Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Technology stack evaluation and comparison with TCO analysis, security assessment, and ecosystem health scoring. Use when comparing frameworks, evaluating technology stacks, calculating total cost of ownership, assessing migration paths, or analyzing ecosystem viability.
.claude/skills/alirezarezvani-tech-stack-evaluator/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 3% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 24% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 74% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -30% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 16% | 0% |
Evaluate and compare technologies, frameworks, and cloud providers with data-driven analysis and actionable recommendations.
| Capability | Description | |------------|-------------| | Technology Comparison | Compare frameworks and libraries with weighted scoring | | TCO Analysis | Calculate 5-year total cost including hidden costs | | Ecosystem Health | Assess GitHub metrics, npm adoption, community strength | | Security Assessment | Evaluate vulnerabilities and compliance readiness | | Migration Analysis | Estimate effort, risks, and timeline for migrations | | Cloud Comparison | Compare AWS, Azure, GCP for specific workloads |
Compare React vs Vue for a SaaS dashboard.
Priorities: developer productivity (40%), ecosystem (30%), performance (30%).Calculate 5-year TCO for Next.js on Vercel.
Team: 8 developers. Hosting: $2500/month. Growth: 40%/year.Evaluate migrating from Angular.js to React.
Codebase: 50,000 lines, 200 components. Team: 6 developers.The evaluator accepts three input formats:
Text - Natural language queries
Compare PostgreSQL vs MongoDB for our e-commerce platform.YAML - Structured input for automation
yamlcomparison: technologies: ["React", "Vue"] use_case: "SaaS dashboard" weights: ecosystem: 30 performance: 25 developer_experience: 45
JSON - Programmatic integration
json{ "technologies": ["React", "Vue"], "use_case": "SaaS dashboard" }
Compare technologies with customizable weighted criteria.
bashpython scripts/stack_comparator.py --help
Calculate total cost of ownership over multi-year projections.
bashpython scripts/tco_calculator.py --input assets/sample_input_tco.json
Analyze ecosystem health from GitHub, npm, and community metrics.
bashpython scripts/ecosystem_analyzer.py --technology react
Evaluate security posture and compliance readiness.
bashpython scripts/security_assessor.py --technology express --compliance soc2,gdpr
Estimate migration complexity, effort, and risks.
bashpython scripts/migration_analyzer.py --from angular-1.x --to react
| Document | Content | |----------|---------| | references/metrics.md | Detailed scoring algorithms and calculation formulas | | references/examples.md | Input/output examples for all analysis types | | references/workflows.md | Step-by-step evaluation workflows |
| Level | Score | Interpretation | |-------|-------|----------------| | High | 80-100% | Clear winner, strong data | | Medium | 50-79% | Trade-offs present, moderate uncertainty | | Low | < 50% | Close call, limited data |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 19,660 | 15,371 | -22% | 1 | 1 | 0% | 3,711 | 3,833 | +3% | 0 | 0 | — |
case-02 | fail→pass | 20,970 | 19,682 | -6% | 1 | 1 | 0% | 3,579 | 4,447 | +24% | 0 | 0 | — |
case-03 | pass→pass | 11,250 | 33,360 | +197% | 1 | 1 | 0% | 1,766 | 2,092 | +18% | 0 | 0 | — |
case-04 | pass→pass | 20,900 | 15,550 | -26% | 1 | 1 | 0% | 3,579 | 3,779 | +6% | 0 | 0 | — |
case-05 | pass→fail | 12,411 | 9,923 | -20% | 1 | 1 | 0% | 1,851 | 2,612 | +41% | 0 | 0 | — |
case-06 | pass→pass | 17,777 | 23,560 | +33% | 1 | 1 | 0% | 2,839 | 4,683 | +65% | 0 | 0 | — |
case-07 | pass→pass | 17,230 | 16,865 | -2% | 1 | 1 | 0% | 2,823 | 4,126 | +46% | 0 | 0 | — |
case-08 | fail→pass | 12,276 | 15,278 | +24% | 1 | 1 | 0% | 1,944 | 3,381 | +74% | 0 | 0 | — |
case-09 | pass→pass | 15,700 | 15,269 | -3% | 1 | 1 | 0% | 2,445 | 3,748 | +53% | 0 | 0 | — |
case-10 | pass→pass | 11,948 | 3,535 | -70% | 1 | 1 | 0% | 2,661 | 1,577 | -41% | 0 | 0 | — |
case-11 | fail→pass | 15,028 | 5,398 | -64% | 1 | 1 | 0% | 2,957 | 2,077 | -30% | 0 | 0 | — |
case-12 | fail→pass | 11,401 | 6,908 | -39% | 1 | 1 | 0% | 2,009 | 2,338 | +16% | 0 | 0 | — |
case-13 | fail→pass | 15,483 | 15,721 | +2% | 1 | 1 | 0% | 2,465 | 4,038 | +64% | 0 | 0 | — |
case-14 | pass→pass | 25,109 | 22,675 | -10% | 1 | 1 | 0% | 4,664 | 5,011 | +7% | 0 | 0 | — |
case-15 | pass→pass | 9,131 | 2,262 | -75% | 1 | 1 | 0% | 1,664 | 1,397 | -16% | 0 | 0 | — |
case-16 | fail→pass | 5,647 | 2,450 | -57% | 1 | 1 | 0% | 997 | 1,468 | +47% | 0 | 0 | — |
case-17 | pass→pass | 6,825 | 2,202 | -68% | 1 | 1 | 0% | 1,133 | 1,358 | +20% | 0 | 0 | — |
case-18 | pass→pass | 16,682 | 18,922 | +13% | 1 | 1 | 0% | 3,168 | 4,544 | +43% | 0 | 0 | — |
case-19 | pass→pass | 15,129 | 16,254 | +7% | 1 | 1 | 0% | 2,481 | 3,894 | +57% | 0 | 0 | — |
case-20 | pass→pass | 13,961 | 17,256 | +24% | 1 | 1 | 0% | 2,561 | 3,968 | +55% | 0 | 0 | — |
case-21 | pass→pass | 12,062 | 16,990 | +41% | 1 | 1 | 0% | 2,133 | 4,032 | +89% | 0 | 0 | — |
case-22 | fail→fail | 12,203 | 2,076 | -83% | 1 | 1 | 0% | 2,114 | 1,397 | -34% | 0 | 0 | — |
case-23 | pass→pass | 16,099 | 17,658 | +10% | 1 | 1 | 0% | 2,694 | 4,173 | +55% | 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 +26 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.