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

86%

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%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.

A well-structured, highly actionable phased workflow with strong validation feedback loops. The main weaknesses are some explanatory padding Claude doesn't need and a broken reference to a missing templates/refactoring-plan.md file.

Suggestions

Create templates/refactoring-plan.md or remove the three references to it; the missing file is a broken navigation link that should not ship.

Cut the 'What Are Code Smells?', 'Why Tests Matter', and Core Principles prose — Claude already knows these concepts; keep only the actionable tables and commands.

Consolidate the duplicated 'References' / 'Scripts' footer with the inline reference links to avoid restating the same paths twice.

Dimension	Reasoning	Score
Conciseness	Mostly efficient, but it retreads concepts Claude already knows — the 'What Are Code Smells?' definition, 'Why Tests Matter' exposition, repeated Fowler quotes, and a re-listed Core Principles section add padding that could be trimmed.	3 / 5
Actionability	Provides copy-paste-ready commands (find, npm test, pytest, mvn test), executable script invocations, a smell-to-refactoring mapping table, and concrete commit-message examples covering the common cases.	5 / 5
Workflow Clarity	The six-phase sequence has explicit validation checkpoints and feedback loops ('STOP. Fix failing tests', change→test→green→commit, per-phase user approval gates) appropriate for destructive/batch refactoring operations.	5 / 5
Progressive Disclosure	References to references/code-smells.md, references/refactoring-catalog.md and the scripts resolve to real files, but templates/refactoring-plan.md is referenced three times yet the templates/ directory does not exist — a broken navigation link.	3 / 5
	Total	16 / 20 Passed

Description

96%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 description: third-person, concrete, and explicit about both capabilities and triggering conditions. It reads naturally as something a user would say when they need this skill.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'refactor code', 'improve code structure', 'reduce technical debt', 'clean up legacy code', 'eliminate code smells', 'improve code maintainability' — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both what (systematic refactoring via a phased approach) and when ('Use when users ask to refactor code...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes the natural phrases users actually say ('refactor code', 'reduce technical debt', 'eliminate code smells', 'clean up legacy code') rather than technical jargon, with good synonym coverage.	5 / 5
Distinctiveness Conflict Risk	The Fowler-methodology framing and code-smell triggers carve a clear niche, though 'improve code structure' has minor overlap with general code-editing skills.	4 / 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
relative_links	Relative link issues: 2 missing	Warning

	Total	15 / 16 Passed

Repository: luongnv89/claude-howto
Path: 03-skills/refactor/SKILL.md
Commit: 1c04dbf

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.