Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Apply Rittel's 10 criteria to determine if the problem is tame, complex, or wicked, and adjust research strategy accordingly.
.claude/skills/yogsoth-ai-wickedness-assessment/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 175% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 187% | 0% |
| case-10 | ✓→✗ | ▼ Worse | 223% | 0% |
| case-11 | ✓→✗ | ▼ Worse | -39% | 0% |
| case-14 | ✓→✗ | ▼ Worse | -58% | 0% |
Determine the problem's nature — tame, complex, or wicked.
| Base SOP | Target | ±10% Range | |----------|--------|------------| | web-search | 25 | 22–28 | | web-research | 10 | 9–11 | | paper-overview | 25 | 22–28 | | paper-search | 15 | 13–17 | | paper-research | 10 | 9–11 |
<HARD-GATE>
| SOP | Done | Target | % |
|-----|------|--------|---|
| web-search | ? | 25 | ? |
| web-research | ? | 10 | ? |
| paper-overview | ? | 25 | ? |
| paper-search | ? | 15 | ? |
| paper-research | ? | 10 | ? |
Budget Gate: OPEN/CLOSED (>=80% required to exit)
</HARD-GATE>Import: web-search, web-research, paper-overview, paper-search, paper-research Subagent: wickedness-scoring
Apply Rittel's 10 criteria for wicked problems, score the research problem on each, determine if the problem is tame (solvable with standard methods), complex (requires systems thinking), or wicked (requires ongoing management, not solution). Adjust research strategy accordingly.
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use | | --- | --- | | wickedness-scoring | Score a problem against Rittel's 10 criteria to determine if it is tame, complex, or wicked. |
<!-- 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 | 24,280 | 50,527 | +108% | 1 | 1 | 0% | 3,034 | 8,338 | +175% | 0 | 0 | — |
case-02 | pass→pass | 25,207 | 43,768 | +74% | 1 | 1 | 0% | 3,358 | 6,768 | +102% | 0 | 0 | — |
case-03 | fail→pass | 21,337 | 62,647 | +194% | 1 | 1 | 0% | 3,010 | 8,642 | +187% | 0 | 0 | — |
case-04 | pass→pass | 17,302 | 37,901 | +119% | 1 | 1 | 0% | 2,008 | 4,351 | +117% | 0 | 0 | — |
case-05 | pass→pass | 15,807 | 32,930 | +108% | 1 | 1 | 0% | 1,719 | 5,175 | +201% | 0 | 0 | — |
case-06 | fail→fail | 19,166 | 49,403 | +158% | 1 | 1 | 0% | 2,194 | 8,192 | +273% | 0 | 0 | — |
case-07 | pass→pass | 18,942 | 48,366 | +155% | 1 | 1 | 0% | 2,160 | 7,747 | +259% | 0 | 0 | — |
case-08 | pass→pass | 20,947 | 37,021 | +77% | 1 | 1 | 0% | 2,421 | 5,365 | +122% | 0 | 0 | — |
case-09 | pass→pass | 20,399 | 55,058 | +170% | 1 | 1 | 0% | 2,393 | 8,593 | +259% | 0 | 0 | — |
case-10 | pass→fail | 20,357 | 47,561 | +134% | 1 | 1 | 0% | 2,259 | 7,290 | +223% | 0 | 0 | — |
case-11 | pass→fail | 22,987 | 23,106 | +1% | 1 | 1 | 0% | 2,636 | 1,600 | -39% | 0 | 0 | — |
case-12 | pass→pass | 15,198 | 44,189 | +191% | 1 | 1 | 0% | 1,520 | 7,044 | +363% | 0 | 0 | — |
case-13 | pass→pass | 20,051 | 58,844 | +193% | 1 | 1 | 0% | 2,193 | 7,885 | +260% | 0 | 0 | — |
case-14 | pass→fail | 20,683 | 19,290 | -7% | 1 | 1 | 0% | 2,454 | 1,035 | -58% | 0 | 0 | — |
case-15 | pass→pass | 17,284 | 54,783 | +217% | 1 | 1 | 0% | 1,747 | 8,656 | +395% | 0 | 0 | — |
case-16 | pass→pass | 21,969 | 39,614 | +80% | 1 | 1 | 0% | 2,648 | 6,078 | +130% | 0 | 0 | — |
case-17 | pass→pass | 20,428 | 58,810 | +188% | 1 | 1 | 0% | 2,205 | 7,304 | +231% | 0 | 0 | — |
case-18 | pass→pass | 18,399 | 46,564 | +153% | 1 | 1 | 0% | 2,006 | 7,162 | +257% | 0 | 0 | — |
case-19 | pass→pass | 20,992 | 46,060 | +119% | 1 | 1 | 0% | 2,379 | 6,995 | +194% | 0 | 0 | — |
case-20 | pass→pass | 11,283 | 18,393 | +63% | 1 | 1 | 0% | 1,014 | 2,577 | +154% | 0 | 0 | — |
case-21 | pass→pass | 19,953 | 57,293 | +187% | 1 | 1 | 0% | 2,316 | 8,667 | +274% | 0 | 0 | — |
case-22 | pass→fail | 26,204 | 32,679 | +25% | 1 | 1 | 0% | 3,121 | 3,082 | -1% | 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 -9 percentage points is the difference between those two pass rates over the 19 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.