Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Identify the key parameters/dimensions of a problem space. Produces a structured parameter list with value ranges for morphological analysis.
.claude/skills/yogsoth-ai-parameter-identification/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-20 | ✓→✓ | ＝ Same ✓ | 73% | 0% |
| case-21 | ✓→✓ | ＝ Same ✓ | 29% | 0% |
| case-22 | ✓→✓ | ＝ Same ✓ | 65% | 0% |
| case-04 | ✗→✗ | ＝ Same ✗ | 54% | 0% |
| case-01 | ✗→✗ | ＝ Same ✗ | 76% | 0% |
Identify the key parameters/dimensions of a problem space.
Subagent — spawned via subagent-spawning/spawn-agent skill.
Parameter identification requires systematic decomposition of a system into orthogonal dimensions. Benefits from focused analytical attention to ensure completeness and independence of parameters.
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use | | --- | --- | | spawn-agent | Spawn a customized CC subagent with full MCP tool access. Used by SOPs that declare execution: subagent. |
<!-- 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-04 | fail→fail | 28,790 | 37,594 | +31% | 1 | 1 | 0% | 3,351 | 5,175 | +54% | 0 | 0 | — |
case-01 | fail→fail | 20,569 | 39,852 | +94% | 1 | 1 | 0% | 3,237 | 5,695 | +76% | 0 | 0 | — |
case-02 | fail→fail | 34,541 | 42,581 | +23% | 1 | 1 | 0% | 5,641 | 6,315 | +12% | 0 | 0 | — |
case-03 | fail→fail | 19,511 | 36,653 | +88% | 1 | 1 | 0% | 2,974 | 4,397 | +48% | 0 | 0 | — |
case-05 | fail→fail | 23,206 | 23,757 | +2% | 1 | 1 | 0% | 3,813 | 3,943 | +3% | 0 | 0 | — |
case-06 | fail→fail | 45,803 | 37,616 | -18% | 1 | 1 | 0% | 1,563 | 6,434 | +312% | 0 | 0 | — |
case-07 | fail→fail | 26,269 | 45,546 | +73% | 1 | 1 | 0% | 4,486 | 4,004 | -11% | 0 | 0 | — |
case-08 | fail→fail | 26,752 | 67,274 | +151% | 1 | 1 | 0% | 3,763 | 4,773 | +27% | 0 | 0 | — |
case-09 | fail→fail | 23,164 | 29,734 | +28% | 1 | 1 | 0% | 3,550 | 984 | -72% | 0 | 0 | — |
case-10 | fail→fail | 25,914 | 25,546 | -1% | 1 | 1 | 0% | 3,116 | 3,388 | +9% | 0 | 0 | — |
case-11 | fail→fail | 20,075 | 38,220 | +90% | 1 | 1 | 0% | 3,358 | 4,784 | +42% | 0 | 0 | — |
case-12 | fail→fail | 26,738 | 21,298 | -20% | 1 | 1 | 0% | 3,281 | 3,372 | +3% | 0 | 0 | — |
case-13 | fail→fail | 26,598 | 46,716 | +76% | 1 | 1 | 0% | 3,187 | 4,622 | +45% | 0 | 0 | — |
case-14 | fail→fail | 18,944 | 50,420 | +166% | 1 | 1 | 0% | 2,755 | 5,329 | +93% | 0 | 0 | — |
case-15 | fail→fail | 29,348 | 41,870 | +43% | 1 | 1 | 0% | 4,980 | 5,183 | +4% | 0 | 0 | — |
case-16 | fail→fail | 25,381 | 52,307 | +106% | 1 | 1 | 0% | 3,134 | 6,805 | +117% | 0 | 0 | — |
case-17 | fail→fail | 24,446 | 29,750 | +22% | 1 | 1 | 0% | 3,059 | 4,067 | +33% | 0 | 0 | — |
case-18 | fail→fail | 32,099 | 58,409 | +82% | 1 | 1 | 0% | 4,307 | 6,623 | +54% | 0 | 0 | — |
case-19 | fail→fail | 28,048 | 33,565 | +20% | 1 | 1 | 0% | 4,309 | 4,929 | +14% | 0 | 0 | — |
case-20 | pass→pass | 19,332 | 29,472 | +52% | 1 | 1 | 0% | 2,846 | 4,926 | +73% | 0 | 0 | — |
case-21 | pass→pass | 16,405 | 18,026 | +10% | 1 | 1 | 0% | 2,352 | 3,045 | +29% | 0 | 0 | — |
case-22 | pass→pass | 2,483 | 8,259 | +233% | 1 | 1 | 0% | 410 | 676 | +65% | 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 20 counted toward the lift figure. The other 2 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 0 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.
Other measured skills in the registry, with their headline benchmark lift.