CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

72

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is ui in tw93/Waza

SKILL.md
Quality
Evals
Security

Quality

Content

85%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 is a well-structured, directive skill that routes to a clean one-level-deep reference bundle and sequences its workflow with explicit validation checkpoints. The main weakness is mild repetition in the design-reference routing that could be tightened for token efficiency.

Suggestions

Consolidate the repeated instructions to load references/design-reference.md into a single routing point to reduce token cost across the Hard Rules, Direction Lock, and Aesthetic Review sections.

The Mode Picker table and the 'Lock the Direction First' default overlap on routing for new surfaces; consider stating the default once and cross-referencing to trim the repeated guidance.

DimensionReasoningScore

Conciseness

The body is dense and directive, assuming Claude's competence (OKLCH, brutalist grid, tokens) with little concept explanation, but references/design-reference.md is re-routed to several times and the routing logic recurs across sections, so it is efficient with minor instances that could be trimmed. It is above the 3 anchor (which flags some unnecessary explanation) but does not reach the 5 anchor's every-token-earns-its-place tightness.

4 / 5

Actionability

It gives concrete executable guidance: exact token files to grep ("theme.ts, colors.ts, tokens.css, _variables.scss"), values to lift ("hex codes, spacing scale entries, font stacks, border radii"), a five-dimension lock sequence, named bans, and an aesthetic-review checklist. It is mostly actionable with minor gaps, above the 3 anchor (incomplete/pseudocode) but short of the 5 anchor's fully copy-paste-ready coverage of common cases.

4 / 5

Workflow Clarity

The flow is clearly sequenced (Mode Picker -> Lock the Direction First with five dimensions -> state direction -> write code -> Aesthetic Review -> handoff) with explicit checkpoints ("Do not write code until all five are resolved") and a feedback loop ("If any check fails, fix first"), matching the 5 anchor. It exceeds the 4 anchor, which allows minor validation gaps.

5 / 5

Progressive Disclosure

SKILL.md acts as a concise overview/router pointing to seven real one-level-deep reference files (all verified present) via markdown links and a mode-picker table, with content appropriately split (modes, design reference, data viz, motion each in their own file). This matches the 5 anchor's clear overview with well-signaled one-level-deep references and easy navigation.

5 / 5

Total

18

/

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.

The description is strong: it states a concrete capability, gives comprehensive natural-language and complaint-based triggers, explicitly answers both what and when, and draws a clear negative boundary. The only minor gap is that the action verbs are less varied than the deliverable list.

DimensionReasoningScore

Specificity

"Produces distinctive, production-grade UI for pages, components, visual interfaces, typography, and screenshot-driven polish" names several concrete deliverable types, but the actions cluster around a single verb ("Produces") rather than the multiple distinct verbs of a 5, so it sits at 4. It is above the 3 anchor (which allows only 1-2 concrete actions) but below the 5 anchor's comprehensive multi-action coverage.

4 / 5

Completeness

It explicitly states what ("Produces distinctive, production-grade UI for pages, components, visual interfaces, typography, and screenshot-driven polish") and when ("Use when users ask in any language for UI, page, component, frontend, typography..."), with concrete trigger phrases and a negative boundary ("Not for backend logic or data pipelines"). This matches the 5 anchor exactly and exceeds the 4 anchor, whose 'when' is less explicit.

5 / 5

Trigger Term Quality

"UI, page, component, frontend, typography, screenshot-grounded visual polish, or complaints that a screen looks unclear, ugly, inconsistent, or visually wrong" covers the natural keywords users say, plus complaint phrasings and "in any language", matching the 5 anchor's comprehensive coverage including synonyms. It clearly exceeds the 4 anchor, which expects a few natural terms missing.

5 / 5

Distinctiveness Conflict Risk

The UI/visual-frontend niche is clearly scoped and the explicit exclusion ("Not for backend logic or data pipelines") plus complaint-trigger phrasing give it distinct triggers with minimal conflict risk, matching the 5 anchor. It is clearly above the 4 anchor, which still allows minor overlap with closely related skills.

5 / 5

Total

19

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
tw93/Waza
Reviewed

Table of Contents

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.