codebase-cleanup-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

45%

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/codebase-cleanup-refactor-clean/SKILL.md

The canonical home for this skill is jbvc/codebase-cleanup-refactor-clean

Quality

Content

50%

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

The skill body is clean, well-organized, and responsibly scoped (Use/Do-not-use, Safety, Output Format), but it is held back by redundant prose, abstract instructions lacking concrete examples, implicit validation checkpoints, and a referenced resource file that is missing from the bundle.

Suggestions

Delete the redundant opening paragraph (it duplicates the frontmatter description) and tighten or remove the 'Context' section to improve conciseness.

Add at least one concrete refactoring example or named technique (e.g., extract method, replace conditional with polymorphism) to make the instructions actionable rather than descriptive.

Add an explicit validate→fix→re-test feedback loop with a checkpoint, and create the referenced 'resources/implementation-playbook.md' so the progressive-disclosure reference resolves.

Dimension	Reasoning	Score
Conciseness	The body is short and well-sectioned, but the opening paragraph repeats the frontmatter description verbatim and the 'Context' section restates the same purpose, so it could be tightened; it also leans on concepts Claude already knows (clean code, SOLID).	2 / 3
Actionability	Guidance is structured (Use/Do-not-use, Instructions, Output Format) but the instructions are abstract ('Identify high-impact refactor candidates', 'Apply changes with a focus on readability') with no concrete example refactor or specific technique, matching 'some concrete guidance but incomplete'.	2 / 3
Workflow Clarity	A loose sequence exists (identify → break into steps → apply → validate with tests) and validation is mentioned, but there is no explicit feedback-loop checkpoint (refactor → test → fix → re-test), so checkpoints remain implicit.	2 / 3
Progressive Disclosure	Sections are well organized and a single one-level-deep reference is clearly signaled ('resources/implementation-playbook.md'), but that referenced file does not exist in the bundle, leaving a broken/dangling reference that caps the score.	2 / 3
	Total	8 / 12 Passed

Description

40%

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 conveys the skill's purpose and domain but is weakened by second-person voice, absent explicit 'Use when' triggers, and jargon-heavy phrasing. It clears a baseline but falls short of the strongest examples on every dimension.

Suggestions

Rewrite in third person ('Refactors and cleans code to improve quality, maintainability, and performance...') to remove the second-person voice and recover the specificity penalty.

Add an explicit 'Use when...' clause with concrete triggers (e.g., 'Use when cleaning up large codebases, removing duplication, or preparing code for new feature work') to lift completeness.

Swap jargon like 'modern software engineering best practices' for natural user phrasings ('refactor', 'clean up code', 'reduce duplication', 'tech debt') to improve trigger-term quality.

Dimension	Reasoning	Score
Specificity	It names the domain and two actions ('Analyze and refactor the provided code to improve its quality, maintainability, and performance'), which would anchor at 2, but the second-person voice ('You are a code refactoring expert...') triggers the rubric's −1 specificity penalty, dropping it to 1.	1 / 3
Completeness	It clearly states what the skill does but provides no 'Use when...' clause or equivalent trigger guidance; per the rubric a missing explicit trigger caps completeness at 2.	2 / 3
Trigger Term Quality	It includes some relevant natural terms ('refactor', 'clean code', 'SOLID'), but leans on jargon ('modern software engineering best practices') and lacks common user phrasings like 'clean up code' or 'tech debt', matching the 'some relevant keywords but missing variations' anchor.	2 / 3
Distinctiveness Conflict Risk	The refactoring/clean-code niche is somewhat specific but broad enough to overlap with general coding skills, matching 'somewhat specific but could still overlap with similar skills'.	2 / 3
	Total	7 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: rmyndharis/antigravity-skills
Path: skills/codebase-cleanup-refactor-clean/SKILL.md
Commit: e63f7dd

Reviewed: about 5 hours 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.