jbvc/senior-architect
Comprehensive software architecture skill for designing scalable, maintainable systems using ReactJS, NextJS, NodeJS, Express, React Native, Swift, Kotlin, Flutter, Postgres, GraphQL, Go, Python. Includes architecture diagram generation, system design patterns, tech stack decision frameworks, and dependency analysis. Use when designing system architecture, making technical decisions, creating architecture diagrams, evaluating trade-offs, or defining integration patterns.
47
59%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
92%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong description that clearly articulates capabilities and provides explicit trigger guidance. Its main weakness is the breadth of technologies and scope, which could cause overlap with more specialized skills for individual frameworks or databases. The description would benefit from narrowing its scope or more clearly delineating its architectural focus versus implementation-level skills.
Suggestions
Consider narrowing the technology list or grouping them more concisely (e.g., 'modern web and mobile stacks') to reduce potential overlap with technology-specific skills.
Add a brief exclusion clause like 'Not for implementation-level coding tasks' to further distinguish from coding/development skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: architecture diagram generation, system design patterns, tech stack decision frameworks, dependency analysis. Also enumerates specific technologies (ReactJS, NextJS, NodeJS, etc.). | 3 / 3 |
Completeness | Clearly answers both 'what' (architecture diagram generation, system design patterns, tech stack decision frameworks, dependency analysis) and 'when' with an explicit 'Use when...' clause listing five trigger scenarios. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'system architecture', 'technical decisions', 'architecture diagrams', 'trade-offs', 'integration patterns', 'tech stack'. Also lists many specific technology names users might mention. | 3 / 3 |
Distinctiveness Conflict Risk | While the architecture focus is somewhat distinct, the extremely broad technology list (12+ technologies spanning frontend, backend, mobile, databases) and broad scope ('comprehensive software architecture') could overlap with coding skills, database skills, or individual framework-specific skills. | 2 / 3 |
Total | 11 / 12 Passed |
Implementation
7%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is a hollow template filled with generic platitudes rather than actionable architecture guidance. It references scripts and documentation files that don't exist, provides no concrete examples of architecture patterns, system design decisions, or tech stack trade-offs, and wastes significant token budget on truisms Claude already knows. The skill fails to deliver on its stated purpose of providing architecture design, decision frameworks, and dependency analysis capabilities.
Suggestions
Replace generic feature bullet points ('Automated scaffolding', 'Deep analysis') with concrete examples showing actual architecture patterns, e.g., a specific microservices vs monolith decision framework with criteria and trade-offs.
Provide real, executable code examples for at least one core capability—e.g., a concrete architecture diagram generation workflow with actual input/output, or a dependency analysis example with sample output.
Add a concrete decision-making workflow with validation checkpoints, e.g., 'Step 1: Identify requirements → Step 2: Evaluate patterns against criteria table → Step 3: Validate with checklist → Step 4: Document decision in ADR format'.
Either include the referenced bundle files (scripts/, references/) or remove references to them and inline the essential content directly in the skill.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with generic filler content that adds no value. Feature lists like 'Automated scaffolding', 'Best practices built-in', 'Deep analysis', 'Expert-level automation' are meaningless platitudes. The best practices section restates things Claude already knows ('Write clear code', 'Validate all inputs'). Most of this content is padding. | 1 / 3 |
Actionability | Despite referencing scripts, none of the commands are concrete or executable—the scripts don't exist (no bundle files provided), arguments are vague placeholders like '[options]' and '[arguments]', and there are zero real code examples showing actual architecture patterns, system design, or decision frameworks. The skill describes rather than instructs. | 1 / 3 |
Workflow Clarity | The 'Development Workflow' section lists generic steps (install deps, run checks, implement best practices) with no validation checkpoints, no feedback loops, and no specificity about what constitutes success or failure. For a skill involving system architecture decisions, there's no decision-making workflow, no trade-off evaluation process, and no verification steps. | 1 / 3 |
Progressive Disclosure | The structure attempts progressive disclosure by referencing external files (references/architecture_patterns.md, references/system_design_workflows.md, references/tech_decision_guide.md, scripts/), and references are one level deep. However, no bundle files exist to support these references, and the overview itself contains too much generic filler rather than useful summary content. | 2 / 3 |
Total | 5 / 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