Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Map 15 vital relations between concepts
.claude/skills/yogsoth-ai-vital-relation-mapping/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✓→✗ | ▼ Worse | 62% | 0% |
| case-04 | ✓→✗ | ▼ Worse | 86% | 0% |
| case-06 | ✓→✗ | ▼ Worse | 139% | 0% |
| case-11 | ✗→✗ | ＝ Same ✗ | 73% | 0% |
| case-01 | ✗→✗ | ＝ Same ✗ | 97% | 0% |
Map 15 vital relations between concepts — the fundamental cognitive relations that structure conceptual integration (Change, Identity, Time, Space, Cause-Effect, Part-Whole, Representation, Role, Analogy, Disanalogy, Property, Similarity, Category, Intentionality, Uniqueness).
Subagent — spawned via subagent-spawning/spawn-agent skill.
Vital relation mapping requires systematic analysis of 15 distinct relation types between two concepts, each requiring careful judgment about presence, strength, and compression potential. Benefits from methodical dedicated attention.
<!-- 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-11 | fail→fail | 30,343 | 39,761 | +31% | 1 | 1 | 0% | 3,357 | 5,799 | +73% | 0 | 0 | — |
case-05 | pass→fail | 24,591 | 46,616 | +90% | 1 | 1 | 0% | 3,653 | 5,927 | +62% | 0 | 0 | — |
case-01 | fail→fail | 25,410 | 38,659 | +52% | 1 | 1 | 0% | 2,935 | 5,795 | +97% | 0 | 0 | — |
case-02 | fail→fail | 34,144 | 41,985 | +23% | 1 | 1 | 0% | 3,493 | 6,672 | +91% | 0 | 0 | — |
case-03 | fail→fail | 29,791 | 48,518 | +63% | 1 | 1 | 0% | 4,443 | 7,742 | +74% | 0 | 0 | — |
case-04 | pass→fail | 15,186 | 32,781 | +116% | 1 | 1 | 0% | 2,561 | 4,773 | +86% | 0 | 0 | — |
case-06 | pass→fail | 20,772 | 60,016 | +189% | 1 | 1 | 0% | 2,760 | 6,604 | +139% | 0 | 0 | — |
case-07 | fail→fail | 24,643 | 42,005 | +70% | 1 | 1 | 0% | 2,742 | 6,082 | +122% | 0 | 0 | — |
case-08 | fail→fail | 20,540 | 15,721 | -23% | 1 | 1 | 0% | 3,137 | 792 | -75% | 0 | 0 | — |
case-09 | fail→fail | 22,895 | 38,433 | +68% | 1 | 1 | 0% | 2,642 | 6,649 | +152% | 0 | 0 | — |
case-10 | fail→fail | 19,376 | 69,693 | +260% | 1 | 1 | 0% | 2,868 | 8,433 | +194% | 0 | 0 | — |
case-12 | fail→fail | 21,935 | 48,335 | +120% | 1 | 1 | 0% | 3,357 | 7,849 | +134% | 0 | 0 | — |
case-13 | fail→fail | 26,751 | 54,471 | +104% | 1 | 1 | 0% | 3,122 | 7,614 | +144% | 0 | 0 | — |
case-14 | fail→fail | 28,549 | 69,570 | +144% | 1 | 1 | 0% | 3,531 | 7,140 | +102% | 0 | 0 | — |
case-15 | fail→fail | 25,473 | 54,371 | +113% | 1 | 1 | 0% | 3,001 | 8,297 | +176% | 0 | 0 | — |
case-16 | fail→fail | 26,129 | 64,023 | +145% | 1 | 1 | 0% | 3,110 | 7,905 | +154% | 0 | 0 | — |
case-17 | fail→fail | 24,322 | 60,700 | +150% | 1 | 1 | 0% | 2,964 | 6,826 | +130% | 0 | 0 | — |
case-18 | fail→fail | 22,591 | 53,084 | +135% | 1 | 1 | 0% | 2,893 | 6,660 | +130% | 0 | 0 | — |
case-19 | fail→fail | 23,212 | 59,518 | +156% | 1 | 1 | 0% | 2,852 | 7,260 | +155% | 0 | 0 | — |
case-20 | fail→fail | 19,238 | 46,133 | +140% | 1 | 1 | 0% | 3,055 | 6,954 | +128% | 0 | 0 | — |
case-21 | fail→fail | 38,685 | 56,055 | +45% | 1 | 1 | 0% | 4,904 | 8,419 | +72% | 0 | 0 | — |
case-22 | fail→fail | 21,504 | 43,125 | +101% | 1 | 1 | 0% | 2,689 | 6,304 | +134% | 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 -14 percentage points is the difference between those two pass rates over the 20 comparable cases. 3 cases got worse with the skill loaded, and they are included in that figure.
Other measured skills in the registry, with their headline benchmark lift.