ui

Produces distinctive, production-grade UI for pages, components, visual interfaces, typography, and screenshot-driven polish. Use when users ask in any language for UI, page, component, frontend, typography, screenshot-grounded visual polish, or complaints that a screen looks unclear, ugly, inconsistent, or visually wrong. Not for backend logic or data pipelines.

Quality

86%

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

78%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.

A mature, opinionated skill body that routes cleanly to real one-level-deep references and gives concrete, executable design rules with specific values. It is slightly long in its exception-handling prose and could make intermediate validation gates as explicit as the final aesthetic review.

Suggestions

Tighten the direction-lock clarification-round and exception prose (app-shell, native-app, data-dashboard) into terser rules to reclaim tokens.

Add an explicit mid-build validation checkpoint (not only the handoff aesthetic review) so drift is caught before the final pass.

Consolidate the two overlapping aesthetic-quality references into one canonical pointer to remove the compatibility-map caveat that currently consumes a line.

Dimension	Reasoning	Score
Conciseness	Dense and opinionated, assuming Claude's competence without explaining basics, but the elaborate exception mechanics (clarification rounds, app-shell/native-app/data-dashboard carve-outs) could be tightened in places.	4 / 5
Actionability	Concrete and executable guidance throughout: named hard bans, specific direction dimensions, exact values to lift (hex codes, spacing scale, border radii) and a precise shadow/lightness minimum ("sidebar vs main >=4% lightness difference", "0 1px 3px rgba(0,0,0,0.10)").	4 / 5
Workflow Clarity	Clear sequence from preflight through mode pick, direction lock, thesis summary, build, and a handoff aesthetic-review checklist with fix-first feedback, though per-step validation gates are less explicit than the final review.	4 / 5
Progressive Disclosure	SKILL.md is a well-signaled overview with a mode-picker routing table pointing to one-level-deep reference files (design-reference, mode-quick-fix, mode-screenshot-iteration, mode-generated-asset, etc.), all of which exist under references/.	5 / 5
	Total	17 / 20 Passed

Description

95%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.

A strong, third-person description that crisply states what the skill does and when to use it, with rich multilingual trigger terms and an explicit scope boundary. The only minor gap is verb diversity, relying largely on "Produces" across several objects.

Dimension	Reasoning	Score
Specificity	Names the UI domain and several concrete capability areas ("pages, components, visual interfaces, typography, and screenshot-driven polish"), though it relies on one main verb ("Produces") plus "polish" rather than many distinct actions, so it stops just short of comprehensive.	4 / 5
Completeness	Explicitly answers both what ("Produces distinctive, production-grade UI...") and when ("Use when users ask..."), with concrete trigger phrases and a clear negative boundary ("Not for backend logic or data pipelines").	5 / 5
Trigger Term Quality	Comprehensive natural trigger coverage including synonyms and complaint phrasing ("UI, page, component, frontend, typography, screenshot-grounded visual polish" plus "unclear, ugly, inconsistent, or visually wrong"), explicitly spanning any language.	5 / 5
Distinctiveness Conflict Risk	Clear niche (UI/visual polish) with distinct triggers and an explicit out-of-scope clause ("Not for backend logic or data pipelines"), giving minimal conflict risk with adjacent skills.	5 / 5
	Total	19 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: tw93/Waza
Path: plugins/waza/skills/ui/SKILL.md
Commit: f902996

Reviewed: 1 day 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.