refactorer

Code refactoring expert - clean code, patterns, restructuring

Quality

63%

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/refactorer/SKILL.md

Quality

Content

62%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 a lean, well-structured catalog of executable refactoring examples that scores well on conciseness, actionability, and organization. Its main weakness is the absence of any sequenced workflow with test/behavior verification, which is important for a destructive operation like refactoring.

Suggestions

Add a short refactoring workflow with explicit validation checkpoints, e.g. 1) run the existing test suite, 2) apply the pattern, 3) re-run tests, 4) only proceed if behavior is unchanged.

Include a feedback loop for when tests fail after a refactor (revert/re-apply, re-validate) to satisfy the destructive-operation validation requirement.

Consider moving the SOLID Principles section into a separate reference file with a one-line pointer from SKILL.md to better separate the overview from extended reference material.

Dimension	Reasoning	Score
Conciseness	The body jumps straight to Before/After TypeScript examples with almost no padding prose and no re-explanation of concepts Claude already knows; it sits just below a 5 because the multiple full before/after blocks are lengthy though each earns its place.	4 / 5
Actionability	Concrete, executable TypeScript Before/After examples and a direct "Code Smells → fix" mapping give mostly copy-paste-ready guidance; minor gaps (e.g. `/* ... */` placeholders in the SOLID examples) keep it at 4 rather than 5.	4 / 5
Workflow Clarity	The content is a pattern catalog with no sequenced refactoring workflow and no validation checkpoints (run tests, verify behavior unchanged); refactoring is a destructive/risky change, so the missing validation cap plus the absence of any step sequence places it low, just above the incoherent anchor.	2 / 5
Progressive Disclosure	A single self-contained file with clear section headers (Refactoring Patterns, SOLID Principles, Code Smells), no nested references, and content appropriately placed inline; it does not reach 5 because at ~190 lines it exceeds the simple-skill threshold and lacks any overview-to-detail split.	4 / 5
	Total	14 / 20 Passed

Description

48%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 identifies a clear niche (code refactoring) but relies on generic action categories and omits any explicit trigger/"Use when" guidance, which caps its completeness. It is distinguishable but not comprehensive enough to score highly.

Suggestions

Replace generic terms ("clean code, patterns, restructuring") with concrete refactoring actions such as "extract functions, replace conditionals with polymorphism, introduce parameter objects".

Add an explicit trigger clause, e.g. "Use when the user asks to refactor, restructure, clean up, or reorganize existing code without changing its behavior".

Include natural trigger synonyms users say ("rename", "extract", "simplify", "reduce duplication", "apply design patterns") to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	"Code refactoring expert - clean code, patterns, restructuring" names the domain but the listed actions ("clean code, patterns, restructuring") are generic categories rather than concrete refactoring operations, matching the anchor that names the domain with minimal/generic actions.	2 / 5
Completeness	The description gives a clear "what" (refactoring, clean code, patterns, restructuring) but entirely lacks a "when"/"Use when..." clause, so per the rubric cap completeness cannot exceed 3.	3 / 5
Trigger Term Quality	"refactoring" and "clean code" are natural terms a user would say, but common synonyms and variations ("restructure", "rename", "extract", "improve code quality") are missing, fitting the anchor with some relevant keywords but missing common variations.	3 / 5
Distinctiveness Conflict Risk	"Code refactoring expert" carves a mostly distinct niche with only minor overlap risk against general coding/code-review skills, matching the "mostly distinct" anchor; it does not reach 5 because the brief phrasing leaves some overlap with general code-editing skills.	4 / 5
	Total	12 / 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: TurnaboutHero/oh-my-antigravity
Path: skills/refactorer/SKILL.md
Commit: f73e1ff

Reviewed: 15 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.