CtrlK
BlogDocsLog inGet started
Tessl Logo

bencium-innovative-ux-designer

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

60

Quality

70%

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

Fix and improve this skill with Tessl

tessl review fix ./bencium-innovative-ux-designer/skills/bencium-innovative-ux-designer/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

52%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 is actionable and well-sequenced, but it is significantly over-padded with beginner-level explanations and repeated prohibitions, and its progressive-disclosure structure is broken by references to bundle files that do not exist. Trimming redundant sections and either creating or removing the dangling reference files would most improve it.

Suggestions

Create the advertised bundle files (ACCESSIBILITY.md, MOTION-SPEC.md, RESPONSIVE-DESIGN.md) or remove the dangling references, so navigation actually resolves.

Cut repetition: the banned-fonts/banned-aesthetics rules appear in Core Philosophy, Visual Standards, Interaction Design, and Common Patterns — consolidate into one canonical list and reference it.

Remove beginner-level explanations Claude already knows (line-height 1.5, 44px touch targets, conversational-interface taxonomy) to reclaim token budget.

DimensionReasoningScore

Conciseness

At ~720 lines the body is noticeably verbose: it explains concepts Claude already knows (line-height 1.5, 44px touch targets, what color contrast is, conversational-interface taxonomy) and repeats the anti-Inter/Roboto/glass-morphism rules across Core Philosophy, Visual Standards, Interaction Design, and Common Patterns. It is above 1 because the actionable snippets carry real value, but the padding and repetition keep it below the midpoint.

2 / 5

Actionability

Provides mostly executable guidance — shadcn/Phosphor/sonner/clsx import snippets, a concrete typographic scale table, and copy-paste tsx button/headline examples. It is not 5 because the referenced MOTION-SPEC.md does not exist and some guidance stays abstract (e.g., 'create atmosphere').

4 / 5

Workflow Clarity

The Design Thinking Protocol and Design Workflow give a clear sequence (ask context → present 2-3 options → implement iteratively → validate with playwright MCP) with a design-decision checklist and validation step. It is not 5 because validation is high-level ('validate', 'test across devices') rather than a rigorous fix-and-retry feedback loop.

4 / 5

Progressive Disclosure

The body advertises 'Progressive Disclosure Files' (ACCESSIBILITY.md, MOTION-SPEC.md, RESPONSIVE-DESIGN.md) and points inline to MOTION-SPEC.md, but none of these files exist in the bundle — dangling references that cannot be navigated. Large chunks (full color-system architecture, typography scale, UX pattern catalog) that belong in separate files are also inlined, placing it below the 3 anchor.

2 / 5

Total

12

/

20

Passed

Description

87%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 concrete capabilities, gives an explicit 'Use when...' trigger clause, and carves out a distinctive niche. Minor improvements would add more synonyms (UI, dashboard, landing page) to broaden natural trigger coverage.

DimensionReasoningScore

Specificity

Lists several concrete actions ('Create distinctive, production-grade frontend interfaces', 'build web components, pages, or applications', 'Generates creative, polished code that avoids generic AI aesthetics'), but coverage is not fully comprehensive, so it sits at the 4 anchor rather than 5.

4 / 5

Completeness

Explicitly answers both what ('Create distinctive, production-grade frontend interfaces... Generates creative, polished code') and when ('Use this skill when the user asks to build web components, pages, or applications') with concrete trigger phrases, matching the 5 anchor; it is not a 4 because the 'when' is explicit and specific rather than weakly implied.

5 / 5

Trigger Term Quality

Includes natural user-facing terms like 'web components, pages, or applications' and 'frontend interfaces', but misses common synonyms such as 'UI', 'dashboard', 'landing page', or 'React', leaving it just below comprehensive.

4 / 5

Distinctiveness Conflict Risk

The anti-'AI slop'/distinctive-aesthetic niche with explicit triggers ('avoids generic AI aesthetics') gives it a clear, low-conflict identity unlikely to fire for unrelated skills.

5 / 5

Total

18

/

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

skill_md_line_count

SKILL.md is long (719 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.