Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →What will competitors do? — Competitive method progress prediction and time window analysis
.claude/skills/yogsoth-ai-competitive-scenario/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-20 | ✗→✓ | ▲ Improved | -43% | 0% |
| case-21 | ✗→✓ | ▲ Improved | 47% | 0% |
| case-22 | ✗→✓ | ▲ Improved | 75% | 0% |
| case-01 | ✗→✓ | ▲ Improved | 54% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 14% | 0% |
Competitive Intelligence Scenario Planning. Predict competitor progress, publication timelines, and methodological breakthroughs that could affect our research positioning. Assess time windows of opportunity and first-mover advantages.
Key principles:
scenario-driver-identificationcompetitive-move-prediction (×3-5 competitors)timeline-projectionscenario-impact-assessment (per competitive scenario)robustness-scoringscenario-synthesis| Step | Token Budget | Notes | |------|-------------|-------| | Driver identification | 8K | Competitor-focused | | Move prediction | 10K × N | N = 3-5 key competitors | | Timeline projection | 12K | Multi-horizon | | Impact assessment | 10K × N | Per competitive scenario | | Robustness scoring | 8K | Competitive positioning | | Synthesis | 12K | Strategy 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 | | --- | --- | | competitive-move-prediction | Predict competitor progress, publications, and strategic moves | | 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-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-20 | fail→pass | 11,334 | 2,014 | -82% | 1 | 1 | 0% | 1,658 | 953 | -43% | 0 | 0 | — |
case-21 | fail→pass | 16,491 | 2,012 | -88% | 1 | 1 | 0% | 635 | 932 | +47% | 0 | 0 | — |
case-22 | fail→pass | 10,710 | 14,176 | +32% | 1 | 1 | 0% | 1,573 | 2,746 | +75% | 0 | 0 | — |
case-01 | fail→pass | 62,103 | 37,433 | -40% | 1 | 1 | 0% | 4,400 | 6,785 | +54% | 0 | 0 | — |
case-02 | fail→pass | 32,283 | 31,588 | -2% | 1 | 1 | 0% | 4,982 | 5,659 | +14% | 0 | 0 | — |
case-03 | fail→fail | 37,224 | 3,945 | -89% | 1 | 1 | 0% | 6,200 | 1,163 | -81% | 0 | 0 | — |
case-04 | pass→pass | 20,632 | 36,586 | +77% | 1 | 1 | 0% | 3,217 | 6,867 | +113% | 0 | 0 | — |
case-05 | fail→pass | 10,417 | 12,143 | +17% | 1 | 1 | 0% | 1,566 | 2,611 | +67% | 0 | 0 | — |
case-06 | pass→pass | 26,392 | 37,101 | +41% | 1 | 1 | 0% | 4,863 | 6,857 | +41% | 0 | 0 | — |
case-07 | pass→pass | 22,088 | 40,776 | +85% | 1 | 1 | 0% | 3,084 | 6,855 | +122% | 0 | 0 | — |
case-08 | pass→fail | 18,655 | 13,466 | -28% | 1 | 1 | 0% | 2,670 | 2,476 | -7% | 0 | 0 | — |
case-09 | fail→pass | 21,703 | 33,218 | +53% | 1 | 1 | 0% | 2,992 | 5,422 | +81% | 0 | 0 | — |
case-10 | pass→pass | 19,815 | 3,334 | -83% | 1 | 1 | 0% | 2,845 | 1,244 | -56% | 0 | 0 | — |
case-11 | fail→pass | 7,646 | 6,426 | -16% | 1 | 1 | 0% | 923 | 1,630 | +77% | 0 | 0 | — |
case-12 | pass→pass | 12,625 | 5,748 | -54% | 1 | 1 | 0% | 1,774 | 1,570 | -11% | 0 | 0 | — |
case-13 | pass→pass | 20,293 | 33,107 | +63% | 1 | 1 | 0% | 2,727 | 5,529 | +103% | 0 | 0 | — |
case-14 | pass→pass | 19,433 | 29,913 | +54% | 1 | 1 | 0% | 2,827 | 4,067 | +44% | 0 | 0 | — |
case-15 | fail→pass | 10,793 | 2,267 | -79% | 1 | 1 | 0% | 437 | 1,008 | +131% | 0 | 0 | — |
case-16 | fail→pass | 13,937 | 1,874 | -87% | 1 | 1 | 0% | 643 | 910 | +42% | 0 | 0 | — |
case-17 | pass→pass | 15,214 | 3,257 | -79% | 1 | 1 | 0% | 2,254 | 1,118 | -50% | 0 | 0 | — |
case-18 | fail→pass | 14,674 | 2,345 | -84% | 1 | 1 | 0% | 2,278 | 1,047 | -54% | 0 | 0 | — |
case-19 | pass→pass | 12,831 | 4,561 | -64% | 1 | 1 | 0% | 1,815 | 1,496 | -18% | 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, and 19 counted toward the lift figure. The other 3 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 +45 percentage points is the difference between those two pass rates over the 19 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.