Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Feasibility Assessment Campaign — evaluate whether selected candidates can actually be implemented using TRL, NASSS, Stage-Gate, TRIZ, TOC, and parametric estimation methods.
.claude/skills/yogsoth-ai-feasibility-assessment/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-11 | ✗→✓ | ▲ Improved | 66% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 76% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 334% | 0% |
| case-17 | ✗→✓ | ▲ Improved | 60% | 0% |
| case-20 | ✓→✗ | ▼ Worse | -55% | 0% |
Evaluate whether selected research candidates can actually be implemented. This campaign applies Technology Readiness Levels (TRL), NASSS complexity framework, Stage-Gate processes, TRIZ contradiction analysis, Theory of Constraints (TOC), and parametric estimation to determine real-world viability before committing resources.
| Signal | Strategy | |--------|----------| | assess readiness level / maturity / TRL | maturity-diagnosis | | identify blockers / constraints / showstoppers | constraint-identification | | estimate resources / budget / timeline | resource-envelope-estimation | | compare feasibility across candidates | comparative-feasibility-ranking | | design maturation path / roadmap to readiness | maturation-pathway-design |
| Strategy | Description | |----------|-------------| | maturity-diagnosis | Assess current readiness using TRL 9-level, NASSS 7-dimension, and Innovation Readiness Level frameworks | | constraint-identification | Find blockers using TOC, TRIZ contradiction analysis, and Pre-mortem techniques | | resource-envelope-estimation | Estimate resources using parametric, analogous, and three-point (PERT) estimation | | comparative-feasibility-ranking | Compare candidates using multi-dimensional radar and weighted feasibility index | | maturation-pathway-design | Design path to readiness using Stage-Gate, Technology Roadmapping, and milestone planning |
| Tactic | Description | |--------|-------------| | multi-dimensional-readiness-scan | Assess each dimension, synthesize radar, identify bottlenecks | | constraint-drilling | Identify constraints, classify, assess removability, design removal path | | staged-gate-evaluation | Define gate criteria, evaluate at each gate, render go/kill/recycle decision |
| SOP | Description | |-----|-------------| | dimension-assessment | Score a single readiness dimension with evidence and gap analysis | | radar-synthesis | Synthesize dimension scores into radar chart data and overall readiness | | bottleneck-identification | Identify bottlenecks from radar data with severity ranking | | constraint-identification-sop | Identify constraints for a candidate in context | | constraint-classification | Classify constraints into hard, soft, and assumptions | | removability-assessment | Assess removability of a constraint with effort estimate | | removal-path | Design removal steps with timeline and resource needs | | gate-criteria-definition | Define gate criteria and pass thresholds for a stage | | gate-judgment | Render GO/KILL/RECYCLE verdict with evidence | | feasibility-synthesis | Synthesize all assessments into feasibility matrix and recommendation |
| Metric | Target | |--------|--------| | Dimensions assessed | >= 5 (technical, market, regulatory, resource, organizational) | | Blockers identified | >= 3 per candidate | | Estimate precision | from +/-30% to +/-10% through iteration | | Gates evaluated | >= 3 stage gates |
vault_search — find prior feasibility assessments and readiness datavault_query_graph — traverse relationships between candidates and constraintsvault_add_edge — link feasibility findings to candidatessemantic-scholar — retrieve technical maturity evidence from literatureState is maintained in the campaign ledger with keys:
candidates[] — items under feasibility assessmentdimension_scores{} — readiness scores per dimension per candidateconstraints{} — identified constraints per candidategate_verdicts{} — stage-gate decisionsfeasibility_matrix — final comparative matrix<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| Strategy | When to use | | --- | --- | | comparative-feasibility-ranking | Compare feasibility across multiple candidates using multi-dimensional radar and weighted feasibility index. | | constraint-identification | Find blockers and showstoppers using TOC, TRIZ contradiction analysis, and Pre-mortem techniques. | | maturation-pathway-design | Design path to readiness using Stage-Gate, Technology Roadmapping, and milestone planning methods. | | maturity-diagnosis | Assess current readiness of candidates using TRL 9-level, NASSS 7-dimension, and Innovation Readiness Level frameworks. | | resource-envelope-estimation | Estimate resources, budget, and timeline using parametric, analogous, and three-point (PERT) estimation methods. |
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use | | --- | --- | | context-checkpoint | Append research process and results to the current Phase's context file. Covers both process and results with genuine substance. Use this skill at plan-designated checkpoint points — typically after each strategy completes or at key decision nodes within a research Phase. | | context-init | Create a new context file for a research Phase. Called once at Phase start to initialize the file that subsequent context-checkpoint calls will append to. Use this skill whenever a new research Phase begins and a fresh context file is needed. | | convergence-paper-research | Full-text deep reading of methodology papers — complete understanding of algorithms, proofs, and implementation details. | | convergence-paper-search | Paper AI summary reading — deeper understanding of specific methodology papers without full-text commitment. | | convergence-saturation-detection | Determines when to stop iterating — coverage threshold met or marginal returns diminishing. Shared across all campaigns. |
<!-- 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→fail | 20,436 | 45,160 | +121% | 1 | 1 | 0% | 3,384 | 1,538 | -55% | 0 | 0 | — |
case-02 | fail→fail | 31,257 | 8,397 | -73% | 1 | 1 | 0% | 4,863 | 1,740 | -64% | 0 | 0 | — |
case-03 | fail→fail | 24,019 | 10,350 | -57% | 1 | 1 | 0% | 3,830 | 1,836 | -52% | 0 | 0 | — |
case-04 | fail→fail | 32,759 | 7,427 | -77% | 1 | 1 | 0% | 5,216 | 1,605 | -69% | 0 | 0 | — |
case-05 | fail→fail | 21,302 | 10,625 | -50% | 1 | 1 | 0% | 3,202 | 1,680 | -48% | 0 | 0 | — |
case-06 | fail→fail | 17,524 | 8,322 | -53% | 1 | 1 | 0% | 2,909 | 1,542 | -47% | 0 | 0 | — |
case-07 | pass→pass | 16,448 | 32,412 | +97% | 1 | 1 | 0% | 2,791 | 5,912 | +112% | 0 | 0 | — |
case-08 | fail→fail | 18,822 | 26,717 | +42% | 1 | 1 | 0% | 2,986 | 5,612 | +88% | 0 | 0 | — |
case-09 | fail→fail | 25,818 | 7,246 | -72% | 1 | 1 | 0% | 3,748 | 1,641 | -56% | 0 | 0 | — |
case-10 | pass→pass | 20,858 | 36,930 | +77% | 1 | 1 | 0% | 3,320 | 7,374 | +122% | 0 | 0 | — |
case-11 | fail→pass | 19,263 | 21,501 | +12% | 1 | 1 | 0% | 3,204 | 5,325 | +66% | 0 | 0 | — |
case-12 | fail→fail | 16,696 | 20,283 | +21% | 1 | 1 | 0% | 2,569 | 4,396 | +71% | 0 | 0 | — |
case-13 | pass→pass | 19,426 | 18,008 | -7% | 1 | 1 | 0% | 3,005 | 4,070 | +35% | 0 | 0 | — |
case-14 | fail→pass | 17,164 | 22,162 | +29% | 1 | 1 | 0% | 2,636 | 4,648 | +76% | 0 | 0 | — |
case-15 | fail→fail | 20,227 | 10,752 | -47% | 1 | 1 | 0% | 2,810 | 1,789 | -36% | 0 | 0 | — |
case-16 | fail→pass | 6,161 | 18,210 | +196% | 1 | 1 | 0% | 977 | 4,238 | +334% | 0 | 0 | — |
case-17 | fail→pass | 18,212 | 25,136 | +38% | 1 | 1 | 0% | 3,081 | 4,931 | +60% | 0 | 0 | — |
case-18 | fail→fail | 19,963 | 30,503 | +53% | 1 | 1 | 0% | 3,134 | 6,464 | +106% | 0 | 0 | — |
case-19 | pass→pass | 15,063 | 24,804 | +65% | 1 | 1 | 0% | 2,408 | 5,507 | +129% | 0 | 0 | — |
case-20 | pass→fail | 31,304 | 13,414 | -57% | 1 | 1 | 0% | 6,177 | 2,763 | -55% | 0 | 0 | — |
case-21 | pass→fail | 30,239 | 31,288 | +3% | 1 | 1 | 0% | 6,173 | 7,375 | +19% | 0 | 0 | — |
case-22 | pass→pass | 19,757 | 27,258 | +38% | 1 | 1 | 0% | 2,960 | 5,275 | +78% | 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 13 counted toward the lift figure. The other 9 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 +9 percentage points is the difference between those two pass rates over the 13 comparable cases. 6 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.