ux-review

Validates a UX spec, HUD design, or interaction pattern library for completeness, accessibility compliance, GDD alignment, and implementation readiness. Produces APPROVED / NEEDS REVISION / MAJOR REVISION NEEDED verdict with specific gaps.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

92%

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

A highly actionable, well-sequenced validation skill with concrete checklists, an explicit output template, and no concept-teaching fluff. Its only real weakness is progressive disclosure: at this size it should split the three checklists and/or the output template into reference files rather than keeping everything inline in SKILL.md.

Suggestions

Move the three detailed checklists (Phase 3A/3B/3C) and the Phase 4 output template into reference files (e.g. references/spec-checklist.md, references/hud-checklist.md, references/output-template.md), keeping SKILL.md as an overview that signals them one level deep.

De-duplicate the verdict-level definitions, which currently appear in the Overview and again in Phase 5, to tighten token use.

Add a brief 'Quick reference' pointer at the top so Claude can jump to the relevant checklist by document type without scanning all three.

Dimension	Reasoning	Score
Conciseness	The body is dense and purposeful — operationalized checklists, a concrete output template, and argument handling — with no teaching of concepts Claude already knows (no 'what is accessibility' or 'what is a GDD' padding), matching the lean, every-token-earns-its-place level-3 anchor rather than the level-2 'includes some unnecessary explanation' case.	3 / 3
Actionability	For an instruction-only QA skill, the guidance is maximally concrete: each checkbox is a precise testable criterion ('no data element has UI listed as the owner', 'screen opens within Xms') and Phase 4 provides a copy-paste-ready verdict template, meeting the level-3 fully-executable-guidance anchor.	3 / 3
Workflow Clarity	Phases 1-5 are explicitly sequenced (parse args -> load cross-reference context -> run the right checklist -> output verdict -> collaborative protocol) with the checklist itself acting as the validation checkpoint and a re-run feedback loop ('re-run /ux-review'); the destructive-ops cap does not apply since the skill is explicitly READ-ONLY.	3 / 3
Progressive Disclosure	The skill is a well-organized single file but fully monolithic — the three large checklists (spec/HUD/patterns) and the full output template are all inline with no references to separate files; the under-50-lines/simple-skill exception does not apply to a 250+ line multi-checklist skill, so this sits at the level-2 'content that should be separate is inline' anchor rather than level 3.	2 / 3
	Total	11 / 12 Passed

Description

82%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific, third-person description with concrete capabilities and a clear distinct niche, but it omits any explicit 'Use when' trigger clause, which caps completeness at 2. Adding a natural-language trigger clause would raise it to a full-score description.

Suggestions

Add an explicit 'Use when...' clause naming the natural trigger moments, e.g. 'Use when reviewing a UX spec, HUD design, or interaction-pattern library before handoff to implementation.'

Keep the concrete action list and verdict phrasing as-is; they are the strongest parts and should not be trimmed.

Dimension	Reasoning	Score
Specificity	Names several concrete validation actions ('completeness, accessibility compliance, GDD alignment, and implementation readiness') plus a concrete verdict output, matching the anchor for listing multiple specific concrete actions rather than a single level-2 'names domain and some actions' description.	3 / 3
Completeness	It clearly answers 'what does this do' but lacks any explicit 'Use when...' or equivalent trigger guidance stating when Claude should invoke it; per the judging guideline, a missing explicit trigger clause caps completeness at 2 even though the 'what' is strong enough for level 3.	2 / 3
Trigger Term Quality	Uses the natural domain vocabulary a user in this pipeline would say ('UX spec', 'HUD design', 'interaction pattern library', 'accessibility', 'GDD alignment', 'implementation readiness'), giving good coverage of terms a user would actually invoke rather than jargon-only or generic terms at level 1.	3 / 3
Distinctiveness Conflict Risk	The niche is narrow and domain-specific (game UX specs, HUD design, GDD alignment with an APPROVED/NEEDS REVISION/MAJOR REVISION verdict), making it clearly distinguishable and unlikely to trigger for the wrong skill, matching the level-3 'clear niche with distinct triggers' anchor rather than the overlapping level-2 case.	3 / 3
	Total	11 / 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/ux-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.