Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →How does it evolve over time? — Short/medium/long-term timeline projection with technology maturity curves
.claude/skills/yogsoth-ai-temporal-scenario/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 8% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -2% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -37% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -45% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 125% | 0% |
Temporal Scenario Planning with Technology Maturity Curves. Project how the research landscape evolves across multiple time horizons (short: 6 months, medium: 2 years, long: 5+ years). Map technology S-curves, adoption dynamics, and paradigm shift timing.
Key principles:
scenario-driver-identificationtimeline-projectionscenario-narrative-construction (×3 horizons)scenario-impact-assessment (per horizon)robustness-scoringscenario-synthesis| Step | Token Budget | Notes | |------|-------------|-------| | Driver identification | 8K | Time-dynamics focused | | Timeline projection | 15K | Multi-horizon + S-curves | | Narrative construction | 12K × 3 | Per horizon | | Impact assessment | 10K × 3 | Per horizon | | Robustness scoring | 10K | Temporal sensitivity | | Synthesis | 12K | Timing recommendations |
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| Tactic | When to use | | --- | --- | | strategy-robustness-testing | Orchestrates impact assessment and robustness scoring to evaluate research approach resilience across scenarios |
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use | | --- | --- | | robustness-scoring | Compute robustness index across scenarios with sensitivity analysis | | scenario-driver-identification | Identify key uncertainty drivers using PESTEL framework scanning | | scenario-impact-assessment | Assess each scenario's impact on the research approach across multiple dimensions | | scenario-narrative-construction | Build rich narratives for surviving morphological configurations using Shell method | | scenario-synthesis | Comprehensive scenario analysis report synthesizing all scenario work | | timeline-projection | Extrapolate research landscape timelines using trend analysis and milestone projection |
<!-- END available-tables (generated) -->
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 50,019 | 55,210 | +10% | 1 | 1 | 0% | 8,291 | 8,992 | +8% | 0 | 0 | — |
case-02 | fail→pass | 54,394 | 49,472 | -9% | 1 | 1 | 0% | 8,269 | 8,115 | -2% | 0 | 0 | — |
case-03 | pass→pass | 21,949 | 42,760 | +95% | 1 | 1 | 0% | 2,560 | 6,705 | +162% | 0 | 0 | — |
case-04 | pass→fail | 22,635 | 46,498 | +105% | 1 | 1 | 0% | 3,468 | 8,183 | +136% | 0 | 0 | — |
case-05 | pass→pass | 10,847 | 40,484 | +273% | 1 | 1 | 0% | 2,244 | 8,937 | +298% | 0 | 0 | — |
case-06 | fail→pass | 18,601 | 8,431 | -55% | 1 | 1 | 0% | 2,015 | 1,261 | -37% | 0 | 0 | — |
case-07 | fail→pass | 18,000 | 7,679 | -57% | 1 | 1 | 0% | 2,047 | 1,123 | -45% | 0 | 0 | — |
case-08 | fail→pass | 25,810 | 7,366 | -71% | 1 | 1 | 0% | 494 | 1,110 | +125% | 0 | 0 | — |
case-09 | fail→pass | 19,928 | 10,940 | -45% | 1 | 1 | 0% | 2,372 | 1,576 | -34% | 0 | 0 | — |
case-10 | fail→pass | 18,178 | 9,463 | -48% | 1 | 1 | 0% | 2,081 | 1,338 | -36% | 0 | 0 | — |
case-11 | fail→fail | 14,588 | 11,881 | -19% | 1 | 1 | 0% | 1,232 | 1,631 | +32% | 0 | 0 | — |
case-12 | fail→pass | 27,669 | 1,513 | -95% | 1 | 1 | 0% | 872 | 918 | +5% | 0 | 0 | — |
case-13 | fail→pass | 13,997 | 7,431 | -47% | 1 | 1 | 0% | 1,389 | 1,075 | -23% | 0 | 0 | — |
case-14 | fail→pass | 18,274 | 8,071 | -56% | 1 | 1 | 0% | 1,787 | 1,044 | -42% | 0 | 0 | — |
case-15 | fail→pass | 8,938 | 6,936 | -22% | 1 | 1 | 0% | 562 | 936 | +67% | 0 | 0 | — |
case-16 | fail→pass | 12,898 | 6,486 | -50% | 1 | 1 | 0% | 617 | 886 | +44% | 0 | 0 | — |
case-17 | pass→pass | 14,413 | 8,923 | -38% | 1 | 1 | 0% | 1,487 | 1,281 | -14% | 0 | 0 | — |
case-18 | fail→pass | 14,119 | 9,598 | -32% | 1 | 1 | 0% | 1,390 | 1,419 | +2% | 0 | 0 | — |
case-19 | pass→pass | 14,838 | 10,890 | -27% | 1 | 1 | 0% | 1,636 | 1,556 | -5% | 0 | 0 | — |
case-20 | fail→pass | 14,165 | 7,655 | -46% | 1 | 1 | 0% | 2,223 | 1,119 | -50% | 0 | 0 | — |
case-21 | pass→pass | 15,239 | 7,178 | -53% | 1 | 1 | 0% | 1,764 | 1,066 | -40% | 0 | 0 | — |
case-22 | fail→pass | 15,231 | 6,778 | -55% | 1 | 1 | 0% | 1,686 | 1,002 | -41% | 0 | 0 | — |
case-23 | pass→pass | 16,529 | 7,314 | -56% | 1 | 1 | 0% | 1,076 | 1,076 | 0% | 0 | 0 | — |
case-24 | fail→pass | 10,903 | 7,077 | -35% | 1 | 1 | 0% | 1,749 | 1,030 | -41% | 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. 24 cases were attempted, and 23 counted toward the lift figure. The other 1 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +63 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.