code-refactoring-refactor-clean

You 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.

Quality

52%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/code-refactoring-refactor-clean/SKILL.md

Quality

Content

65%Weight 40%Scale 1-3

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

The content is concise, well-structured, and respectably organized, but it stays at the directional level: it lacks concrete executable examples, explicit feedback loops, and the referenced playbook file does not exist in the bundle. Tightening actionability and fixing the dangling reference would lift it further.

Suggestions

Add at least one concrete, executable example (e.g. a small before/after refactor snippet or a specific command to run the test suite) to move from directional to copy-paste-ready guidance.

Make the validate→fix→retry loop explicit for behavior-sensitive refactors (e.g. 'run tests; if failing, revert the slice and re-plan') to strengthen workflow_clarity.

Either create references/implementation-playbook.md (matching the path cited in Instructions and Resources) or remove the reference to avoid a dangling pointer.

Dimension	Reasoning	Score
Conciseness	The body is lean and well-sectioned with no padding and no explanation of concepts Claude already knows; every line ('Assess code smells…', 'Apply changes in small slices') earns its place.	3 / 3
Actionability	It gives imperative direction ('Assess…', 'Propose a refactor plan…', 'Update tests and verify regressions') but no concrete executable code, commands, or worked examples, so it instructs without being copy-paste ready — matching the 'some concrete guidance but incomplete' anchor.	2 / 3
Workflow Clarity	A clear sequence exists (assess → plan → apply → test/verify) with validation cues ('verify regressions', 'ensure tests pass'), but for behavior-sensitive refactoring the checkpoints are implicit and lack an explicit validate→fix→retry feedback loop, so it sits at 2 rather than 3.	2 / 3
Progressive Disclosure	The skill is short and well-organized into clear sections (qualifying for a high score), but it references 'resources/implementation-playbook.md' twice while no such bundle file or directory exists, leaving a dangling reference that weakens navigation.	2 / 3
	Total	9 / 12 Passed

Description

40%Weight 40%Scale 1-3

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 clear on what the skill does but is written in second person, omits an explicit 'Use when' trigger clause, and uses fairly generic refactoring language. It is competent but generic, leaving room for stronger trigger terms and clearer use-conditions.

Suggestions

Rewrite in third person (e.g. 'Analyzes and refactors code…') and add an explicit 'Use when…' clause naming concrete triggers (e.g. tangled code, duplication, code smells, preparing modules for new features).

Add the natural phrasings users actually say, such as 'clean up', 'reduce duplication', 'fix code smells', and 'simplify complex methods', to improve trigger-term coverage.

Narrow the niche slightly (e.g. reference SOLID/clean-code-driven refactor planning) to reduce overlap with general coding and review skills.

Dimension	Reasoning	Score
Specificity	The description names the domain ('code refactoring expert', 'clean code principles, SOLID design patterns') but enumerates only one broad action ('Analyze and refactor the provided code'); the second-person voice ('You are a code refactoring expert') triggers a 1-point specificity penalty per the rubric guidelines, dropping it from 2 to 1.	1 / 3
Completeness	It clearly answers 'what does this do' (analyze and refactor code for quality/maintainability/performance) but provides no 'Use when…' trigger clause, so per the guidelines 'when' is missing and completeness is capped at 2.	2 / 3
Trigger Term Quality	It includes some natural keywords a user might say ('refactor', 'clean code', 'SOLID'), but misses common variations users actually use like 'clean up this code', 'reduce duplication', or 'fix code smells'.	2 / 3
Distinctiveness Conflict Risk	The clean-code/SOLID framing carves a recognizable niche, but 'refactor code to improve quality' is broad enough to overlap with general coding and review skills, so it is not yet a fully distinct trigger space.	2 / 3
	Total	7 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: sickn33/antigravity-awesome-skills
Path: skills/code-refactoring-refactor-clean/SKILL.md
Commit: 7962275

Reviewed: 2 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.