Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Design path to readiness using Stage-Gate, Technology Roadmapping, and milestone planning methods.
.claude/skills/yogsoth-ai-maturation-pathway-design/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-16 | ✗→✓ | ▲ Improved | 14% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -43% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -45% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -32% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -10% | 0% |
Purpose: Given a candidate that is not yet ready, design a concrete pathway to bring it to implementation readiness. Uses Stage-Gate processes to define decision points, Technology Roadmapping to sequence development activities, and milestone planning to create actionable checkpoints.
When to use:
| Metric | Target | |--------|--------| | Stage gates defined | >= 3 | | Milestones per stage | >= 2 | | Resource estimates per stage | 1 per stage |
| Key | Type | Description | |-----|------|-------------| | candidate | object | The candidate needing maturation | | current_readiness | object | Starting maturity profile | | target_readiness | object | Required maturity for implementation | | stages] | array | Defined maturation stages | | gates] | array | Decision gates between stages | | milestones] | array | Checkpoints within stages | | roadmap | object | Complete maturation roadmap |
| Tactic | When | |--------|------| | staged-gate-evaluation | To define and evaluate gates along the maturation path | | multi-dimensional-readiness-scan | To assess readiness at each stage |
| SOP | Purpose | |-----|---------| | gate-criteria-definition | Define criteria for each gate | | gate-judgment | Evaluate readiness at each gate | | dimension-assessment | Assess dimension readiness at checkpoints | | feasibility-synthesis | Synthesize pathway into overall feasibility view |
yamlmaturation_pathway: candidate: <name> current_readiness: <overall score> target_readiness: <required score> gap_dimensions: [{dimension, current, target, gap}] stages: - stage: 1 name: <stage name> objective: <what this stage achieves> milestones: [{name, criteria, target_date}] resources: {time, cost, personnel} gate: criteria: [...] pass_threshold: <condition> total_timeline: <duration> total_cost: <estimate> critical_path: [<stage dependencies>] risk_factors: [{risk, mitigation, stage_affected}]
<!-- 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. | | staged-gate-evaluation | Define gate criteria for each stage, evaluate candidates at each gate, and render go/kill/recycle decisions with evidence. |
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use | | --- | --- | | dimension-assessment | Score a single readiness dimension for a candidate with evidence and gap analysis. | | feasibility-synthesis | Synthesize all assessments into a feasibility matrix, recommendation, and risk summary. |
<!-- 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-16 | fail→pass | 36,737 | 28,400 | -23% | 1 | 1 | 0% | 5,260 | 6,010 | +14% | 0 | 0 | — |
case-01 | pass→fail | 22,978 | 46,782 | +104% | 1 | 1 | 0% | 2,794 | 6,153 | +120% | 0 | 0 | — |
case-02 | pass→fail | 18,205 | 26,201 | +44% | 1 | 1 | 0% | 2,786 | 5,289 | +90% | 0 | 0 | — |
case-03 | pass→fail | 5,809 | 41,508 | +615% | 1 | 1 | 0% | 843 | 7,532 | +793% | 0 | 0 | — |
case-04 | fail→pass | 47,962 | 22,526 | -53% | 1 | 1 | 0% | 7,188 | 4,125 | -43% | 0 | 0 | — |
case-05 | fail→pass | 45,012 | 20,023 | -56% | 1 | 1 | 0% | 8,289 | 4,542 | -45% | 0 | 0 | — |
case-06 | fail→pass | 52,251 | 31,032 | -41% | 1 | 1 | 0% | 8,290 | 5,675 | -32% | 0 | 0 | — |
case-07 | fail→pass | 68,781 | 37,103 | -46% | 1 | 1 | 0% | 7,841 | 7,036 | -10% | 0 | 0 | — |
case-08 | fail→pass | 46,652 | 32,706 | -30% | 1 | 1 | 0% | 8,267 | 6,289 | -24% | 0 | 0 | — |
case-09 | fail→pass | 54,053 | 64,660 | +20% | 1 | 1 | 0% | 4,626 | 6,266 | +35% | 0 | 0 | — |
case-10 | fail→pass | 64,838 | 41,481 | -36% | 1 | 1 | 0% | 5,649 | 7,338 | +30% | 0 | 0 | — |
case-11 | fail→pass | 39,721 | 28,031 | -29% | 1 | 1 | 0% | 7,143 | 6,020 | -16% | 0 | 0 | — |
case-12 | fail→pass | 42,532 | 44,189 | +4% | 1 | 1 | 0% | 6,681 | 5,797 | -13% | 0 | 0 | — |
case-13 | fail→pass | 29,738 | 42,478 | +43% | 1 | 1 | 0% | 5,358 | 7,713 | +44% | 0 | 0 | — |
case-14 | fail→pass | 41,330 | 33,302 | -19% | 1 | 1 | 0% | 6,387 | 4,529 | -29% | 0 | 0 | — |
case-15 | fail→pass | 44,051 | 19,486 | -56% | 1 | 1 | 0% | 7,148 | 4,598 | -36% | 0 | 0 | — |
case-17 | fail→pass | 53,134 | 29,892 | -44% | 1 | 1 | 0% | 8,066 | 5,434 | -33% | 0 | 0 | — |
case-18 | fail→pass | 26,038 | 34,754 | +33% | 1 | 1 | 0% | 4,467 | 7,992 | +79% | 0 | 0 | — |
case-19 | fail→fail | 35,802 | 18,122 | -49% | 1 | 1 | 0% | 6,050 | 4,007 | -34% | 0 | 0 | — |
case-20 | fail→pass | 43,399 | 21,203 | -51% | 1 | 1 | 0% | 7,460 | 4,798 | -36% | 0 | 0 | — |
case-21 | fail→fail | 43,890 | 75,362 | +72% | 1 | 1 | 0% | 8,258 | 5,536 | -33% | 0 | 0 | — |
case-22 | fail→fail | 37,572 | 23,983 | -36% | 1 | 1 | 0% | 6,492 | 5,094 | -22% | 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 +59 percentage points is the difference between those two pass rates over the 22 comparable cases. 3 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.