Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Random word/paper/concept as thinking entry point. Use genuine randomness to escape fixation and open unexpected solution paths.
.claude/skills/yogsoth-ai-random-stimulus-entry/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | 1% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 29% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 98% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 4% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -17% | 0% |
Use random word/paper/concept as thinking entry point. Genuine randomness breaks fixation patterns and forces the mind into unexplored territory.
| Resource | Target | Current | % | |----------|--------|---------|---| | web-search | 20 | 0 | 0% | | web-research | 5 | 0 | 0% | | paper-overview | 15 | 0 | 0% | | paper-search | 10 | 0 | 0% | | paper-research | 3 | 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 | |--------|------| | domain-divergence | Ensure stimuli come from genuinely unrelated domains | | bridge-validation | Validate that forced connections produce real insight |
| SOP | Role | |-----|------| | random-word-stimulus | Generate random word stimuli and force connections | | random-paper-entry | Select random paper as stimulus entry point | | forced-connection | Force connection between stimulus and problem | | abstraction-extraction | Extract transferable principle from stimulus domain | | cross-domain-synthesis | Synthesize all stimulus-derived ideas |
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| Tactic | When to use | | --- | --- | | bridge-validation | Validate analogy depth and transfer viability. Ensures only deep structural analogies (not surface-level similarities) proceed to transfer. | | domain-divergence | Scan and select maximally diverse source domains. Ensures creative search covers genuinely unrelated fields with high transfer potential. |
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use | | --- | --- | | cross-domain-synthesis | Synthesize all cross-domain findings into a structured idea report. Integrates outputs from all strategies and SOPs. | | forced-connection | Force connection between two unrelated concepts. Deliberately construct bridging paths where no natural connection exists. | | random-paper-entry | Select random paper facet as creative stimulus. Uses genuine randomness in paper selection to break domain fixation. |
<!-- 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 | pass→pass | 29,919 | 42,889 | +43% | 1 | 1 | 0% | 4,093 | 6,737 | +65% | 0 | 0 | — |
case-07 | fail→pass | 16,215 | 12,234 | -25% | 1 | 1 | 0% | 1,737 | 1,749 | +1% | 0 | 0 | — |
case-08 | pass→pass | 14,834 | 14,429 | -3% | 1 | 1 | 0% | 1,487 | 2,278 | +53% | 0 | 0 | — |
case-09 | fail→pass | 33,250 | 2,157 | -94% | 1 | 1 | 0% | 766 | 989 | +29% | 0 | 0 | — |
case-02 | fail→pass | 35,558 | 56,535 | +59% | 1 | 1 | 0% | 4,518 | 8,925 | +98% | 0 | 0 | — |
case-03 | fail→fail | 39,442 | 20,259 | -49% | 1 | 1 | 0% | 5,024 | 1,486 | -70% | 0 | 0 | — |
case-04 | pass→pass | 22,605 | 16,692 | -26% | 1 | 1 | 0% | 2,544 | 2,717 | +7% | 0 | 0 | — |
case-05 | pass→pass | 22,161 | 37,749 | +70% | 1 | 1 | 0% | 2,472 | 4,082 | +65% | 0 | 0 | — |
case-06 | pass→pass | 9,899 | 12,527 | +27% | 1 | 1 | 0% | 1,484 | 2,592 | +75% | 0 | 0 | — |
case-10 | fail→pass | 11,514 | 7,841 | -32% | 1 | 1 | 0% | 919 | 956 | +4% | 0 | 0 | — |
case-11 | fail→pass | 30,950 | 7,239 | -77% | 1 | 1 | 0% | 1,185 | 986 | -17% | 0 | 0 | — |
case-12 | fail→pass | 15,330 | 7,107 | -54% | 1 | 1 | 0% | 1,497 | 973 | -35% | 0 | 0 | — |
case-13 | pass→pass | 18,829 | 15,079 | -20% | 1 | 1 | 0% | 2,107 | 2,985 | +42% | 0 | 0 | — |
case-14 | pass→pass | 8,160 | 16,268 | +99% | 1 | 1 | 0% | 1,534 | 2,557 | +67% | 0 | 0 | — |
case-15 | pass→pass | 8,817 | 9,812 | +11% | 1 | 1 | 0% | 677 | 1,598 | +136% | 0 | 0 | — |
case-16 | pass→pass | 13,247 | 12,647 | -5% | 1 | 1 | 0% | 1,805 | 2,301 | +27% | 0 | 0 | — |
case-17 | pass→pass | 25,214 | 7,746 | -69% | 1 | 1 | 0% | 1,789 | 1,139 | -36% | 0 | 0 | — |
case-18 | fail→pass | 46,178 | 8,158 | -82% | 1 | 1 | 0% | 1,688 | 1,134 | -33% | 0 | 0 | — |
case-19 | fail→pass | 21,142 | 8,886 | -58% | 1 | 1 | 0% | 2,841 | 1,293 | -54% | 0 | 0 | — |
case-20 | pass→pass | 25,744 | 2,564 | -90% | 1 | 1 | 0% | 1,249 | 1,083 | -13% | 0 | 0 | — |
case-21 | pass→pass | 16,920 | 12,764 | -25% | 1 | 1 | 0% | 1,850 | 1,897 | +3% | 0 | 0 | — |
case-22 | pass→pass | 14,526 | 19,168 | +32% | 1 | 1 | 0% | 1,433 | 2,858 | +99% | 0 | 0 | — |
case-23 | fail→pass | 15,576 | 7,284 | -53% | 1 | 1 | 0% | 1,837 | 974 | -47% | 0 | 0 | — |
case-24 | pass→pass | 18,082 | 8,878 | -51% | 1 | 1 | 0% | 2,094 | 1,342 | -36% | 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 20 counted toward the lift figure. The other 4 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 +38 percentage points is the difference between those two pass rates over the 20 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.