Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Strategy for ranking unexplored combinations by novelty, feasibility, and potential impact.
.claude/skills/yogsoth-ai-knowledge-structuring-gap-prioritization/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-12 | ✗→✓ | ▲ Improved | 8% | 0% |
| case-01 | ✗→✓ | ▲ Improved | -30% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 15% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 9% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -1% | 0% |
Rank the empty cells (unexplored combinations) by their potential value. Not all gaps are worth filling — prioritize by novelty, feasibility, and expected impact.
An empty cell is only an opportunity if it's feasible and valuable. Rank gaps by: (1) how novel the combination is, (2) how feasible it is to realize, (3) what impact it would have if successful.
| Metric | S | M | L | |--------|---|---|---| | Gaps scored | 3 | 8 | 15 | | Questions generated | 3 | 8 | 15 | | Top priorities identified | 2 | 4 | 8 |
| Metric | Target | Current | Status |
|---------------------|--------|---------|--------|
| Gaps scored | X | 0 | ⬜ |
| Questions generated | X | 0 | ⬜ |
| Top priorities | X | 0 | ⬜ |<HARD-GATE> Cannot exit until 80% of budget met. Print state ledger before each iteration decision. </HARD-GATE>
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| Tactic | When to use | | --- | --- | | axis-extraction | Tactic for systematically extracting axes of variation from literature — identify how practitioners compare approaches. | | matrix-generation | Tactic for generating and populating combination matrices — cross dimensions to enumerate the design space. |
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use | | --- | --- | | knowledge-structuring-novelty-scoring | SOP for scoring empty cells by novelty potential — how surprising and valuable would this combination be? | | matrix-export | SOP for exporting the dimensional matrix as a readable document or structured data. | | question-generation | SOP for generating research questions from promising gaps in the design space. |
<!-- 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-12 | fail→pass | 34,287 | 25,200 | -27% | 1 | 1 | 0% | 3,604 | 3,889 | +8% | 0 | 0 | — |
case-01 | fail→pass | 53,172 | 47,272 | -11% | 1 | 1 | 0% | 8,262 | 5,756 | -30% | 0 | 0 | — |
case-02 | fail→fail | 51,468 | 34,369 | -33% | 1 | 1 | 0% | 4,682 | 6,337 | +35% | 0 | 0 | — |
case-03 | fail→pass | 45,199 | 65,602 | +45% | 1 | 1 | 0% | 7,661 | 8,776 | +15% | 0 | 0 | — |
case-04 | pass→fail | 18,973 | 36,646 | +93% | 1 | 1 | 0% | 2,921 | 6,168 | +111% | 0 | 0 | — |
case-05 | pass→pass | 39,241 | 37,232 | -5% | 1 | 1 | 0% | 5,278 | 6,249 | +18% | 0 | 0 | — |
case-06 | pass→pass | 18,093 | 38,350 | +112% | 1 | 1 | 0% | 1,098 | 1,988 | +81% | 0 | 0 | — |
case-07 | fail→pass | 58,194 | 41,318 | -29% | 1 | 1 | 0% | 4,134 | 4,505 | +9% | 0 | 0 | — |
case-08 | pass→pass | 64,236 | 49,809 | -22% | 1 | 1 | 0% | 7,104 | 6,090 | -14% | 0 | 0 | — |
case-09 | fail→pass | 59,240 | 48,411 | -18% | 1 | 1 | 0% | 8,246 | 8,171 | -1% | 0 | 0 | — |
case-10 | fail→pass | 49,560 | 48,087 | -3% | 1 | 1 | 0% | 3,487 | 5,830 | +67% | 0 | 0 | — |
case-11 | pass→pass | 32,066 | 17,083 | -47% | 1 | 1 | 0% | 2,054 | 2,614 | +27% | 0 | 0 | — |
case-13 | fail→pass | 20,472 | 4,591 | -78% | 1 | 1 | 0% | 2,419 | 1,216 | -50% | 0 | 0 | — |
case-14 | fail→pass | 26,638 | 10,689 | -60% | 1 | 1 | 0% | 1,560 | 1,594 | +2% | 0 | 0 | — |
case-15 | fail→pass | 20,237 | 6,283 | -69% | 1 | 1 | 0% | 1,849 | 1,624 | -12% | 0 | 0 | — |
case-16 | pass→pass | 19,140 | 11,347 | -41% | 1 | 1 | 0% | 2,222 | 1,517 | -32% | 0 | 0 | — |
case-17 | pass→pass | 9,126 | 2,407 | -74% | 1 | 1 | 0% | 1,480 | 925 | -38% | 0 | 0 | — |
case-18 | fail→pass | 20,291 | 11,832 | -42% | 1 | 1 | 0% | 2,573 | 1,648 | -36% | 0 | 0 | — |
case-19 | fail→pass | 15,338 | 21,259 | +39% | 1 | 1 | 0% | 2,375 | 3,187 | +34% | 0 | 0 | — |
case-20 | pass→pass | 18,400 | 12,354 | -33% | 1 | 1 | 0% | 1,212 | 1,771 | +46% | 0 | 0 | — |
case-21 | pass→pass | 14,761 | 40,040 | +171% | 1 | 1 | 0% | 2,340 | 8,754 | +274% | 0 | 0 | — |
case-22 | pass→pass | 19,646 | 12,918 | -34% | 1 | 1 | 0% | 1,877 | 2,833 | +51% | 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. The headline lift of +45 percentage points is the difference between those two pass rates over the 22 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.