Skip to main content
ClaudeWave
Skill801 repo starsupdated 7mo ago

tech-stack-evaluator

The tech-stack-evaluator skill provides comprehensive analysis for comparing technologies, frameworks, and complete technology stacks through data-driven evaluation. It generates total cost of ownership calculations, security assessments, ecosystem health scoring, and migration path analysis to support engineering teams making technology decisions. Use this skill when evaluating alternative tools or frameworks for specific projects, assessing the viability of migrating from legacy systems, or comparing cloud providers and infrastructure options.

Install in Claude Code
Copy
git clone --depth 1 https://github.com/alirezarezvani/claude-code-skill-factory /tmp/tech-stack-evaluator && cp -r /tmp/tech-stack-evaluator/generated-skills/tech-stack-evaluator ~/.claude/skills/tech-stack-evaluator
Then start a new Claude Code session; the skill loads automatically.

SKILL.md

# Technology Stack Evaluator

A comprehensive evaluation framework for comparing technologies, frameworks, cloud providers, and complete technology stacks. Provides data-driven recommendations with TCO analysis, security assessment, ecosystem health scoring, and migration path analysis.

## Capabilities

This skill provides eight comprehensive evaluation capabilities:

- **Technology Comparison**: Head-to-head comparisons of frameworks, languages, and tools (React vs Vue, PostgreSQL vs MongoDB, Node.js vs Python)
- **Stack Evaluation**: Assess complete technology stacks for specific use cases (real-time collaboration, API-heavy SaaS, data-intensive platforms)
- **Maturity & Ecosystem Analysis**: Evaluate community health, maintenance status, long-term viability, and ecosystem strength
- **Total Cost of Ownership (TCO)**: Calculate comprehensive costs including licensing, hosting, developer productivity, and scaling
- **Security & Compliance**: Analyze vulnerabilities, compliance readiness (GDPR, SOC2, HIPAA), and security posture
- **Migration Path Analysis**: Assess migration complexity, risks, timelines, and strategies from legacy to modern stacks
- **Cloud Provider Comparison**: Compare AWS vs Azure vs GCP for specific workloads with cost and feature analysis
- **Decision Reports**: Generate comprehensive decision matrices with pros/cons, confidence scores, and actionable recommendations

## Input Requirements

### Flexible Input Formats (Automatic Detection)

The skill automatically detects and processes multiple input formats:

**Text/Conversational**:
```
"Compare React vs Vue for building a SaaS dashboard"
"Evaluate technology stack for real-time collaboration platform"
"Should we migrate from MongoDB to PostgreSQL?"
```

**Structured (YAML)**:
```yaml
comparison:
  technologies:
    - name: "React"
    - name: "Vue"
  use_case: "SaaS dashboard"
  priorities:
    - "Developer productivity"
    - "Ecosystem maturity"
    - "Performance"
```

**Structured (JSON)**:
```json
{
  "comparison": {
    "technologies": ["React", "Vue"],
    "use_case": "SaaS dashboard",
    "priorities": ["Developer productivity", "Ecosystem maturity"]
  }
}
```

**URLs for Ecosystem Analysis**:
- GitHub repository URLs (for health scoring)
- npm package URLs (for download statistics)
- Technology documentation URLs (for feature extraction)

### Analysis Scope Selection

Users can select which analyses to run:
- **Quick Comparison**: Basic scoring and comparison (200-300 tokens)
- **Standard Analysis**: Scoring + TCO + Security (500-800 tokens)
- **Comprehensive Report**: All analyses including migration paths (1200-1500 tokens)
- **Custom**: User selects specific sections (modular)

## Output Formats

### Context-Aware Output

The skill automatically adapts output based on environment:

**Claude Desktop (Rich Markdown)**:
- Formatted tables with color indicators
- Expandable sections for detailed analysis
- Visual decision matrices
- Charts and graphs (when appropriate)

**CLI/Terminal (Terminal-Friendly)**:
- Plain text tables with ASCII borders
- Compact formatting
- Clear section headers
- Copy-paste friendly code blocks

### Progressive Disclosure Structure

**Executive Summary (200-300 tokens)**:
- Recommendation summary
- Top 3 pros and cons
- Confidence level (High/Medium/Low)
- Key decision factors

**Detailed Breakdown (on-demand)**:
- Complete scoring matrices
- Detailed TCO calculations
- Full security analysis
- Migration complexity assessment
- All supporting data and calculations

### Report Sections (User-Selectable)

Users choose which sections to include:

1. **Scoring & Comparison Matrix**
   - Weighted decision scores
   - Head-to-head comparison tables
   - Strengths and weaknesses

2. **Financial Analysis**
   - TCO breakdown (5-year projection)
   - ROI analysis
   - Cost per user/request metrics
   - Hidden cost identification

3. **Ecosystem Health**
   - Community size and activity
   - GitHub stars, npm downloads
   - Release frequency and maintenance
   - Issue response times
   - Viability assessment

4. **Security & Compliance**
   - Vulnerability count (CVE database)
   - Security patch frequency
   - Compliance readiness (GDPR, SOC2, HIPAA)
   - Security scoring

5. **Migration Analysis** (when applicable)
   - Migration complexity scoring
   - Code change estimates
   - Data migration requirements
   - Downtime assessment
   - Risk mitigation strategies

6. **Performance Benchmarks**
   - Throughput/latency comparisons
   - Resource usage analysis
   - Scalability characteristics

## How to Use

### Basic Invocations

**Quick Comparison**:
```
"Compare React vs Vue for our SaaS dashboard project"
"PostgreSQL vs MongoDB for our application"
```

**Stack Evaluation**:
```
"Evaluate technology stack for real-time collaboration platform:
Node.js, WebSockets, Redis, PostgreSQL"
```

**TCO Analysis**:
```
"Calculate total cost of ownership for AWS vs Azure for our workload:
- 50 EC2/VM instances
- 10TB storage
- High bandwidth requirements"
```

**Security Assessment**:
```
"Analyze security posture of our current stack:
Express.js, MongoDB, JWT authentication.
Need SOC2 compliance."
```

**Migration Path**:
```
"Assess migration from Angular.js (1.x) to React.
Application has 50,000 lines of code, 200 components."
```

### Advanced Invocations

**Custom Analysis Sections**:
```
"Compare Next.js vs Nuxt.js.
Include: Ecosystem health, TCO, and performance benchmarks.
Skip: Migration analysis, compliance."
```

**Weighted Decision Criteria**:
```
"Compare cloud providers for ML workloads.
Priorities (weighted):
- GPU availability (40%)
- Cost (30%)
- Ecosystem (20%)
- Support (10%)"
```

**Multi-Technology Comparison**:
```
"Compare: React, Vue, Svelte, Angular for enterprise SaaS.
Use case: Large team (20+ developers), complex state management.
Generate comprehensive decision matrix."
```

## Scripts

### Core Modules

- **`stack_comparator.py`**: Main comparison engine with weig
agents-guideSubagent

Interactive guide for building custom Claude Code Agents and subagents. Asks straightforward questions, generates enhanced YAML frontmatter with tools/model/color/field/expertise, creates agent .md files, validates format, and helps install to .claude/agents/ or ~/.claude/agents/. Use when user wants to build workflow specialist agents.

factory-guideSubagent

Main navigation guide for Claude Code Skills Factory. Use when user wants to build custom Skills, Prompts, or Agents. Orchestrates and delegates to specialized guide agents.

hooks-guideSubagent

Interactive guide for building custom Claude Code hooks. Asks straightforward questions, uses hook-factory skill, generates complete hooks with validation, and provides installation instructions.

prompts-guideSubagent

Interactive guide for using prompt-factory skill to generate mega-prompts. Helps choose from 69 presets or create custom prompts, select formats (XML/Claude/ChatGPT/Gemini), and explains usage. Use when user wants to generate production-ready prompts for any LLM.

skills-guideSubagent

Interactive guide for building custom Claude Skills. Asks straightforward questions, uses SKILLS_FACTORY_PROMPT template, generates complete skill files, validates format, creates ZIP, and helps install. Use when user wants to build multi-file skill capabilities.

ci-guardSlash Command

Trigger the Commit & Branch Guard workflow on demand.

cmSlash Command

Stage working tree changes and create a Conventional Commit (no push).

cpSlash Command

Stage, commit, and push the current branch following git governance rules.