Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Define niches within the solution space, map candidates to niches, score coverage completeness, and identify gaps requiring attention.
.claude/skills/yogsoth-ai-niche-coverage-analysis/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | 14% | 0% |
| case-14 | ✗→✓ | ▲ Improved | -4% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 101% | 0% |
| case-22 | ✗→✓ | ▲ Improved | 109% | 0% |
| case-23 | ✗→✓ | ▲ Improved | 19% | 0% |
Systematically define the niches or capability areas that a portfolio should cover, map candidates to those niches, and score how well the current selection covers the space.
| Stage | SOP | Purpose | |-------|-----|---------| | 1 | niche-definition | Define niches and capability areas to cover | | 2 | niche-mapping | Map each candidate to its covered niches | | 3 | coverage-scoring | Score coverage, redundancy, and gap severity |
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use | | --- | --- | | coverage-scoring | Compute coverage completeness, redundancy, and gap severity scores from a coverage map. | | niche-definition | Define niches and capability areas that a portfolio should cover based on domain structure and objectives. | | niche-mapping | Map each candidate to the niches it covers, indicating strength of coverage for each assignment. |
<!-- 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-02 | pass→fail | 36,070 | 26,078 | -28% | 1 | 1 | 0% | 3,028 | 5,155 | +70% | 0 | 0 | — |
case-01 | pass→pass | 41,802 | 29,853 | -29% | 1 | 1 | 0% | 6,695 | 5,289 | -21% | 0 | 0 | — |
case-03 | pass→fail | 37,294 | 53,750 | +44% | 1 | 1 | 0% | 5,891 | 8,560 | +45% | 0 | 0 | — |
case-04 | pass→pass | 24,179 | 31,365 | +30% | 1 | 1 | 0% | 2,907 | 3,118 | +7% | 0 | 0 | — |
case-05 | fail→pass | 51,098 | 58,456 | +14% | 1 | 1 | 0% | 5,318 | 6,066 | +14% | 0 | 0 | — |
case-06 | fail→fail | 22,974 | 29,497 | +28% | 1 | 1 | 0% | 3,454 | 4,190 | +21% | 0 | 0 | — |
case-07 | fail→fail | 12,674 | 29,133 | +130% | 1 | 1 | 0% | 479 | 1,975 | +312% | 0 | 0 | — |
case-08 | fail→fail | 39,468 | 42,720 | +8% | 1 | 1 | 0% | 6,179 | 4,742 | -23% | 0 | 0 | — |
case-09 | fail→fail | 41,879 | 40,894 | -2% | 1 | 1 | 0% | 3,055 | 2,665 | -13% | 0 | 0 | — |
case-10 | fail→fail | 44,681 | 45,716 | +2% | 1 | 1 | 0% | 2,848 | 3,618 | +27% | 0 | 0 | — |
case-11 | fail→fail | 19,818 | 27,306 | +38% | 1 | 1 | 0% | 2,751 | 3,954 | +44% | 0 | 0 | — |
case-12 | fail→fail | 16,816 | 16,694 | -1% | 1 | 1 | 0% | 1,860 | 3,717 | +100% | 0 | 0 | — |
case-13 | fail→fail | 27,528 | 21,448 | -22% | 1 | 1 | 0% | 3,983 | 3,556 | -11% | 0 | 0 | — |
case-14 | fail→pass | 34,452 | 21,535 | -37% | 1 | 1 | 0% | 4,517 | 4,318 | -4% | 0 | 0 | — |
case-15 | fail→pass | 18,834 | 20,408 | +8% | 1 | 1 | 0% | 2,245 | 4,517 | +101% | 0 | 0 | — |
case-16 | fail→fail | 19,963 | 15,545 | -22% | 1 | 1 | 0% | 3,053 | 3,412 | +12% | 0 | 0 | — |
case-17 | fail→fail | 15,517 | 20,015 | +29% | 1 | 1 | 0% | 2,650 | 3,196 | +21% | 0 | 0 | — |
case-18 | fail→fail | 20,734 | 14,723 | -29% | 1 | 1 | 0% | 2,579 | 2,068 | -20% | 0 | 0 | — |
case-19 | fail→fail | 22,285 | 30,385 | +36% | 1 | 1 | 0% | 2,808 | 5,992 | +113% | 0 | 0 | — |
case-20 | fail→fail | 23,415 | 23,039 | -2% | 1 | 1 | 0% | 2,950 | 4,685 | +59% | 0 | 0 | — |
case-21 | fail→fail | 19,800 | 25,216 | +27% | 1 | 1 | 0% | 2,558 | 4,209 | +65% | 0 | 0 | — |
case-22 | fail→pass | 12,039 | 28,239 | +135% | 1 | 1 | 0% | 2,247 | 4,690 | +109% | 0 | 0 | — |
case-23 | fail→pass | 24,935 | 25,362 | +2% | 1 | 1 | 0% | 3,380 | 4,037 | +19% | 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. 23 cases were attempted. The headline lift of +13 percentage points is the difference between those two pass rates over the 23 comparable cases. 2 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.