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?

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/clean-code/SKILL.md

Quality

Content

7%Scale 1-3

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, covering principles Claude already knows thoroughly. It lacks actionable, executable guidance — there are no concrete workflows for how to apply these principles during code review or refactoring tasks. The content would be far more valuable if it focused on project-specific conventions, concrete transformation patterns, or a step-by-step refactoring workflow rather than restating well-known software engineering principles.

Suggestions

Replace the book summary with a concrete workflow: e.g., 'Step 1: Identify functions > 20 lines → Step 2: Extract sub-functions → Step 3: Rename using pattern X → Step 4: Verify tests pass'

Add executable before/after code examples showing specific refactoring transformations Claude should apply, rather than abstract principles

Remove sections that restate general knowledge (TDD laws, FIRST principles, Law of Demeter) and focus only on project-specific conventions or non-obvious preferences

Include a concrete decision tree or prioritization order for which clean code principles to apply first when refactoring, with validation checkpoints between steps

Dimension	Reasoning	Score
Conciseness	This skill extensively explains concepts Claude already knows well — Clean Code principles, naming conventions, function design, TDD laws, SOLID principles, and code smells. Nearly all content is a summary of a well-known book that Claude has deep familiarity with, adding no novel or project-specific information.	1 / 3
Actionability	The skill provides abstract principles and guidelines rather than concrete, executable instructions. There are no specific commands, refactoring workflows, or copy-paste-ready code transformations. The one code example (comments section) illustrates a concept rather than providing actionable guidance for Claude to follow.	1 / 3
Workflow Clarity	There is no clear workflow or sequenced process for how Claude should actually apply these principles when reviewing or refactoring code. The checklist at the end is a static list without any process flow, validation steps, or feedback loops for iterative improvement.	1 / 3
Progressive Disclosure	The content is organized into numbered sections with clear headers, which provides some structure. However, it's a monolithic document with no references to supporting files, and the extensive inline content (9 major sections plus extras) could benefit from being split into separate reference files with a concise overview in the main skill.	2 / 3
	Total	5 / 12 Passed

Description

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 relies heavily on the 'Clean Code' brand name without specifying what concrete actions the skill performs (e.g., refactoring, improving naming, reducing function length, applying SOLID principles). The 'when' clause is present but vague, and the lack of natural trigger terms beyond the book title limits discoverability.

Suggestions

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

Add explicit trigger guidance with natural user terms, e.g., 'Use when the user asks to refactor code, improve readability, fix code smells, apply clean code principles, or review code quality.'

Include common variations of trigger terms users might say: 'refactor', 'code review', 'readability', 'naming conventions', 'code smell', 'SOLID', 'DRY', 'single responsibility'.

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) and a partial 'when' ('Use it to transform code that works into code that is clean'), but the 'when' is vague and not framed with 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', 'code review', 'naming conventions', 'readability', 'code smell', or 'SOLID principles'.	2 / 3
Distinctiveness Conflict Risk	The reference to 'Clean Code' by Robert C. Martin gives it some distinctiveness, but 'transform code' is broad enough to overlap with general code review, refactoring, or linting skills.	2 / 3
	Total	7 / 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: popey/claude-code-skills
Path: skills/clean-code/SKILL.md
Commit: a5a6601

Reviewed: 5 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.