aiox-ux-design-expert

Activate the AIOX UX/UI Designer & Design System Architect agent (Uma). Complete design workflow - user research, wireframes, design systems, token extraction, component building, and quality assurance Trigger when user asks to ux-design-expert, or says 'activate ux-design-expert', 'switch to ux-design-expert', '@ux-design-expert'.

Quality

60%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.kimi/skills/aiox-ux-design-expert/SKILL.md

Quality

Content

38%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 content has a clear phased workflow structure and concrete command routing, but it is heavily padded with an inline persona/YAML block, lacks validation checkpoints on batch operations, and relies on external files that are not bundled. Progressive disclosure is weak because the bulk of the definition is inlined rather than split into reference files.

Suggestions

Extract the large inline YAML agent definition (persona_profile, vocabulary, customization, dependencies) into bundled reference files under references/ and keep SKILL.md as a lean overview with one-level-deep links.

Add explicit validation/verification checkpoints to the batch and destructive workflow phases (audit → consolidate → migrate), e.g., confirm pattern counts before/after consolidation and validate token schema before migration.

Remove redundant repetition (the Star Commands table, the commands YAML, Quick Commands, and the guide all restate the same commands) and drop non-essential persona padding such as zodiac sign and Portuguese vocabulary.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose: a large inline YAML agent definition repeats the command table and principles already shown above, and includes padded persona details (zodiac sign, Portuguese vocabulary, emoji frequency) that do not earn their tokens.	2 / 5
Actionability	Concrete command-to-task file mappings (e.g., "*audit → Read(\".aiox-core/development/tasks/audit-codebase.md\")") give routing guidance, but the actual executable instructions live in external files not present in the bundle, leaving the body itself without copy-paste-ready steps.	3 / 5
Workflow Clarity	Phases 1-5 are clearly sequenced with greenfield/brownfield/complete paths, but batch operations like audit, consolidate, and *migrate lack explicit validation or verification checkpoints, capping clarity at 3.	3 / 5
Progressive Disclosure	No references/, scripts/, or assets/ bundle files exist, yet the body inlines a monolithic ~400-line YAML agent definition that clearly belongs in separate files, and its references point to non-bundled external .aiox-core paths.	2 / 5
	Total	10 / 20 Passed

Description

81%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 clearly states what the skill does and when to trigger it, with a concrete list of workflow capabilities and explicit activation phrases. Its main weakness is narrow trigger-term variation, relying almost entirely on the agent name rather than natural domain synonyms.

Suggestions

Add natural domain trigger terms (e.g., "design system", "wireframe", "design tokens", "UX research", "WCAG audit") so the skill fires when users describe the task rather than only the agent name.

Tighten broad capabilities like "design systems" and "quality assurance" into more concrete actions to lift specificity.

Fix the run-on sentence (missing period before "Trigger") for clearer parsing of the what/when boundary.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ("user research, wireframes, design systems, token extraction, component building, and quality assurance"), but several are broad domains rather than crisp actions, leaving minor coverage gaps.	4 / 5
Completeness	It explicitly answers both what ("Complete design workflow - user research, wireframes...") and when ("Trigger when user asks to ux-design-expert, or says...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Trigger phrases ("ux-design-expert", "activate ux-design-expert", "switch to ux-design-expert", "@ux-design-expert") are all variants of the same root term and omit natural domain synonyms like "design system" or "wireframe" that a user would actually say.	3 / 5
Distinctiveness Conflict Risk	The UX/UI design-system niche is clear and triggers are tied to a specific agent name, but broad phrases like "design systems" and "component building" create minor overlap risk with general frontend or dev skills.	4 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (576 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

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

Reviewed: 2 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.