code-review

Performs an architectural and quality code review on a specified file or set of files. Checks for coding standard compliance, architectural pattern adherence, SOLID principles, testability, and performance concerns.

Quality

68%

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 ./.claude/skills/code-review/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.

The body is a well-sequenced, actionable review workflow with concrete commands and a clear output template. Its main weakness is that a large amount of inline content (the output template, checklists) could be moved to reference files for better progressive disclosure.

Suggestions

Extract the Phase 8 output template into a references file (e.g. references/review-output-template.md) and link to it, keeping only the verdict categories inline.

Move the detailed Standards/Architecture/SOLID checklists into a reference file referenced once, reducing inline length.

Tighten Phase 3's prose; the ADR lookup priority and deviation classification could be condensed into a compact list.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and procedural without explaining basic concepts, but the Phase 8 output template and Phase 3 ADR prose add length that could be tightened.	2 / 3
Actionability	Provides concrete commands ('git log --oneline -- [file]', explicit Task-spawning instructions) and a fully specified output template with checklists, giving copy-paste-ready guidance for an instruction/workflow skill.	3 / 3
Workflow Clarity	A clearly sequenced 9-phase workflow with numbered priority order for ADR lookup, explicit skip conditions ('[TO BE CONFIGURED]'), and a defined error/review loop for ADR violations.	3 / 3
Progressive Disclosure	Content is well-organized into phases with no nested references, but it is a single ~175-line monolithic document with no bundle files to offload the long output template or ADR classification details.	2 / 3
	Total	10 / 12 Passed

Description

60%

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 specific and clearly communicates the review capabilities, but it lacks any explicit 'when to use' trigger guidance. Adding a 'Use when...' clause would lift completeness and distinctiveness.

Suggestions

Append a 'Use when ...' clause naming natural triggers (e.g. 'Use when the user asks for a code review, wants to check SOLID compliance, or needs architectural sign-off on changed files').

Include common phrasings a user might say ('review my code', 'check coding standards', 'SOLID review') to improve trigger-term coverage.

Add a distinguishing phrase that separates this from a generic review skill, such as emphasizing ADR and engine-specialist checks.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete review actions: 'architectural and quality code review', 'coding standard compliance', 'architectural pattern adherence', 'SOLID principles, testability, and performance concerns'.	3 / 3
Completeness	It clearly answers 'what' the skill does, but omits any 'when to use it' trigger guidance, which caps completeness at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	Relevant technical terms ('code review', 'SOLID principles', 'testability') are present, but there is no 'Use when...' clause and coverage of natural phrasings a user would say is partial.	2 / 3
Distinctiveness Conflict Risk	The architectural/SOLID review niche is somewhat specific, but the absence of explicit distinct triggers means it could still overlap with general review skills.	2 / 3
	Total	9 / 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: Donchitos/Claude-Code-Game-Studios
Path: .claude/skills/code-review/SKILL.md
Commit: 984023d

Reviewed: 3 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.