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.

1.05x

Quality

83%

Does it follow best practices?

Impact

79%

1.05x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Quality

Content

75%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with executable commands and concrete examples, and it links cleanly to two real reference files. Its main weakness is conciseness and progressive-disclosure overlap: large portions of the smell catalog and refactoring strategies are duplicated inline rather than delegated to the bundled references.

Suggestions

Remove the inlined 'Design Smells Detected' catalog section and the duplicated 'Common Design Smells' / 'Refactoring Strategies' sections from SKILL.md, keeping only a brief overview plus links to smell_catalog.md and refactoring_strategies.md.

Tighten 'Detection Workflow' step 5 into an explicit validate-feedback loop (e.g., 'If critical/major counts did not decrease, revisit the refactoring before committing') to reach the top workflow anchor.

Trim redundant restatements such as the 'Design Smell Catalog' summary list at the end, which repeats categories already covered above.

Dimension	Reasoning	Score
Conciseness	The body inlines large duplicated sections — full smell definitions, symptoms, and before/after refactoring examples — that already exist in smell_catalog.md and refactoring_strategies.md, adding notable padding that competes with the context window.	3 / 5
Actionability	Provides copy-paste-ready commands (`python scripts/detect_smells.py src/ --format json`), concrete example output, a thresholds table, and complete before/after code examples covering the common cases.	5 / 5
Workflow Clarity	A clear five-step Detection Workflow is sequenced with an explicit verification step ('Re-run detection to measure progress' / 'Compare metrics before/after'), but the checkpoint guidance for acting on failures is lighter than the top anchor.	4 / 5
Progressive Disclosure	References are real one-level-deep files clearly signaled with markdown links, and structure is good; however substantial content duplicated from those reference files is inlined in SKILL.md rather than kept solely in the bundled files.	4 / 5
	Total	16 / 20 Passed

Description

92%Weight 40%Scale 1-5

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 is specific, well-triggered, and complete, explicitly covering what the skill detects and when to use it with concrete numbered scenarios. It is slightly long and could drop the redundant trailing restatement of categories, but quality is high overall.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete detection targets — 'high coupling, low cohesion, God classes, long methods' plus coupling/cohesion/complexity/size/encapsulation categories — giving comprehensive coverage rather than vague language.	5 / 5
Completeness	Explicitly answers both 'what' ('Identify design quality issues... Detects coupling smells, cohesion problems...') and 'when' via five numbered 'Use when' trigger phrases with concrete scenarios.	5 / 5
Trigger Term Quality	Strong natural terms users would say ('God classes', 'high coupling', 'low cohesion', 'refactoring opportunities', 'technical debt') but lacks common synonyms and has no file-extension or tooling triggers, leaving a few natural terms missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (design smells and refactoring) with distinct, specific triggers, making overlap with unrelated skills minimal.	5 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 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	15 / 16 Passed

Repository: ArabelaTso/Skills-4-SE
Path: skills/design-smell-detector/SKILL.md
Commit: 4f38503

Reviewed: 8 days ago

Table of Contents

Discovery Implementation Validation

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.