Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Analyze business cycle phases (expansion, peak, contraction, trough) and their implications for business strategy and policy response. Use this skill when the user needs to identify the current economic phase, anticipate cyclical turning points, or adapt business strategy to macroeconomic cycles — even if they say 'are we heading into a recession', 'how should we prepare for a downturn', or 'when will the economy recover'.
.claude/skills/asgard-ai-platform-econ-business-cycle/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-09 | ✗→✓ | ▲ Improved | 16% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 22% | 0% |
| case-01 | ✗→✓ | ▲ Improved | 3% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 13% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -10% | 0% |
The business cycle describes recurring fluctuations in economic activity: expansion → peak → contraction → trough → expansion. Understanding the current phase helps businesses time investments, manage inventory, and prepare for downturns or recoveries.
IRON LAW: Cycles Are Inevitable, Timing Is Not Predictable
Business cycles WILL happen — no economy grows forever. But predicting
EXACTLY when a peak or trough occurs is unreliable. Focus on identifying
the CURRENT phase and preparing for the NEXT one, not predicting exact
turning points.| Phase | Characteristics | Key Indicators | |-------|----------------|----------------| | Expansion | Rising GDP, falling unemployment, growing profits, rising asset prices | PMI > 50, yield curve normal, consumer confidence rising | | Peak | Economy at maximum output, inflation accelerating, capacity constraints | PMI declining from highs, inflation above target, central bank tightening | | Contraction | Falling GDP, rising unemployment, declining profits, credit tightening | PMI < 50, yield curve may invert, layoffs increasing | | Trough | Economy at minimum, excess capacity, low inflation, maximum pessimism | PMI stabilizing, central bank easing, inventories depleted |
| Phase | Business Strategy | Financial Strategy | |-------|------------------|-------------------| | Expansion | Invest in capacity, hire, launch new products | Lock in fixed-rate debt, build reserves | | Peak | Reduce inventory, tighten credit terms, prepare cost cuts | Reduce leverage, increase cash position | | Contraction | Cut costs, preserve cash, acquire distressed assets | Extend debt maturities, negotiate with creditors | | Trough | Invest counter-cyclically, acquire talent at lower cost | Deploy cash reserves, buy undervalued assets |
| Indicator | Signal | |-----------|--------| | Inverted yield curve | 10Y-2Y Treasury spread negative → recession in 12-18 months (historically ~80% accurate) | | Sahm Rule | Unemployment 3-month average rises 0.5%+ from 12-month low | | 2 consecutive quarters negative GDP | Technical recession (lagging confirmation) | | Conference Board Leading Index | 6+ months of decline |
markdown# Business Cycle Assessment: {Country/Region} ## Current Phase: {Expansion / Peak / Contraction / Trough} ## Evidence | Category | Indicator | Reading | Signal | |----------|-----------|---------|--------| | Leading | PMI | XX | {interpretation} | | Leading | Yield curve | XX bps | {interpretation} | | Coincident | Industrial production | X% YoY | {interpretation} | | Lagging | Unemployment | X% | {interpretation} | ## Phase Progression {Where we are in the cycle and directional signals} ## Strategic Implications | Domain | Recommendation | |--------|---------------| | Investment | {expand/hold/cut} | | Hiring | {hire/freeze/reduce} | | Inventory | {build/maintain/liquidate} | | Pricing | {raise/hold/discount} | | Cash management | {deploy/conserve} |
Scenario: Taiwan economy Q4 2025
Diagnosis: Likely at or just past Peak, entering early contraction. Leading indicators are negative but lagging indicators haven't caught up yet — classic inflection point ✓
Strategy: Reduce inventory, tighten receivables, build cash position, delay non-essential capex.
references/taiwan-cycles.md| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-09 | fail→pass | 13,184 | 8,212 | -38% | 1 | 1 | 0% | 2,310 | 2,679 | +16% | 0 | 0 | — |
case-10 | fail→pass | 17,895 | 11,360 | -37% | 1 | 1 | 0% | 2,293 | 2,805 | +22% | 0 | 0 | — |
case-01 | fail→pass | 15,474 | 9,897 | -36% | 1 | 1 | 0% | 2,996 | 3,073 | +3% | 0 | 0 | — |
case-02 | fail→pass | 18,811 | 9,736 | -48% | 1 | 1 | 0% | 2,622 | 2,954 | +13% | 0 | 0 | — |
case-03 | fail→pass | 18,208 | 10,111 | -44% | 1 | 1 | 0% | 3,477 | 3,125 | -10% | 0 | 0 | — |
case-04 | pass→pass | 9,315 | 4,613 | -50% | 1 | 1 | 0% | 1,500 | 2,323 | +55% | 0 | 0 | — |
case-05 | pass→pass | 16,533 | 17,237 | +4% | 1 | 1 | 0% | 2,324 | 4,133 | +78% | 0 | 0 | — |
case-06 | pass→pass | 13,731 | 6,568 | -52% | 1 | 1 | 0% | 1,782 | 2,639 | +48% | 0 | 0 | — |
case-07 | fail→pass | 13,189 | 10,024 | -24% | 1 | 1 | 0% | 2,315 | 2,553 | +10% | 0 | 0 | — |
case-08 | fail→pass | 20,466 | 16,631 | -19% | 1 | 1 | 0% | 2,622 | 2,842 | +8% | 0 | 0 | — |
case-11 | pass→pass | 7,667 | 7,314 | -5% | 1 | 1 | 0% | 937 | 2,560 | +173% | 0 | 0 | — |
case-12 | pass→pass | 17,205 | 11,339 | -34% | 1 | 1 | 0% | 2,296 | 2,714 | +18% | 0 | 0 | — |
case-13 | pass→pass | 16,365 | 11,234 | -31% | 1 | 1 | 0% | 2,210 | 2,849 | +29% | 0 | 0 | — |
case-14 | pass→pass | 16,834 | 18,329 | +9% | 1 | 1 | 0% | 2,732 | 3,490 | +28% | 0 | 0 | — |
case-15 | fail→pass | 14,582 | 10,527 | -28% | 1 | 1 | 0% | 2,385 | 2,609 | +9% | 0 | 0 | — |
case-16 | fail→fail | 13,561 | 13,281 | -2% | 1 | 1 | 0% | 2,142 | 2,999 | +40% | 0 | 0 | — |
case-17 | pass→pass | 16,114 | 13,433 | -17% | 1 | 1 | 0% | 2,239 | 3,195 | +43% | 0 | 0 | — |
case-18 | pass→pass | 22,614 | 15,092 | -33% | 1 | 1 | 0% | 3,139 | 3,188 | +2% | 0 | 0 | — |
case-19 | fail→pass | 20,262 | 10,344 | -49% | 1 | 1 | 0% | 2,839 | 2,886 | +2% | 0 | 0 | — |
case-20 | fail→pass | 36,381 | 8,912 | -76% | 1 | 1 | 0% | 2,533 | 2,785 | +10% | 0 | 0 | — |
case-21 | fail→pass | 12,166 | 7,762 | -36% | 1 | 1 | 0% | 1,937 | 2,455 | +27% | 0 | 0 | — |
case-22 | pass→pass | 20,673 | 19,174 | -7% | 1 | 1 | 0% | 3,393 | 3,067 | -10% | 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. 22 cases were attempted. The headline lift of +50 percentage points is the difference between those two pass rates over the 22 comparable cases.
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.