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.

1.43x

Quality

88%

Does it follow best practices?

Impact

93%

1.43x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Evaluation results

88%

29%

Legacy Inventory System Code Quality Audit

Full smell report structure and format

Criteria

Without context

With context

Uses detect_smells.py script

75%

100%

Emoji severity headers

File and line locations

100%

Before/after code examples

100%

Summary section with counts

100%

Three-tier recommendations

60%

100%

CI/CD prevention commands

30%

100%

Code review checklist

12%

75%

God class severity

100%

Magic number severity

100%

12%

Code Smell Severity Classification for Design Review

Smell severity thresholds and categorization

Criteria

Without context

With context

Large class is medium severity

100%

God class is high severity

100%

Long method is medium severity

100%

6-param function is medium severity

100%

8-param function is high severity

100%

Feature envy is high severity

100%

Magic numbers are low severity

100%

God class refactoring technique

100%

Long parameter refactoring technique

100%

92%

42%

Python Code Quality Standards and Tooling Setup

Code quality tooling and prevention setup

Criteria

Without context

With context

radon cc command

100%

radon mi command

100%

pylint --disable=C0111

100%

pylint --fail-under=8.0

100%

Method length limit of 50

100%

Class method limit of 15

100%

Parameter count limit of 5

100%

detect_smells.py script mentioned

No hardcoded config or magic numbers in checklist

40%

100%

Repository: ArabelaTso/Skills-4-SE
Commit: 0f00a4f

Evaluated: 29 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Legacy Inventory System Code Quality Audit Code Smell Severity Classification for Design Review Python Code Quality Standards and Tooling Setup

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.