clean-code

This skill embodies the principles of "Clean Code" by Robert C. Martin (Uncle Bob). Use it to transform "code that works" into "code that is clean."

Quality

23%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/clean-code/SKILL.md

Quality

Discovery

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 relies heavily on the 'Clean Code' brand name without specifying what concrete actions the skill performs (e.g., improving naming, reducing function length, eliminating duplication, applying SOLID principles). It lacks explicit trigger guidance and natural user keywords, making it difficult for Claude to reliably select this skill from a large pool.

Suggestions

List specific concrete actions the skill performs, such as 'Refactors functions for single responsibility, improves variable/function naming, reduces code duplication, and applies SOLID principles.'

Add an explicit 'Use when...' clause with natural trigger terms like 'refactor', 'code review', 'readability', 'code smell', 'naming conventions', 'simplify code', or 'maintainability'.

Switch from the vague metaphor 'transform code that works into code that is clean' to specific, measurable improvements the skill targets.

Dimension	Reasoning	Score
Specificity	The description mentions no concrete actions—'transform code that works into code that is clean' is abstract and metaphorical. It does not list specific capabilities like refactoring functions, renaming variables, reducing complexity, etc.	1 / 3
Completeness	It has a weak 'what' (transform code into clean code) and a partial 'when' ('Use it to transform code that works into code that is clean'), but the 'when' is vague and doesn't provide explicit trigger scenarios or user request patterns.	2 / 3
Trigger Term Quality	It includes 'Clean Code' and 'Robert C. Martin' which are recognizable terms a user might mention, but lacks natural trigger terms like 'refactor', 'readability', 'naming conventions', 'code smell', 'simplify', or 'maintainability' that users would commonly say.	2 / 3
Distinctiveness Conflict Risk	The reference to 'Clean Code' by Robert C. Martin gives it some distinctiveness from generic code review skills, but 'transform code' is broad enough to overlap with general refactoring, linting, or code review skills.	2 / 3
	Total	7 / 12 Passed

Implementation

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

This skill is essentially a condensed summary of Robert C. Martin's 'Clean Code' book, which Claude already knows thoroughly. It provides no actionable workflow for how to actually perform code transformations, no concrete refactoring steps, and no validation checkpoints. The content would be far more valuable if it focused on a specific refactoring workflow with concrete before/after examples and clear decision criteria rather than restating well-known principles.

Suggestions

Replace the principle summaries with a concrete step-by-step refactoring workflow (e.g., 1. Identify the worst smell, 2. Apply specific transformation, 3. Verify tests still pass, 4. Repeat)

Add concrete before/after code transformation examples showing exactly how Claude should refactor specific patterns, rather than listing abstract principles

Remove all explanations of Clean Code concepts that Claude already knows and instead focus on decision criteria for when to apply which refactoring technique

Add validation checkpoints to the workflow, such as 'run tests after each refactoring step' and 'verify function length metrics before proceeding'

Dimension	Reasoning	Score
Conciseness	The skill extensively explains concepts Claude already knows well — Clean Code principles, SOLID, TDD laws, code smells. This is essentially a summary of a well-known book that Claude has already been trained on. Nearly every token is redundant for Claude's existing knowledge base.	1 / 3
Actionability	The content is almost entirely descriptive principles and guidelines rather than concrete, executable instructions. There's no actionable workflow for how Claude should actually transform code — no specific refactoring commands, no concrete before/after transformation patterns, no step-by-step process. The one code example (comments section) illustrates a concept rather than providing executable guidance.	1 / 3
Workflow Clarity	There is no clear workflow or sequenced process for how Claude should apply these principles when refactoring code. The checklist at the end is a static list of questions, not a workflow with validation steps or feedback loops. There's no guidance on order of operations, how to prioritize competing concerns, or how to verify improvements.	1 / 3
Progressive Disclosure	The content is organized into numbered sections with clear headers, which provides reasonable structure. However, it's a monolithic document with no references to supporting files, and the inline content is extensive enough that it could benefit from being split into separate reference files for each principle area.	2 / 3
	Total	5 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: sickn33/antigravity-awesome-skills
Commit: fb2efea

Reviewed: about 14 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.