clean-code

Pragmatic coding standards - concise, direct, no over-engineering, no unnecessary comments

Quality

25%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

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

Quality

Content

50%

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

This skill is a well-structured but overly broad coding standards document that largely restates principles Claude already knows (SRP, DRY, KISS, YAGNI, naming conventions). Its strengths are the table-based format for quick scanning and the dependency-checking workflow before edits. Its weaknesses are the lack of concrete executable examples, verbose coverage of common knowledge, and vague verification steps.

Suggestions

Remove or drastically condense sections on well-known principles (SRP, DRY, KISS, naming conventions) since Claude already knows these — focus only on project-specific deviations or preferences

Add concrete before/after code examples showing the specific coding style expected, rather than abstract rules like 'keep functions small'

Replace vague verification checklist items ('Did I test/verify the change?') with specific commands or tool invocations (e.g., 'Run `npx tsc --noEmit` and `npm run lint`')

Inline at least the agent-script mapping content or provide the actual verification commands, since the sub-skill references cannot be validated and the main skill lacks actionable verification steps

Dimension	Reasoning	Score
Conciseness	The table-based format is efficient, but the skill covers many well-known coding principles (SRP, DRY, KISS, YAGNI) that Claude already knows deeply. The 'AI Coding Style' and self-check sections add some unique value, but much of this is restating common knowledge. The repeated 🔴 CRITICAL markers and emphasis formatting add visual noise.	2 / 3
Actionability	The skill provides general rules and anti-patterns but lacks concrete, executable examples. The one code snippet (dependency check) is a conceptual diagram rather than executable code. Most guidance is abstract ('keep functions small', 'single responsibility') rather than showing specific before/after code transformations Claude could directly apply.	2 / 3
Workflow Clarity	The 'Before Editing ANY File' section and 'Self-Check Before Completing' section provide a reasonable workflow with checkpoints, but the verification steps are vague ('Did I test/verify the change?') without specifying how. The 'Verification Scripts (MANDATORY)' section references sub-skills but provides no actual scripts or commands inline, leaving a gap in the workflow.	2 / 3
Progressive Disclosure	The skill references 5 sub-skill files for verification/script handling, which is good progressive disclosure structure. However, no bundle files were provided to verify these references exist, and the main SKILL.md itself is quite long with content that could be split out (e.g., naming conventions, function rules could be separate reference files). The sub-skill references are well-signaled but the overall organization mixes overview content with detailed rules.	2 / 3
	Total	8 / 12 Passed

Description

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 description reads as a set of vague coding principles rather than a functional skill description. It lacks concrete actions, natural trigger terms, explicit 'when to use' guidance, and distinctiveness from other coding-related skills. It would be very difficult for Claude to reliably select this skill from a pool of alternatives.

Suggestions

Add specific concrete actions the skill performs, e.g., 'Applies minimalist coding conventions: avoids redundant comments, prefers simple implementations over abstractions, keeps functions short and focused.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about code style, coding conventions, writing clean code, simplifying code, or removing unnecessary complexity.'

Differentiate from other coding skills by specifying the scope or language context, e.g., 'Enforces pragmatic Python/JS coding standards during code generation and review tasks.'

Dimension	Reasoning	Score
Specificity	The description uses vague, abstract language like 'pragmatic coding standards' and 'no over-engineering' without listing any concrete actions. It describes a philosophy rather than specific capabilities.	1 / 3
Completeness	The description weakly addresses 'what' (coding standards) but provides no 'when' clause or explicit trigger guidance. There is no 'Use when...' or equivalent, which per the rubric caps completeness at 2, and the 'what' is itself too vague to merit even a 2.	1 / 3
Trigger Term Quality	The terms used ('pragmatic', 'over-engineering', 'unnecessary comments') are not natural keywords a user would say when requesting help. Users are more likely to say 'write clean code', 'code style', 'coding conventions', or 'code review'.	1 / 3
Distinctiveness Conflict Risk	The description is extremely generic and could overlap with any coding skill, linting skill, code review skill, or style guide skill. 'Coding standards' is too broad to carve out a distinct niche.	1 / 3
	Total	4 / 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: Dokhacgiakhoa/antigravity-ide
Commit: c4a059b

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.