aiox-ux-design-expert

Activate Uma (ux-design-expert) for UX/UI Designer & Design System Architect. Complete design workflow - user research, wireframes, design systems, token extraction, component building, and quality assurance

Quality

58%

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/AIOX/agents/ux-design-expert/SKILL.md

Quality

Content

50%Weight 40%Scale 1-5

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

The body provides concrete commands and a clear phased workflow, but it is heavily padded with duplicated listings and persona fluff, lacks validation checkpoints in its batch/destructive workflows, and inlines a monolithic config block that belongs in separate files.

Suggestions

De-duplicate the command listings (they appear in the customization map, the commands section, and Quick Commands) and remove persona padding (zodiac, Portuguese vocabulary, archetypal greetings) to recover token budget.

Add explicit validation checkpoints between phases, e.g. require *audit-tailwind-config / migration-readiness-checklist to pass before proceeding from tokenization to migration.

Externalize the large embedded YAML agent config into a referenced file so SKILL.md acts as a lean overview pointing to one-level-deep materials.

Dimension	Reasoning	Score
Conciseness	The ~500-line body is noticeably verbose: command lists are duplicated three times (customization command-to-task map, the commands section, and the Quick Commands markdown), and persona fluff (zodiac "♋ Cancer", Portuguese vocabulary, archetypal greetings) adds padding Claude does not need.	2 / 5
Actionability	Concrete star-prefixed commands are mapped to specific file paths (e.g. *research → Read(".aiox-core/development/tasks/ux-user-research.md")) and example session transcripts show real usage, giving mostly executable guidance with minor gaps.	4 / 5
Workflow Clarity	A clear 5-phase sequence with per-phase commands and outputs is present, but there are no explicit validation checkpoints for batch/destructive operations like migrate and consolidate, which per the rubric caps workflow clarity at 3.	3 / 5
Progressive Disclosure	No bundle files exist (references/scripts/assets absent), and a large monolithic YAML config block is inlined in SKILL.md that should be externalized; task-file references are clearly signaled via the command map, but the overall split is imperfect.	3 / 5
	Total	12 / 20 Passed

Description

66%Weight 40%Scale 1-5

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 conveys a clear purpose and reasonably specific actions for a UX/design-system skill, but it omits any explicit "Use when..." trigger guidance, which limits its completeness. Keywords are good but lack synonym coverage.

Suggestions

Add an explicit trigger clause, e.g. "Use when conducting user research, creating wireframes, auditing or building design systems, extracting design tokens, or building accessible components."

Broaden trigger terms with natural synonyms users actually say ("mockups", "prototypes", "UI design", "design tokens", "component library").

Reframe vague domain entries ("design systems", "quality assurance") as concrete actions to lift specificity toward 5.

Dimension	Reasoning	Score
Specificity	Lists several concrete workflow actions ("user research, wireframes, design systems, token extraction, component building, and quality assurance"), though a few entries like "design systems" and "quality assurance" read as domains rather than discrete actions, leaving minor coverage gaps.	4 / 5
Completeness	The "what" is clearly stated ("Complete design workflow - user research, wireframes, ..."), but there is no "Use when..." clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Includes natural terms a user would say ("UX/UI", "wireframes", "design systems", "design tokens", "component building"), but misses common synonyms such as "mockups", "prototypes", or "UI design".	4 / 5
Distinctiveness Conflict Risk	The "UX/UI Designer & Design System Architect" framing carves a clear niche with distinct triggers, with only minor overlap risk against general frontend or architect skills.	4 / 5
	Total	15 / 20 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
skill_md_line_count	SKILL.md is long (504 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: SynkraAI/aiox-core
Path: .claude/skills/AIOX/agents/ux-design-expert/SKILL.md
Commit: 4ef6530

Reviewed: 23 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.