clean-code

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

Quality

63%

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 ./.agents/skills/clean-code/SKILL.md

Quality

Content

77%

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

A terse, well-structured standards skill with concrete rules and a clear validation loop, weakened by internal redundancy and a monolithic structure with no progressive disclosure. It is strong on actionability and workflow but average on token efficiency and file organization.

Suggestions

Remove or condense the Summary table, which duplicates the Anti-Patterns and Do/Don't sections, to cut redundant tokens.

Move the 15-row agent-to-script verification mapping into a separate reference file and link to it from SKILL.md, reducing inline bulk.

Split detailed reference material (e.g., full naming and function rule tables) into a linked reference so SKILL.md stays a concise overview.

Dimension	Reasoning	Score
Conciseness	Mostly lean table-based rules with no concept-explanation fluff, but the Summary table duplicates the Anti-Patterns/Do-Don't content and the 15-row verification-scripts table is reference bulk that could be tightened or split out.	2 / 3
Actionability	Provides concrete numeric thresholds ('Max 20 lines', 'Max 3 arguments'), inline examples ('userCount not n'), and copy-paste executable script commands, meeting the fully-actionable anchor for an instruction skill.	3 / 3
Workflow Clarity	The script-output section is a clearly sequenced READ -> SUMMARIZE -> ASK -> fix -> re-run loop with an explicit validation checkpoint, and the before-edit and self-check sections provide checklists for the process.	3 / 3
Progressive Disclosure	Well-organized into headed sections but monolithic: no bundle files or one-level references exist, and the large agent-to-script mapping table is inline content that could live in a separate reference file.	2 / 3
	Total	10 / 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 is terse and fluff-free, naming the domain and key constraints, but it reads as a list of qualities rather than concrete actions and lacks an explicit trigger clause. It is adequate but undifferentiated.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers (e.g., 'Use when writing, reviewing, or refactoring code, or when applying coding standards').

Reframe qualities as concrete actions (e.g., 'Enforces small functions, clear naming, and guard clauses; removes over-engineering and obvious comments') to lift specificity.

Include common user terms such as 'clean code' or 'refactor' to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('coding standards') and concrete constraints like 'no over-engineering, no unnecessary comments', but lists qualities rather than specific actions, so it falls short of the multiple-concrete-actions anchor.	2 / 3
Completeness	States what the skill enforces, but the description field has no explicit 'Use when...' trigger clause, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Includes some natural terms users say ('coding standards', 'no over-engineering') but misses common variations like 'clean code', 'refactor', or 'best practices', matching the partial-coverage anchor.	2 / 3
Distinctiveness Conflict Risk	'Pragmatic coding standards' is moderately specific but broad enough to overlap with linting, testing, and other code-quality skills, matching the 'somewhat specific but could overlap' anchor.	2 / 3
	Total	8 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: vudovn/ag-kit
Path: .agents/skills/clean-code/SKILL.md
Commit: 04514f0

Reviewed: about 12 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.