | 20,739 | 13,160 | -37% | 1 | 1 | 0% | 3,193 | 3,177 | -1% | 0 | 0 | — |
case-07 | pass→pass | 8,998 | 7,696 | -14% | 1 | 1 | 0% | 1,371 | 2,832 | +107% | 0 | 0 | — |
case-08 | pass→pass | 31,324 | 12,229 | -61% | 1 | 1 | 0% | 2,297 | 3,097 | +35% | 0 | 0 | — |
case-09 | fail→fail | 22,168 | 17,728 | -20% | 1 | 1 | 0% | 3,297 | 3,504 | +6% | 0 | 0 | — |
case-10 | pass→pass | 12,103 | 12,392 | +2% | 1 | 1 | 0% | 1,981 | 3,138 | +58% | 0 | 0 | — |
case-11 | pass→pass | 13,704 | 11,591 | -15% | 1 | 1 | 0% | 2,220 | 2,691 | +21% | 0 | 0 | — |
case-12 | fail→pass | 19,367 | 15,004 | -23% | 1 | 1 | 0% | 2,715 | 3,502 | +29% | 0 | 0 | — |
case-13 | pass→pass | 32,096 | 16,360 | -49% | 1 | 1 | 0% | 2,339 | 3,329 | +42% | 0 | 0 | — |
case-20 | pass→pass | 15,616 | 9,558 | -39% | 1 | 1 | 0% | 1,960 | 2,959 | +51% | 0 | 0 | — |
case-14 | pass→pass | 12,180 | 10,104 | -17% | 1 | 1 | 0% | 1,887 | 2,743 | +45% | 0 | 0 | — |
case-15 | fail→pass | 13,255 | 14,510 | +9% | 1 | 1 | 0% | 1,949 | 2,856 | +47% | 0 | 0 | — |
case-16 | fail→pass | 9,663 | 14,937 | +55% | 1 | 1 | 0% | 1,574 | 3,195 | +103% | 0 | 0 | — |
case-17 | pass→pass | 15,220 | 13,220 | -13% | 1 | 1 | 0% | 2,304 | 3,219 | +40% | 0 | 0 | — |
case-18 | fail→pass | 15,884 | 12,499 | -21% | 1 | 1 | 0% | 2,589 | 2,779 | +7% | 0 | 0 | — |
case-19 | pass→pass | 7,867 | 7,316 | -7% | 1 | 1 | 0% | 1,304 | 2,434 | +87% | 0 | 0 | — |
case-21 | fail→fail | 28,219 | 12,810 | -55% | 1 | 1 | 0% | 3,719 | 3,487 | -6% | 0 | 0 | — |
case-22 | pass→pass | 16,301 | 6,663 | -59% | 1 | 1 | 0% | 2,295 | 2,247 | -2% | 0 | 0 | — |
case-23 | pass→pass | 16,668 | 14,455 | -13% | 1 | 1 | 0% | 2,149 | 3,053 | +42% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted. The headline lift of +22 percentage points is the difference between those two pass rates over the 23 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.