Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →View problem from 5yr/50yr/500yr future, backcast to generate temporally-informed creative solutions.
.claude/skills/yogsoth-ai-temporal-projection/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -16% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 105% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -6% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -7% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 7% | 0% |
View problem from 5yr/50yr/500yr future, backcast to generate temporally-informed creative solutions.
| Resource | Target | Current | % | |----------|--------|---------|---| | web-search | 20 | 0 | 0% | | web-research | 8 | 0 | 0% | | paper-overview | 20 | 0 | 0% | | paper-search | 12 | 0 | 0% | | paper-research | 5 | 0 | 0% |
Cannot exit strategy until ≥80% of each budget line is consumed OR yield targets are met with justification for remaining budget.
| Tactic | Role | |--------|------| | evaluation-filtering | Filter and rank resulting ideas (shared) |
| SOP | Role | |-----|------| | time-machine | Project to specific time horizons | | perspective-synthesis | Synthesize temporal insights |
| Metric | Floor | |--------|-------| | Time horizons explored | ≥3 | | Backcast paths generated | ≥3 | | Novel present-day actions identified | ≥5 | | Paradigm shift insights | ≥2 |
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use | | --- | --- | | perspective-synthesis | Synthesize all perspective outputs into a structured multi-perspective idea report. | | time-machine | Temporal projection — view a solution from future/past time horizons to generate temporally-informed insights. |
<!-- 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 | 58,420 | 44,156 | -24% | 1 | 1 | 0% | 7,821 | 6,603 | -16% | 0 | 0 | — |
case-02 | fail→pass | 29,810 | 51,774 | +74% | 1 | 1 | 0% | 3,628 | 7,434 | +105% | 0 | 0 | — |
case-03 | fail→pass | 58,596 | 50,590 | -14% | 1 | 1 | 0% | 7,886 | 7,409 | -6% | 0 | 0 | — |
case-04 | fail→pass | 55,969 | 48,958 | -13% | 1 | 1 | 0% | 8,238 | 7,661 | -7% | 0 | 0 | — |
case-05 | pass→pass | 36,379 | 44,710 | +23% | 1 | 1 | 0% | 5,357 | 6,697 | +25% | 0 | 0 | — |
case-06 | fail→pass | 51,073 | 53,976 | +6% | 1 | 1 | 0% | 7,560 | 8,053 | +7% | 0 | 0 | — |
case-07 | fail→pass | 60,822 | 47,714 | -22% | 1 | 1 | 0% | 8,236 | 8,021 | -3% | 0 | 0 | — |
case-08 | fail→pass | 28,601 | 57,967 | +103% | 1 | 1 | 0% | 3,761 | 8,749 | +133% | 0 | 0 | — |
case-09 | fail→pass | 55,474 | 43,508 | -22% | 1 | 1 | 0% | 8,236 | 6,382 | -23% | 0 | 0 | — |
case-10 | fail→pass | 36,911 | 48,986 | +33% | 1 | 1 | 0% | 5,078 | 7,358 | +45% | 0 | 0 | — |
case-11 | fail→pass | 26,783 | 51,565 | +93% | 1 | 1 | 0% | 4,427 | 8,261 | +87% | 0 | 0 | — |
case-12 | fail→pass | 47,535 | 43,036 | -9% | 1 | 1 | 0% | 6,484 | 6,552 | +1% | 0 | 0 | — |
case-13 | fail→fail | 21,892 | 19,145 | -13% | 1 | 1 | 0% | 2,644 | 1,017 | -62% | 0 | 0 | — |
case-14 | fail→pass | 40,379 | 51,776 | +28% | 1 | 1 | 0% | 5,721 | 7,901 | +38% | 0 | 0 | — |
case-15 | fail→pass | 32,001 | 38,878 | +21% | 1 | 1 | 0% | 4,078 | 5,717 | +40% | 0 | 0 | — |
case-16 | fail→pass | 23,907 | 57,718 | +141% | 1 | 1 | 0% | 3,636 | 8,225 | +126% | 0 | 0 | — |
case-17 | fail→pass | 34,216 | 45,410 | +33% | 1 | 1 | 0% | 4,405 | 6,971 | +58% | 0 | 0 | — |
case-18 | fail→pass | 19,352 | 41,629 | +115% | 1 | 1 | 0% | 3,179 | 6,420 | +102% | 0 | 0 | — |
case-19 | fail→pass | 29,726 | 52,148 | +75% | 1 | 1 | 0% | 3,413 | 7,960 | +133% | 0 | 0 | — |
case-20 | fail→pass | 27,113 | 50,987 | +88% | 1 | 1 | 0% | 3,289 | 8,736 | +166% | 0 | 0 | — |
case-21 | pass→fail | 27,328 | 49,024 | +79% | 1 | 1 | 0% | 3,982 | 7,656 | +92% | 0 | 0 | — |
case-22 | pass→fail | 20,927 | 32,766 | +57% | 1 | 1 | 0% | 3,645 | 6,061 | +66% | 0 | 0 | — |
case-23 | pass→fail | 16,059 | 42,388 | +164% | 1 | 1 | 0% | 2,501 | 6,593 | +164% | 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, and 22 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 +65 percentage points is the difference between those two pass rates over the 22 comparable cases. 4 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.