borghei/Claude-Skills / engineering/tech-stack-evaluator
tech-stack-evaluator
VerifiedEvaluate and compare technology stacks with TCO analysis, security assessment, and ecosystem health scoring. Use when comparing frameworks, calculating total cost of ownership, assessing migration paths, or analyzing ecosystem viability.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 9.1 KB |
| assets/expected_output_comparison.json | config | 3.6 KB |
| assets/sample_compare_evidenced.json | config | 2.1 KB |
| assets/sample_input_ecosystem.json | config | 894 B |
| assets/sample_input_migration.json | config | 629 B |
| assets/sample_input_security.json | config | 1.1 KB |
| assets/sample_input_structured.json | config | 1.1 KB |
| assets/sample_input_tco.json | config | 1.1 KB |
| assets/sample_input_text.json | config | 237 B |
| references/examples.md | markdown | 10.3 KB |
| references/metrics.md | markdown | 6.8 KB |
| references/tool-reference.md | markdown | 15.5 KB |
| references/usage-and-criteria.md | markdown | 4.4 KB |
| references/workflows.md | markdown | 8.4 KB |
| scripts/ecosystem_analyzer.py | script | 16.1 KB |
| scripts/evaluate.py | script | 8.7 KB |
| scripts/format_detector.py | script | 12.3 KB |
| scripts/migration_analyzer.py | script | 20.1 KB |
| scripts/report_generator.py | script | 15.5 KB |
| scripts/security_assessor.py | script | 17.3 KB |
| scripts/stack_comparator.py | script | 12.1 KB |
| scripts/tco_calculator.py | script | 15.8 KB |
references/usage-and-criteria.md
View on GitHub# Usage, Input Formats & Criteria
Read this when invoking the evaluator: example prompts, accepted input formats, analysis depth tiers, confidence scoring, troubleshooting, and success criteria.
## Quick Start
### Compare Two Technologies
```
Compare React vs Vue for a SaaS dashboard.
Priorities: developer productivity (40%), ecosystem (30%), performance (30%).
```
### Calculate TCO
```
Calculate 5-year TCO for Next.js on Vercel.
Team: 8 developers. Hosting: $2500/month. Growth: 40%/year.
```
### Assess Migration
```
Evaluate migrating from Angular.js to React.
Codebase: 50,000 lines, 200 components. Team: 6 developers.
```
## Input Formats
The evaluator accepts three input formats:
**Text** - Natural language queries
```
Compare PostgreSQL vs MongoDB for our e-commerce platform.
```
**YAML** - Structured input for automation
```yaml
comparison:
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"
}
```
## Analysis Types
### Quick Comparison (200-300 tokens)
- Weighted scores and recommendation
- Top 3 decision factors
- Confidence level
### Standard Analysis (500-800 tokens)
- Comparison matrix
- TCO overview
- Security summary
### Full Report (1200-1500 tokens)
- All metrics and calculations
- Migration analysis
- Detailed recommendations
## Confidence Levels
| Level | Score | Interpretation |
|-------|-------|----------------|
| High | 80-100% | Clear winner, strong data |
| Medium | 50-79% | Trade-offs present, moderate uncertainty |
| Low | < 50% | Close call, limited data |
## Troubleshooting
| Problem | Cause | Solution |
|---------|-------|----------|
| Weighted scores all return 50.0 | Technology data dictionaries missing `score` keys under each category | Ensure each category dict contains a `score` key on a 0-100 scale (e.g., `{"performance": {"score": 85}}`) |
| TCO projections look unrealistically low | Default cost parameters used when `operational_costs` or `initial_costs` are empty | Populate `monthly_hosting`, `annual_licensing`, `developer_hourly_rate`, and `maintenance_hours_per_dev_monthly` with real figures |
| Ecosystem health score stuck at 50 for npm | `npm_data` dict is empty or not provided | Pass npm metrics (`weekly_downloads`, `version`, `dependencies_count`, `days_since_last_publish`); 50 is the neutral fallback when npm data is absent |
| Security compliance returns "Unknown standard" | Unsupported standard name passed to `assess_compliance()` | Use one of the supported keys: `GDPR`, `SOC2`, `HIPAA`, `PCI_DSS` (case-sensitive) |
| Migration complexity always shows moderate | `architecture_change_level` defaults to `moderate` when not specified | Set `architecture_change_level` explicitly to `minimal`, `moderate`, `significant`, or `complete` in `codebase_stats` |
| Report renders ASCII tables instead of markdown | `ReportGenerator` auto-detects CLI context when stdout is a TTY | Pass `output_context='desktop'` to force rich markdown output |
| Format detector misclassifies YAML as text | Fewer than 50% of lines match YAML key-value patterns | Ensure input uses standard YAML syntax with `key: value` pairs and proper indentation |
## Success Criteria
- **TCO variance under 15%**: Calculated TCO deviates less than 15% from actual costs when validated against real-world spending data over the projection period.
- **Security score above 80/100**: Technologies recommended for production use achieve a minimum overall security score of 80, corresponding to grade B or higher.
- **Ecosystem health score above 65/100**: Recommended technologies demonstrate viable long-term ecosystem health with a risk level no worse than "Low-Medium."
- **Migration effort estimate within 20%**: Person-hours and timeline estimates land within 20% of actual migration effort when measured post-completion.
- **Comparison confidence above 70%**: Final technology recommendations carry a confidence score of 70% or higher, indicating a meaningful score gap between top candidates.
- **Compliance readiness at "Mostly Ready" or above**: Technologies targeting regulated environments achieve at least 70% feature coverage against required compliance standards (GDPR, SOC2, HIPAA, PCI-DSS).
- **Report generation under 5 seconds**: All report types (executive summary, full report) render within 5 seconds for evaluations comparing up to 5 technologies.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |