tech-stack-evaluator
Comprehensive technology stack evaluation and comparison tool with TCO analysis, security assessment, and intelligent recommendations for engineering teams
Install with Tessl CLI
npx tessl i github:alirezarezvani/claude-code-skill-factory --skill tech-stack-evaluator47
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
32%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description identifies a clear domain (technology evaluation) and mentions specific analysis types (TCO, security), but relies on vague adjectives ('comprehensive', 'intelligent') rather than concrete actions. The critical weakness is the complete absence of trigger guidance telling Claude when to select this skill, which severely limits its utility in a multi-skill environment.
Suggestions
Add an explicit 'Use when...' clause with trigger phrases like 'compare technologies', 'evaluate frameworks', 'which database should I use', 'tech stack decision', or 'build vs buy'.
Replace vague adjectives ('comprehensive', 'intelligent') with specific capabilities like 'generates comparison matrices', 'calculates 3-year cost projections', or 'identifies security vulnerabilities in dependencies'.
Include natural user phrases that would trigger this skill, such as 'choosing between X and Y', 'technology recommendation', or 'stack review'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (technology stack evaluation) and lists some actions (TCO analysis, security assessment, recommendations), but uses somewhat vague terms like 'comprehensive' and 'intelligent' that are more marketing language than concrete capabilities. | 2 / 3 |
Completeness | Describes what the skill does but completely lacks a 'Use when...' clause or any explicit trigger guidance. Per rubric guidelines, missing explicit trigger guidance caps completeness at 2, and this has no 'when' component at all. | 1 / 3 |
Trigger Term Quality | Includes some relevant terms like 'technology stack', 'TCO analysis', 'security assessment', but missing common user phrases like 'compare frameworks', 'which tool should I use', 'tech decision', or 'stack comparison'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of TCO analysis and security assessment provides some distinctiveness, but 'technology stack evaluation' and 'recommendations for engineering teams' are broad enough to potentially overlap with architecture, security, or general decision-making skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill content is comprehensive but severely over-engineered for a SKILL.md file. It reads like product documentation rather than actionable instructions for Claude, explaining concepts Claude already understands (TCO components, compliance standards, what GitHub metrics mean). The lack of actual executable code or concrete implementation details, combined with references to scripts that aren't provided, makes this more of a capability description than an actionable skill.
Suggestions
Reduce content by 70-80% by removing explanations of concepts Claude knows (what TCO is, what GDPR compliance means, basic best practices) and focus only on project-specific implementation details
Provide actual executable code for at least one core script (e.g., stack_comparator.py) rather than just listing module names
Split detailed metrics definitions and calculation formulas into a separate REFERENCE.md file, keeping SKILL.md as a concise overview with clear navigation
Add explicit workflow steps with validation checkpoints for common use cases (e.g., 'Step 1: Gather inputs → Step 2: Run comparison → Step 3: Validate scores → Step 4: Generate report')
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~400+ lines with extensive explanations of concepts Claude already knows (what TCO is, what compliance standards mean, basic best practices). The document reads like comprehensive documentation rather than a lean skill file. | 1 / 3 |
Actionability | Provides example invocations and references scripts, but no actual executable code is shown. The scripts are listed but not provided, and examples are conversational prompts rather than concrete implementations or commands. | 2 / 3 |
Workflow Clarity | Lists capabilities and metrics comprehensively but lacks clear step-by-step workflows with validation checkpoints. The 'How to Use' section shows invocation examples but doesn't explain the actual process flow or verification steps. | 2 / 3 |
Progressive Disclosure | References multiple script modules but doesn't link to actual files. The document is monolithic with all content inline rather than appropriately split into overview + detailed reference files. No clear navigation to external documentation. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.