code-refactor

Systematic code refactoring based on Martin Fowler's methodology. Use when users ask to refactor code, improve code structure, reduce technical debt, clean up legacy code, eliminate code smells, or improve code maintainability. This skill guides through a phased approach with research, planning, and safe incremental implementation.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

77%

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

The skill delivers a strong, well-sequenced refactoring workflow with concrete commands and rigorous validation checkpoints. Its main weaknesses are redundant explanation of concepts Claude already knows, an inline catalog duplicating reference files, and a broken reference to a missing templates/refactoring-plan.md.

Suggestions

Remove or relocate the inline 'Quick Reference' smell table and the explanatory 'What Are Code Smells?' / 'Why Tests Matter' prose, pointing instead to references/code-smells.md, since that content is duplicated and covers concepts Claude already knows.

Create the missing templates/refactoring-plan.md referenced in Phase 4, or remove the broken reference, so navigation to referenced bundle paths resolves.

Move the version history date (v1.0.0, 2025-01-15) into a clearly labeled version/deprecated section or drop it from the body, since time-sensitive dates outside such a section penalize conciseness.

Dimension	Reasoning	Score
Conciseness	The body is well-structured but explains concepts Claude already knows ('Symptoms of deeper problems in code... not bugs, but indicators', 'Tests are the key enabler of safe refactoring. Without them, you risk introducing bugs') and carries a time-sensitive version date (v1.0.0, 2025-01-15) outside any deprecated section, plus an inline smell table that duplicates references/code-smells.md.	2 / 3
Actionability	Provides concrete, executable guidance throughout: bash commands (find, npm test, pytest --cov), a smell-to-refactoring mapping table, real commit-message examples, and a runnable before/after processOrder refactor, rather than vague direction.	3 / 3
Workflow Clarity	Six phases are clearly sequenced with explicit validation checkpoints and feedback loops: the Golden Rule ('Change → Test → Green? → Commit → Next step'), 'STOP immediately / Undo the change' on test failure, and per-phase 'Request approval' decision points.	3 / 3
Progressive Disclosure	References are mostly one level deep and clearly signaled ('See references/code-smells.md for the complete catalog'), but the body references templates/refactoring-plan.md which does not exist in the bundle, and inline catalog/mapping content duplicates what already lives in the reference files.	2 / 3
	Total	10 / 12 Passed

Description

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.

The description is concise, third-person, and clearly states both what the skill does and when to use it with a strong set of natural trigger terms. It is specific to its niche and unlikely to conflict with other skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions such as 'refactor code, improve code structure, reduce technical debt, clean up legacy code, eliminate code smells, or improve code maintainability', matching the anchor for multiple specific concrete actions.	3 / 3
Completeness	Explicitly answers 'what' (systematic refactoring via a phased approach with research, planning, and safe incremental implementation) and 'when' (an explicit 'Use when...' clause with multiple triggers), satisfying both requirements.	3 / 3
Trigger Term Quality	The 'Use when users ask to refactor code, improve code structure, reduce technical debt, clean up legacy code, eliminate code smells...' clause gives good coverage of natural phrases users would actually say.	3 / 3
Distinctiveness Conflict Risk	Scoped specifically to code refactoring with distinct triggers (code smells, technical debt, legacy code), making it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 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
relative_links	Relative link issues: 2 missing	Warning

	Total	15 / 16 Passed

Repository: luongnv89/claude-howto
Path: 03-skills/refactor/SKILL.md
Commit: 97fc961

Reviewed: 4 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.