Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Perform a PESTLE analysis covering Political, Economic, Social, Technological, Legal, and Environmental factors. Use when assessing the macro environment, doing strategic planning, or evaluating external factors affecting your business.
.claude/skills/phuryn-pestle-analysis/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 4% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 25% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 40% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 76% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 8% | 0% |
You are a strategic analyst conducting a PESTLE analysis for $ARGUMENTS.
Your task is to evaluate the macro-environmental factors that could impact product strategy, market entry, or business viability.
What government policies, regulations, and political stability affect the business?
What economic conditions and financial factors matter?
What demographic and cultural trends shape the market?
What technological advances or disruptions are relevant?
What laws, regulations, and compliance requirements apply?
What environmental, climate, and sustainability factors exist?
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-02 | fail→pass | 30,948 | 41,510 | +34% | 1 | 1 | 0% | 6,118 | 6,376 | +4% | 0 | 0 | — |
case-03 | fail→pass | 42,613 | 34,179 | -20% | 1 | 1 | 0% | 5,463 | 6,846 | +25% | 0 | 0 | — |
case-04 | pass→fail | 15,051 | 20,207 | +34% | 1 | 1 | 0% | 2,487 | 4,376 | +76% | 0 | 0 | — |
case-01 | pass→pass | 32,494 | 26,540 | -18% | 1 | 1 | 0% | 5,555 | 5,604 | +1% | 0 | 0 | — |
case-05 | pass→pass | 18,113 | 17,047 | -6% | 1 | 1 | 0% | 2,471 | 3,742 | +51% | 0 | 0 | — |
case-06 | pass→fail | 29,682 | 9,237 | -69% | 1 | 1 | 0% | 5,234 | 2,321 | -56% | 0 | 0 | — |
case-07 | fail→fail | 20,084 | 26,523 | +32% | 1 | 1 | 0% | 3,036 | 5,488 | +81% | 0 | 0 | — |
case-08 | fail→fail | 15,795 | 26,509 | +68% | 1 | 1 | 0% | 2,636 | 5,426 | +106% | 0 | 0 | — |
case-09 | fail→fail | 12,630 | 19,736 | +56% | 1 | 1 | 0% | 1,981 | 4,299 | +117% | 0 | 0 | — |
case-10 | fail→fail | 13,568 | 14,123 | +4% | 1 | 1 | 0% | 1,612 | 3,293 | +104% | 0 | 0 | — |
case-11 | fail→fail | 11,534 | 22,486 | +95% | 1 | 1 | 0% | 1,984 | 4,951 | +150% | 0 | 0 | — |
case-12 | fail→fail | 15,769 | 21,400 | +36% | 1 | 1 | 0% | 2,391 | 4,415 | +85% | 0 | 0 | — |
case-13 | fail→pass | 19,408 | 20,682 | +7% | 1 | 1 | 0% | 3,060 | 4,288 | +40% | 0 | 0 | — |
case-14 | fail→pass | 20,540 | 20,664 | +1% | 1 | 1 | 0% | 2,478 | 4,357 | +76% | 0 | 0 | — |
case-15 | fail→pass | 22,824 | 21,153 | -7% | 1 | 1 | 0% | 3,657 | 3,961 | +8% | 0 | 0 | — |
case-16 | fail→pass | 23,617 | 16,748 | -29% | 1 | 1 | 0% | 2,806 | 3,702 | +32% | 0 | 0 | — |
case-17 | fail→pass | 18,588 | 24,300 | +31% | 1 | 1 | 0% | 2,818 | 5,188 | +84% | 0 | 0 | — |
case-18 | fail→fail | 20,459 | 27,200 | +33% | 1 | 1 | 0% | 3,325 | 5,644 | +70% | 0 | 0 | — |
case-19 | fail→pass | 23,770 | 20,985 | -12% | 1 | 1 | 0% | 3,956 | 4,423 | +12% | 0 | 0 | — |
case-20 | fail→pass | 22,427 | 22,175 | -1% | 1 | 1 | 0% | 3,900 | 4,621 | +18% | 0 | 0 | — |
case-21 | fail→pass | 20,140 | 23,026 | +14% | 1 | 1 | 0% | 3,078 | 4,727 | +54% | 0 | 0 | — |
case-22 | fail→pass | 21,807 | 28,392 | +30% | 1 | 1 | 0% | 2,955 | 4,660 | +58% | 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 +41 percentage points is the difference between those two pass rates over the 22 comparable cases. 2 cases got worse with the skill loaded, and they are 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.