design-smell-detector
Identify design quality issues in code including high coupling, low cohesion, God classes, long methods, and other code smells. Use when: (1) Reviewing code architecture and design quality, (2) Identifying refactoring opportunities, (3) Detecting God classes or classes with too many responsibilities, (4) Finding high coupling or low cohesion issues, (5) Analyzing code maintainability and technical debt. Detects coupling smells, cohesion problems, complexity issues, size violations, and encapsulation problems with actionable refactoring suggestions.
90
92%
Does it follow best practices?
Impact
79%
1.05xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
100%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 an excellent skill description that hits all the marks. It provides specific concrete capabilities, uses natural developer terminology as trigger terms, explicitly states when to use it with a numbered list, and carves out a distinct niche in design-level code quality analysis that won't conflict with general code review skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'high coupling, low cohesion, God classes, long methods, code smells', 'coupling smells, cohesion problems, complexity issues, size violations, encapsulation problems' with 'actionable refactoring suggestions'. | 3 / 3 |
Completeness | Clearly answers both what (identify design quality issues, detect various code smells, provide refactoring suggestions) AND when with explicit numbered triggers covering five specific use cases starting with 'Use when:'. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'code architecture', 'design quality', 'refactoring', 'God classes', 'coupling', 'cohesion', 'code maintainability', 'technical debt', 'code smells' - these are terms developers naturally use when discussing code quality. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on design-level code quality issues (coupling, cohesion, God classes) rather than general code review or syntax issues. The specific terminology like 'God classes', 'encapsulation problems', and 'cohesion' creates distinct triggers unlikely to conflict with general coding skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable skill with clear workflows and good progressive disclosure. The main weakness is some redundancy in the refactoring examples section, where patterns like God Class and High Coupling are demonstrated twice with similar content. The skill effectively balances quick-start guidance with comprehensive reference material.
Suggestions
Consolidate the duplicate refactoring examples - the 'Common Design Smells' section and 'Refactoring Strategies' section show overlapping before/after patterns that could be merged or one could reference the other.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some redundancy - the same refactoring examples appear multiple times (God Class, High Coupling, Low Cohesion patterns are shown twice), and some sections like 'Common Scenarios' add limited value beyond what's already covered. | 2 / 3 |
Actionability | Provides fully executable bash commands for running detection, concrete Python code examples showing before/after refactoring patterns, specific thresholds in a clear table, and copy-paste ready CI/CD integration examples. | 3 / 3 |
Workflow Clarity | Clear 5-step detection workflow with explicit validation step ('Verify Improvements' with re-running detection), numbered sequences, and feedback loop for measuring progress before/after. Pre-commit hook and CI/CD integration provide additional validation checkpoints. | 3 / 3 |
Progressive Disclosure | Excellent structure with Quick Start at top, detailed sections following, and clear one-level-deep references to external files (smell_catalog.md, refactoring_strategies.md) that are consistently signaled throughout the document. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (582 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- ArabelaTso/Skills-4-SE
- Commit
0f00a4f
- 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.