code-smell-detector
Identify and report code smells indicating poor design or maintainability issues in Python code, including duplicate code, magic numbers, hardcoded values, God classes, feature envy, inappropriate intimacy, data clumps, primitive obsession, and long parameter lists. Use when conducting code quality audits, preparing for refactoring, improving codebase maintainability, or performing design reviews. Produces markdown reports with severity ratings, locations, descriptions, and specific refactoring recommendations with before/after examples. Triggers when users ask to find code smells, identify design issues, suggest refactorings, improve code quality, or detect maintainability problems.
90
88%
Does it follow best practices?
Impact
93%
1.43xAverage 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 key criteria. It provides specific capabilities with named code smell types, includes comprehensive trigger terms users would naturally use, explicitly states both what it does and when to use it, and carves out a distinct niche in Python code quality analysis. The description is thorough without being padded with fluff.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'identify and report code smells', names specific smell types (duplicate code, magic numbers, God classes, feature envy, etc.), and describes output format (markdown reports with severity ratings, locations, refactoring recommendations with before/after examples). | 3 / 3 |
Completeness | Clearly answers both what (identify code smells, produce markdown reports with specific details) AND when with explicit 'Use when...' and 'Triggers when...' clauses covering multiple scenarios like code audits, refactoring prep, and design reviews. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'code smells', 'design issues', 'refactoring', 'code quality', 'maintainability problems', 'code quality audits', 'design reviews'. Also includes specific smell names users might search for. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on Python code smell detection and design issue identification. The specific smell types, Python focus, and detailed output format (markdown with before/after examples) make it distinct from general code review or linting skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%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 excellent concrete examples. However, it suffers from verbosity - the full report template and extensive code examples should be moved to reference files rather than inline. The skill would benefit from being more concise in the main file while leveraging its reference documents more heavily.
Suggestions
Move the full report template (from '## Code Smell Analysis Report' through the end of the template) to a separate reference file like 'report-template.md' and link to it
Condense the 'Tips for Effective Smell Detection' and 'Common False Positives' sections - Claude already understands these concepts and they add ~50 lines of content that could be 10 lines or removed
Consider moving the detailed before/after refactoring examples to refactoring-patterns.md and keeping only one brief example inline
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but overly verbose in places. The full report template with extensive before/after examples could be condensed or moved to a reference file. Some sections like 'Tips for Effective Smell Detection' and 'Common False Positives' contain guidance Claude likely already knows. | 2 / 3 |
Actionability | Provides fully executable bash commands, Python code examples, and specific tool invocations. The before/after refactoring examples are concrete and copy-paste ready. Detection strategies include real grep patterns and tool commands. | 3 / 3 |
Workflow Clarity | Clear 6-step workflow with explicit sequencing from scope definition through detection, categorization, refactoring identification, report generation, and presentation. Includes validation through external tools (radon, pylint) and clear decision points. | 3 / 3 |
Progressive Disclosure | References smell-patterns.md and refactoring-patterns.md appropriately, but the main file is too long. The full report template (150+ lines) and extensive before/after examples should be in separate reference files. The inline content overwhelms the overview structure. | 2 / 3 |
Total | 10 / 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 (609 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.