Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Assess current readiness of candidates using TRL 9-level, NASSS 7-dimension, and Innovation Readiness Level frameworks.
.claude/skills/yogsoth-ai-maturity-diagnosis/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -9% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -29% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -18% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -32% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -29% | 0% |
Purpose: Determine how ready a candidate is for implementation by scoring it against established maturity frameworks. Produces a multi-dimensional readiness profile that reveals which aspects are mature and which need development.
When to use:
| Metric | Target | |--------|--------| | Dimensions scored | >= 5 | | Evidence items per dimension | >= 2 | | Bottlenecks identified | >= 1 |
| Key | Type | Description | |-----|------|-------------| | candidate | object | The candidate under assessment | | dimensions] | array | Dimensions being assessed | | scores{} | map | Dimension -> score mapping | | radar_data | object | Synthesized radar chart data | | bottlenecks] | array | Identified bottleneck dimensions |
| Tactic | When | |--------|------| | multi-dimensional-readiness-scan | Default — full readiness assessment across all dimensions |
| SOP | Purpose | |-----|---------| | dimension-assessment | Score a single dimension | | radar-synthesis | Combine scores into radar | | bottleneck-identification | Find limiting dimensions |
dimension-assessment for each dimension — can run in parallelradar-synthesis to produce the composite viewbottleneck-identification on the radar data to surface limiting factorsyamlmaturity_diagnosis: candidate: <name> overall_readiness: <1-9 TRL scale> dimension_scores: technical: {score: N, evidence: [...], gaps: [...]} market: {score: N, evidence: [...], gaps: [...]} regulatory: {score: N, evidence: [...], gaps: [...]} resource: {score: N, evidence: [...], gaps: [...]} organizational: {score: N, evidence: [...], gaps: [...]} bottlenecks: [{dimension, severity, reason}] radar_summary: <text>
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| Tactic | When to use | | --- | --- | | multi-dimensional-readiness-scan | Assess readiness across multiple dimensions, synthesize into radar visualization, and identify bottleneck dimensions. |
<!-- 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 | 28,278 | 17,711 | -37% | 1 | 1 | 0% | 3,101 | 2,836 | -9% | 0 | 0 | — |
case-02 | fail→fail | 37,239 | 14,672 | -61% | 1 | 1 | 0% | 5,549 | 3,185 | -43% | 0 | 0 | — |
case-03 | fail→pass | 36,794 | 23,426 | -36% | 1 | 1 | 0% | 5,562 | 3,943 | -29% | 0 | 0 | — |
case-04 | pass→pass | 19,862 | 39,860 | +101% | 1 | 1 | 0% | 3,857 | 7,501 | +94% | 0 | 0 | — |
case-05 | pass→fail | 20,294 | 22,477 | +11% | 1 | 1 | 0% | 3,434 | 3,785 | +10% | 0 | 0 | — |
case-06 | pass→pass | 28,832 | 47,779 | +66% | 1 | 1 | 0% | 3,964 | 8,019 | +102% | 0 | 0 | — |
case-07 | fail→pass | 29,019 | 32,052 | +10% | 1 | 1 | 0% | 4,681 | 3,828 | -18% | 0 | 0 | — |
case-08 | fail→pass | 29,073 | 18,038 | -38% | 1 | 1 | 0% | 4,205 | 2,878 | -32% | 0 | 0 | — |
case-09 | fail→pass | 32,592 | 16,063 | -51% | 1 | 1 | 0% | 4,489 | 3,197 | -29% | 0 | 0 | — |
case-10 | fail→fail | 34,725 | 19,123 | -45% | 1 | 1 | 0% | 5,298 | 3,060 | -42% | 0 | 0 | — |
case-11 | fail→pass | 23,365 | 24,706 | +6% | 1 | 1 | 0% | 3,674 | 2,792 | -24% | 0 | 0 | — |
case-12 | fail→pass | 28,443 | 21,607 | -24% | 1 | 1 | 0% | 3,862 | 3,536 | -8% | 0 | 0 | — |
case-13 | fail→pass | 42,047 | 15,946 | -62% | 1 | 1 | 0% | 6,213 | 3,371 | -46% | 0 | 0 | — |
case-14 | fail→fail | 34,185 | 16,470 | -52% | 1 | 1 | 0% | 5,003 | 3,040 | -39% | 0 | 0 | — |
case-15 | fail→pass | 36,977 | 22,758 | -38% | 1 | 1 | 0% | 5,136 | 3,355 | -35% | 0 | 0 | — |
case-16 | fail→pass | 35,125 | 21,600 | -39% | 1 | 1 | 0% | 4,179 | 2,834 | -32% | 0 | 0 | — |
case-17 | fail→pass | 27,313 | 15,734 | -42% | 1 | 1 | 0% | 4,477 | 3,161 | -29% | 0 | 0 | — |
case-18 | fail→pass | 38,415 | 24,201 | -37% | 1 | 1 | 0% | 6,245 | 3,982 | -36% | 0 | 0 | — |
case-19 | fail→pass | 27,136 | 19,728 | -27% | 1 | 1 | 0% | 4,807 | 4,060 | -16% | 0 | 0 | — |
case-20 | fail→pass | 30,664 | 24,560 | -20% | 1 | 1 | 0% | 4,966 | 4,738 | -5% | 0 | 0 | — |
case-21 | fail→pass | 23,306 | 16,966 | -27% | 1 | 1 | 0% | 3,671 | 2,920 | -20% | 0 | 0 | — |
case-22 | fail→pass | 43,228 | 16,370 | -62% | 1 | 1 | 0% | 4,353 | 3,272 | -25% | 0 | 0 | — |
case-23 | fail→pass | 22,791 | 18,360 | -19% | 1 | 1 | 0% | 3,778 | 3,742 | -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. 23 cases were attempted. The headline lift of +70 percentage points is the difference between those two pass rates over the 23 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.