Clean Code principles (DRY, KISS, YAGNI), naming conventions, function design, and refactoring. Use when user says "clean this code", "refactor", "improve readability", or when reviewing code quality.
82
78%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/clean-code/SKILL.mdQuality
Discovery
92%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-crafted skill description that clearly articulates its domain (Clean Code principles) with specific sub-capabilities and includes an explicit 'Use when' clause with natural trigger phrases. The main weakness is potential overlap with other code-related skills on generic terms like 'refactor' or 'code quality', though the Clean Code focus provides reasonable differentiation.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete concepts: 'Clean Code principles (DRY, KISS, YAGNI), naming conventions, function design, and refactoring' - these are distinct, actionable areas of expertise. | 3 / 3 |
Completeness | Clearly answers both what (Clean Code principles, naming conventions, function design, refactoring) AND when (explicit 'Use when' clause with specific trigger phrases like 'clean this code', 'refactor', 'improve readability'). | 3 / 3 |
Trigger Term Quality | Includes natural phrases users would actually say: 'clean this code', 'refactor', 'improve readability', 'reviewing code quality'. These are common, natural language triggers that match real user requests. | 3 / 3 |
Distinctiveness Conflict Risk | While 'Clean Code' and specific principles like DRY/KISS/YAGNI are distinctive, 'refactor' and 'reviewing code quality' could overlap with general code review or language-specific refactoring skills. The niche is reasonably clear but not fully distinct. | 2 / 3 |
Total | 11 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a comprehensive clean code reference with excellent actionable examples and clear before/after comparisons. However, it's verbose for a skill file—much of this content (DRY, KISS, YAGNI definitions) is knowledge Claude already possesses. The skill would benefit from being more concise and adding explicit refactoring workflow steps with validation checkpoints.
Suggestions
Reduce verbosity by removing explanations of well-known principles (DRY, KISS, YAGNI definitions) and focus on the project-specific conventions or non-obvious guidance
Add an explicit refactoring workflow with validation steps (e.g., 'ensure tests pass before refactoring -> make changes -> verify tests still pass')
Consider splitting detailed code examples into a separate EXAMPLES.md file, keeping SKILL.md as a concise overview with the checklist and quick reference tables
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | While the content is well-organized with tables and examples, it's quite lengthy (~400 lines) and explains concepts Claude already knows well (DRY, KISS, YAGNI are fundamental principles). The extensive Java examples, while good, could be more condensed. | 2 / 3 |
Actionability | Excellent actionability with fully executable Java code examples throughout. Each principle has clear before/after code comparisons that are copy-paste ready, and the refactoring quick reference table provides concrete techniques. | 3 / 3 |
Workflow Clarity | The checklist at the end provides a clear sequence for code review, but there's no explicit workflow for performing refactoring (e.g., validate tests pass -> refactor -> re-run tests). For a skill involving code changes, validation checkpoints would strengthen this. | 2 / 3 |
Progressive Disclosure | Content is well-structured with clear sections and tables, but everything is inline in one large file. The 'Related Skills' section at the end suggests external references exist, but the main content could benefit from splitting detailed examples into separate files. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%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 |
|---|---|---|
skill_md_line_count | SKILL.md is long (561 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
d9fda23
Table of Contents
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.