CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

frontend-design

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.

84

1.29x
Quality

85%

Does it follow best practices?

Impact

80%

1.29x

Average score across 3 eval scenarios

SecuritybySnyk

—

The risk profile of this skill

The canonical home for this skill is frontend-design in majiayu000/claude-skill-registry

SKILL.md
Quality
Evals
Security

Quality

Content

71%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-organized, largely actionable design guide appropriate to a single-purpose skill, with concrete technique names and a sensible think-then-implement sequence. Its main weakness is redundancy — repeated anti-generic injunctions, a triple-stated typography instruction, and a motivational closing line — that inflates token cost without adding guidance.

Suggestions

Collapse the typography bullet to one formulation: 'Choose beautiful, characterful fonts; avoid Inter, Roboto, Arial, and system defaults; pair a distinctive display font with a refined body font' removes the triple restatement.

Merge the two anti-generic passages (the 'NEVER use generic AI-generated aesthetics' paragraph and the 'NEVER converge on common choices (Space Grotesk...)' sentence) into a single list of banned defaults.

Delete the closing motivational line ('Remember: Claude is capable of extraordinary creative work. Don't hold back...') — it instructs nothing.

DimensionReasoningScore

Conciseness

Mostly efficient, but noticeably padded in places: the typography bullet states the same instruction three ways ('beautiful, unique, and interesting... distinctive choices... unexpected, characterful font choices'), the 'NEVER use generic AI-generated aesthetics' paragraph and the later 'NEVER converge on common choices' sentence duplicate each other, and the closing 'Remember: Claude is capable of extraordinary creative work' line is motivational filler — more than the minor trimming of anchor 4.

3 / 5

Actionability

Guidance is mostly executable for an instruction-only skill: concrete technique names throughout ('Avoid generic fonts like Arial and Inter', 'Use CSS variables for consistency', 'staggered reveals (animation-delay)', 'Use Motion library for React', 'gradient meshes, noise textures, geometric patterns... custom cursors, and grain overlays') plus a specific clarification mechanism ('use mcp-feedback-enhanced (e.g., ask_followup_question)'). Minor gaps: no example font pairings or code snippets.

4 / 5

Workflow Clarity

A clear two-phase sequence is present — Design Thinking (purpose, tone, constraints, differentiation, clarification) followed by implementation with listed quality criteria — and the pre-implementation clarification question acts as a feedback loop. It sits above anchor 3's missing checkpoints but below anchor 5, as there is no post-implementation validation or review step.

4 / 5

Progressive Disclosure

The skill is under 50 lines, self-contained with no external references needed, and organized into clear sections ('Design Thinking', 'Frontend Aesthetics Guidelines'), matching the rubric's simple-skill guideline that well-organized sections alone warrant a 5.

5 / 5

Total

16

/

20

Passed

Description

91%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 description: it explicitly states what the skill does and when to use it, with rich natural trigger terms and synonyms. The only weaknesses are mildly repetitive action verbs and slight overlap risk with generic web-building skills via broad terms like 'dashboards'.

DimensionReasoningScore

Specificity

The description lists several concrete actions and deliverables — 'Create distinctive, production-grade frontend interfaces', 'build web components, pages, artifacts, posters, or applications', 'Generates creative, polished code and UI design' — but the verbs (create/build/generate) are near-synonymous rather than distinct operations, leaving minor coverage gaps versus anchor 5's comprehensively distinct actions.

4 / 5

Completeness

Both questions are explicitly answered: what ('Create distinctive, production-grade frontend interfaces... Generates creative, polished code and UI design that avoids generic AI aesthetics') and when ('Use this skill when the user asks to build web components, pages, artifacts, posters, or applications...').

5 / 5

Trigger Term Quality

Comprehensive natural terms with synonyms a user would actually say: 'build web components', 'websites, landing pages, dashboards', 'React components', 'HTML/CSS layouts', and 'styling/beautifying any web UI' cover both the build and restyle phrasings users naturally use.

5 / 5

Distinctiveness Conflict Risk

The 'avoids generic AI aesthetics' framing carves a clear design-quality niche, but broad trigger terms like 'dashboards' and 'build web components' create minor overlap risk with general web-development and visualization skills, fitting anchor 4 rather than 5.

4 / 5

Total

18

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

majiayu000/claude-skill-registry-data

Path

data/02-designer-frontendimplementation/SKILL.md

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.