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

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

50%

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 and offers concrete examples plus a useful self-check checklist, but it functions as a condensed restatement of widely-known Clean Code principles rather than novel, executable, or workflow-driven guidance. It is efficient and clear but does not fully assume Claude's existing knowledge or provide actionable multi-step procedures.

Suggestions

Trim or externalize the widely-known chapter summaries (naming, formatting, smells) and keep only the judgment calls or team-specific standards Claude would not already know.

Add a short, executable workflow for applying the skill to a real change (e.g. identify smells -> refactor one function -> run tests -> re-checklist) with a validation checkpoint.

Split the detailed chapter references into a separate references file and keep SKILL.md as a lean overview, adding a clearly signaled one-level link to it.

Dimension	Reasoning	Score
Conciseness	The body is a compact, well-structured checklist rather than padded prose, but it largely restates Clean Code heuristics Claude already knows (e.g. 'Don't Return Null', the Law of Demeter, F.I.R.S.T.), so it includes some unnecessary explanation rather than only novel guidance.	2 / 3
Actionability	It provides concrete, specific examples (e.g. `elapsedTimeInDays` vs `d`, `a.getB().getC().doSomething()`) and an applicable self-check checklist, but as a principles reference it offers no executable commands or copy-paste-ready code, so the guidance is concrete yet incomplete as actionable instruction.	2 / 3
Workflow Clarity	The Implementation Checklist gives a sequenced set of checks and the 'When to Use' section lists contexts, but there is no multi-step workflow with validation checkpoints or a fix-retry feedback loop, leaving the sequence present but checkpoints implicit.	2 / 3
Progressive Disclosure	No bundle files exist, so the skill is a single self-contained SKILL.md that is well-organized into clear numbered sections; however at ~90 lines it reads as one monolithic reference that could be split into a detailed reference file rather than a lean overview, keeping it below the well-signaled one-level reference anchor.	2 / 3
	Total	8 / 12 Passed

Description

50%

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 establishes a recognizable niche through its book and author reference and a clear high-level purpose, but it lacks concrete capability actions and any explicit 'Use when...' trigger guidance. These gaps cap specificity, trigger quality, and completeness at the midpoint level.

Suggestions

Add concrete actions the skill performs, e.g. 'review code for smells, refactor functions, enforce naming conventions, and improve test structure'.

Add an explicit 'Use when...' clause with natural trigger terms such as 'refactoring', 'code review', 'code smells', or 'cleaning up code'.

Tighten the mission-statement phrasing into third-person capability statements (e.g. 'Transforms working code into maintainable, readable code following Clean Code principles').

Dimension	Reasoning	Score
Specificity	It names a clear domain ("Clean Code" by Robert C. Martin) and a transformation action ("transform 'code that works' into 'code that is clean'"), but lists no concrete actions like naming, refactoring, or error handling — closer to a mission statement than a list of capabilities, so it sits below the multiple-specific-actions anchor.	2 / 3
Completeness	It states what the skill does at a high level, but there is no 'Use when...' clause or equivalent explicit trigger guidance, and the judging guideline caps completeness at 2 when that trigger guidance is missing.	2 / 3
Trigger Term Quality	"Clean Code" and "Uncle Bob" are recognizable natural terms a user might say, but common variations a user would actually invoke (refactor, code review, code smells, clean up my code) are missing, placing it at 'some relevant keywords but missing common variations.'	2 / 3
Distinctiveness Conflict Risk	The explicit tie to a named book and author gives it a recognizable niche, but the absence of explicit triggers means it could still overlap with general coding, refactoring, or review skills, so it does not reach the distinct-trigger anchor.	2 / 3
	Total	8 / 12 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: sickn33/antigravity-awesome-skills
Commit: 615669b

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.