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

43%

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 ./plugins/AI-Agents-Safe-Coding-Skills/skills/codebase-cleanup-refactor-clean/SKILL.md

The canonical home for this skill is codebase-cleanup-refactor-clean in rmyndharis/antigravity-skills

Quality

Content

42%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.

The body is well-organized into clear sections and includes a safety section and output format, but it offers only abstract directives with no executable refactor guidance, and it points to a playbook file that is absent from the bundle. The workflow has a validation mention but lacks an explicit feedback loop.

Suggestions

Add at least one concrete, runnable example of a refactor (e.g. an extract-method or remove-duplication before/after snippet) or specific commands, so the instructions are actionable without the missing playbook.

Either ship `resources/implementation-playbook.md` (or move it under `references/`) and fix the path, or inline the minimal concrete patterns and drop the broken reference.

Turn validation into an explicit feedback loop: 'Run tests; if any fail, fix and re-run before proceeding' — with a checkpoint gate before declaring the refactor complete.

Dimension	Reasoning	Score
Conciseness	The body is short and sectioned, but it repeats the frontmatter description verbatim as an opening paragraph and the 'Context' section restates the same purpose, which is unnecessary padding. It is mostly efficient but could be tightened, matching the score-3 anchor.	3 / 5
Actionability	The instructions are high-level directives ('Identify high-impact refactor candidates', 'Break work into small, testable steps', 'Apply changes with a focus on readability') with no concrete code, commands, or named refactor techniques, and the one promised concrete resource (the playbook) is not present. This matches the 'minimal concrete guidance; high-level hints but missing specific steps' anchor.	2 / 5
Workflow Clarity	A rough sequence is present (identify → break into steps → apply → validate) and a validation step is named ('Validate with tests and targeted regression checks'), but there are no explicit checkpoints or a validate→fix→retry feedback loop, matching the 'steps listed but checkpoints missing or implicit' anchor.	3 / 5
Progressive Disclosure	The content is cleanly sectioned and signals a one-level-deep reference in two places, but the referenced `resources/implementation-playbook.md` does not exist in the bundle, breaking the navigation it advertises. This fits the 'some structure but references not reliably usable' level rather than a clean 4.	3 / 5
	Total	11 / 20 Passed

Description

45%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.

The description states a clear purpose and a couple of concrete actions but relies on buzzword padding, uses second-person voice, and omits any explicit 'Use when' trigger guidance. It is distinguishable but not sharply differentiated from related code-quality skills.

Suggestions

Rewrite in third person ('Refactors and cleans code...') and drop the buzzword stack ('clean code principles, SOLID design patterns, modern best practices') in favor of listing concrete refactor actions (extract methods, remove duplication, rename for clarity, simplify conditionals).

Add an explicit trigger clause, e.g. 'Use when cleaning up a large codebase, removing duplication, or preparing code for new feature work; not for tiny targeted fixes.'

Include natural synonyms users actually say — 'refactor', 'clean up', 'tidy', 'restructure', 'pay down technical debt' — to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain and two concrete actions ('Analyze and refactor the provided code'), matching the score-3 anchor, but the 'clean code principles, SOLID... best practices' phrasing is buzzword-heavy rather than enumerating specific refactor actions. The second-person voice ('You are a code refactoring expert') triggers the voice penalty, reducing the score by one to 2.	2 / 5
Completeness	It clearly states what the skill does ('Analyze and refactor the provided code to improve its quality, maintainability, and performance') but contains no 'Use when...' clause or explicit trigger guidance, capping completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	It includes natural terms a user would say ('refactor', 'clean code') but misses common variations and synonyms like 'cleanup', 'tidy', 'restructure', or 'technical debt', matching the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	'Code refactoring / clean code' is a recognizable niche but overlaps broadly with general code-improvement, code-review, and simplify skills, fitting the 'somewhat specific but could still overlap' anchor rather than a clearly bounded niche.	3 / 5
	Total	11 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills/skills/codebase-cleanup-refactor-clean/SKILL.md
Commit: 57c135b

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.