CtrlK
BlogDocsLog inGet started
Tessl Logo

code-refactoring-assistant

Suggest and apply code refactorings to improve readability, maintainability, and code quality. Use this skill when improving existing code structure, eliminating code smells, applying design patterns, simplifying complex logic, extracting duplicated code, renaming for clarity, or preparing code for new features. Provides specific before/after examples, explains benefits, identifies risks, and ensures behavior preservation through tests.

85

1.26x
Quality

81%

Does it follow best practices?

Impact

91%

1.26x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

70%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 content is highly actionable with executable examples and a well-validated workflow, but it is severely over-long for a SKILL.md, re-teaching refactoring knowledge Claude already has, and lacks progressive disclosure for a large catalog that should be split into reference files.

Suggestions

Trim the in-depth re-explanation of standard code smells and refactoring catalogs — assume Claude knows Fowler's refactorings and keep only non-obvious guidance, dropping the body well under 200 lines.

Move the 10 worked before/after pattern examples, anti-patterns, and language-specific patterns into separate reference files (e.g. references/patterns.md, references/anti-patterns.md) and link to them one level deep from SKILL.md.

Lead with a concise quick-start showing one end-to-end refactoring with the test-validate-commit loop, then defer the catalog to references.

DimensionReasoningScore

Conciseness

At ~974 lines the body extensively re-explains the standard Fowler refactoring catalog (code smells, Extract Method, Replace Conditional with Polymorphism, etc.) that Claude already knows, with many padded before/after walkthroughs that could be trimmed drastically.

2 / 5

Actionability

Provides complete, copy-paste-ready Python before/after examples for every pattern plus a concrete code-smell-to-refactoring table, covering the common cases with executable code.

5 / 5

Workflow Clarity

The 5-step workflow includes a pre-refactoring checklist, explicit validation ('Run tests after each step', 'If tests fail, revert and try smaller steps'), and a verification phase, giving clear feedback loops for a code-modification task.

5 / 5

Progressive Disclosure

Headers provide reasonable section structure, but with no bundle files the entire 974-line pattern catalog, anti-patterns, and language-specific guidance are inlined in SKILL.md when much of it clearly belongs in separate reference files.

3 / 5

Total

15

/

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.

A strong, third-person description that clearly states capabilities and explicit trigger conditions with concrete refactoring actions. Minor improvement is possible by adding a few more colloquial trigger terms users naturally say.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'eliminating code smells, applying design patterns, simplifying complex logic, extracting duplicated code, renaming for clarity' plus 'Provides specific before/after examples, explains benefits, identifies risks, and ensures behavior preservation through tests' — giving comprehensive coverage.

5 / 5

Completeness

Explicitly answers both what ('Suggest and apply code refactorings... Provides specific before/after examples, explains benefits, identifies risks, and ensures behavior preservation through tests') and when ('Use this skill when improving existing code structure, eliminating code smells...').

5 / 5

Trigger Term Quality

Good natural keyword coverage ('code refactorings', 'code smells', 'design patterns', 'duplicated code', 'renaming for clarity') but misses common variations users say like 'clean code', 'technical debt', or 'reduce complexity'.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear refactoring niche with distinct triggers ('code smells', 'applying design patterns', 'extracting duplicated code') and minimal overlap risk with other skills.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (979 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
ArabelaTso/Skills-4-SE
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.