code-refactoring-refactor-clean
tessl i github:sickn33/antigravity-awesome-skills --skill code-refactoring-refactor-cleanYou are a code refactoring expert specializing in clean code principles, SOLID design patterns, and modern software engineering best practices. Analyze and refactor the provided code to improve its quality, maintainability, and performance.
Activation
33%The description identifies the refactoring domain but relies on abstract concepts rather than concrete actions. It critically lacks explicit trigger guidance ('Use when...') which makes it difficult for Claude to know when to select this skill. The use of second person voice ('You are') violates the third-person requirement in the rubric.
Suggestions
Add an explicit 'Use when...' clause with trigger terms like 'refactor', 'clean up code', 'code smell', 'technical debt', 'simplify', 'restructure'.
Replace vague actions with specific concrete capabilities like 'extract methods, apply design patterns, reduce code duplication, simplify conditional logic, improve naming conventions'.
Rewrite in third person voice (e.g., 'Analyzes and refactors code to improve...' instead of 'You are a code refactoring expert').
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (code refactoring) and mentions some concepts (clean code principles, SOLID design patterns, best practices), but actions are vague ('analyze and refactor', 'improve quality') rather than listing specific concrete actions like 'extract methods', 'reduce cyclomatic complexity', or 'apply dependency injection'. | 2 / 3 |
Completeness | Describes what it does (analyze and refactor code) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing explicit trigger guidance caps this at 2, and the 'what' is also weak. | 1 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'refactoring', 'clean code', 'SOLID', but misses common natural variations users might say such as 'code smell', 'technical debt', 'simplify code', 'restructure', or 'code cleanup'. | 2 / 3 |
Distinctiveness Conflict Risk | Somewhat specific to refactoring but could overlap with general code review skills, code optimization skills, or architecture skills. Terms like 'improve quality' and 'best practices' are generic enough to cause conflicts. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
35%This skill provides a high-level framework for code refactoring but lacks the concrete, actionable guidance that would make it useful. The instructions read more like a job description than executable steps, with no code examples, specific refactoring patterns, or concrete techniques demonstrated. The workflow exists but lacks explicit validation checkpoints.
Suggestions
Add concrete code examples showing before/after refactoring for common patterns (e.g., extracting methods, removing duplication, applying dependency injection)
Replace vague instructions like 'Assess code smells' with specific techniques: 'Look for: methods >20 lines, classes with >5 dependencies, duplicated logic blocks'
Add explicit validation checkpoint: 'Run tests after each refactoring step. If tests fail, revert the last change and try a smaller slice'
Remove the 'Use this skill when/Do not use' sections and 'Context' - these don't add actionable value for Claude
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some unnecessary framing ('You are a code refactoring expert...') that Claude doesn't need, and the 'Context' section restates what's already clear from the title and instructions. | 2 / 3 |
Actionability | The instructions are vague and abstract ('Assess code smells', 'Propose a refactor plan', 'Apply changes in small slices') without any concrete code examples, specific commands, or executable guidance. No actual refactoring patterns or techniques are demonstrated. | 1 / 3 |
Workflow Clarity | Steps are listed in a logical sequence (assess → plan → apply → test), but validation checkpoints are weak ('verify regressions' is vague) and there's no explicit feedback loop for when tests fail or issues are discovered during refactoring. | 2 / 3 |
Progressive Disclosure | References an external resource (implementation-playbook.md) appropriately, but the main content lacks structure - no clear separation between quick-start guidance and advanced patterns. The 'Use this skill when' sections add bulk without adding value for Claude. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
75%| Criteria | Description | Result |
|---|---|---|
description_trigger_hint | Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
body_steps | No step-by-step structure detected (no ordered list); consider adding a simple workflow | Warning |
Total | 12 / 16 Passed | |
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.