CtrlK
BlogDocsLog inGet started
Tessl Logo

bencium-controlled-ux-designer

Expert UI/UX design guidance for unique, accessible interfaces. Use for visual decisions, colors, typography, layouts. Always ask before making design decisions. Use this skill when the user asks to build web components, pages, or applications.

61

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

The body is highly actionable with concrete code, named tools, real palettes, and a sequenced workflow with validation checkpoints, but it is an over-long monolith that re-teaches general design knowledge and references two detail files that are not present in the bundle.

Suggestions

Move the encyclopedic color, typography, motion, and UX-pattern reference material into the already-referenced DESIGN-SYSTEM-TEMPLATE.md / MOTION-SPEC.md files and actually ship them, leaving SKILL.md as a lean overview with the protocol, principles, and quick examples.

Cut re-explanations of concepts Claude already knows (Gestalt principles, what dark mode is, conversational-interface types, basic WCAG definitions) and keep only the skill's distinctive, opinionated guidance.

Add a short 'When to use / decision protocol' quick-start at the top so the critical 'always ask first' rule and tool stack are visible without scrolling past the philosophy section.

DimensionReasoningScore

Conciseness

The body is a ~700-line monolith that re-explains concepts Claude already knows (Gestalt principles, what dark mode is, conversational-interface taxonomies, direct-manipulation examples, 44px touch targets), but it also carries substantial genuinely specific and actionable guidance, so it sits at 'mostly useful but could be tightened' rather than the lean anchor.

2 / 3

Actionability

It provides copy-paste-ready code (shadcn Button imports, Tailwind class strings, framer-motion motion props, responsive clamp() CSS), concrete palettes (slate-50/teal-500), a real type scale in rem, and named tools (phosphor-icons, sonner, playwright MCP), matching the fully-executable anchor.

3 / 3

Workflow Clarity

The Design Workflow is explicitly sequenced (Understand Context -> Explore Options -> Implement Iteratively -> Validate) with a validation checkpoint ('Use playwright MCP to test visual changes', 'Test at each stage') plus Design Decision and Testing checklists, satisfying the clear-sequence-with-validation anchor; the 'ALWAYS ASK before implementing' protocol acts as an additional gating checkpoint.

3 / 3

Progressive Disclosure

Two references are one-level-deep and clearly signaled ('see DESIGN-SYSTEM-TEMPLATE.md', 'see MOTION-SPEC.md'), but neither referenced file actually exists in the bundle, and the bulk of the color/typography/motion/UX detail is inline in a single monolithic file rather than split out, matching the 'some structure but content that should be separate is inline' anchor.

2 / 3

Total

10

/

12

Passed

Description

67%

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 answers what the skill does and when to use it with explicit trigger clauses and third-person voice, but its action language is abstract ('guidance') and its triggers are broad enough to risk overlap with generic web-building skills.

Suggestions

Replace the abstract verb 'guidance' with concrete actions, e.g. 'Designs and restyles UI components, palettes, typography, and layouts'.

Add narrower, distinctive trigger terms that users say for design specifically ('redesign', 'design system', 'make this look better', 'pick colors/fonts') to separate it from general web-building skills.

Tighten the duplicate trigger phrasing — 'Use for visual decisions...' and 'Use this skill when...' say nearly the same thing and could be merged.

DimensionReasoningScore

Specificity

The description names the domain ('UI/UX design guidance for unique, accessible interfaces') and several sub-areas ('visual decisions, colors, typography, layouts'), but the only named action is the abstract 'guidance' rather than concrete verbs like build, restyle, or audit, so it falls short of the multi-specific-concrete-actions anchor.

2 / 3

Completeness

It states both what the skill does ('Expert UI/UX design guidance for unique, accessible interfaces') and explicit when-to-use triggers ('Use for visual decisions...' and 'Use this skill when the user asks to build web components, pages, or applications'), satisfying the explicit what-and-when anchor; the present 'Use when' clauses keep it above the cap of 2.

3 / 3

Trigger Term Quality

It includes natural user-facing terms ('web components, pages, or applications', 'colors, typography, layouts', 'UI/UX'), but misses common variations users actually say ('redesign', 'design system', 'make it look better', 'styling'), matching the 'some relevant keywords but missing common variations' anchor rather than full coverage.

2 / 3

Distinctiveness Conflict Risk

The 'UI/UX design' framing gives it a recognizable niche, but the trigger 'build web components, pages, or applications' is broad and would overlap with general frontend/web-development skills, fitting the 'somewhat specific but could still overlap' anchor rather than a clearly non-conflicting niche.

2 / 3

Total

9

/

12

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

skill_md_line_count

SKILL.md is long (739 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
bencium/bencium-marketplace
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.