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.

62

Quality

78%

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 ./.agents/skills/frontend-design/SKILL.md
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.

A lean, well-structured instruction-only skill that successfully delivers opinionated aesthetic guidance without padding or explanations of basics. Its weakness is actionability: it tells Claude what qualities to pursue (distinctive fonts, bold palettes, staggered reveals) but never shows a concrete example — a sample font pairing, a CSS-variable setup, or a minimal animation snippet — leaving the taste guidance harder to execute.

Suggestions

Add one small executable example, such as a CSS-variable color/typography block or a staggered page-load reveal with animation-delay, to anchor the abstract aesthetic advice in concrete code.

Include 2-3 example font pairings (display + body) so the 'avoid generic fonts, choose distinctive ones' directive has actionable reference points.

Add a brief final checkpoint, e.g., 'before delivering, confirm the result meets stated accessibility and framework constraints', to close the workflow validation gap.

DimensionReasoningScore

Conciseness

The body is directive, opinionated guidance with no explanation of concepts Claude already knows, so it mostly respects token budget. Minor motivational padding ("Remember: Claude is capable of extraordinary creative work. Don't hold back...", "There are so many flavors to choose from.") could be trimmed, matching the 'efficient; minor instances that could be trimmed' anchor rather than the fully lean 5.

4 / 5

Actionability

Concrete tactics are named (CSS variables, animation-delay, Motion library for React, gradient meshes, noise textures, grain overlays), but guidance like "Choose fonts that are beautiful, unique, and interesting" stays directional with no executable example — no sample font pairing, CSS snippet, or skeleton structure. For an instruction-only skill the guidance is partially actionable but missing key specifics, matching the 3 anchor; it is not a 4 because there is no concrete code or command at all, and not a 2 because specific techniques and named tools are provided.

3 / 5

Workflow Clarity

A clear two-phase sequence is presented under labeled headers ("Before coding, understand the context and commit to a BOLD aesthetic direction" → "Then implement working code"), and the operation is generative rather than destructive so heavy validation is not required. It falls short of 5 because there is no checkpoint for confirming that stated constraints (e.g., accessibility) were actually met in the produced code.

4 / 5

Progressive Disclosure

The body is under 50 lines, well-organized into clear sections (Design Thinking, Frontend Aesthetics Guidelines), and needs no external references — no references/, scripts/, or assets/ exist — so it matches the simple-skill exception for a top score with well-organized sections alone.

5 / 5

Total

16

/

20

Passed

Description

78%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 both what the skill does and when to use it, with an unusually rich set of natural trigger terms covering websites, landing pages, dashboards, React components, HTML/CSS layouts, and styling requests. The main weakness is that its action verbs ("create", "generates") stay abstract rather than naming concrete capabilities.

Suggestions

Replace abstract verbs with 1-2 more concrete capabilities (e.g., "builds styled React components and HTML/CSS pages with cohesive typography, color, and motion") to lift specificity.

Add common user phrasings like "design", "redesign", or "mock up" to the trigger list to close the remaining trigger-term gaps.

DimensionReasoningScore

Specificity

The description names the domain ("frontend interfaces") and a couple of actions ("Create distinctive, production-grade frontend interfaces", "Generates creative, polished code and UI design"), but the verbs are abstract and no concrete operations are enumerated, matching the 'names domain and 1-2 concrete actions' anchor. It is not a 4 because it lacks several specific actions; not a 2 because it goes beyond a bare domain mention with generic verbs.

3 / 5

Completeness

Both what and when are explicitly and concretely answered: "Create distinctive, production-grade frontend interfaces... Use this skill when the user asks to build web components, pages, artifacts, posters, or applications", with a rich list of concrete trigger examples — a clear match for the 5 anchor.

5 / 5

Trigger Term Quality

Trigger terms are strong and natural: "build web components, pages, artifacts, posters, or applications (websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI)". A few natural user phrases such as "design", "redesign", or "mockup" are missing, so it falls just short of the comprehensive 5 anchor.

4 / 5

Distinctiveness Conflict Risk

It carves a clear frontend-building niche with distinct triggers, but the broad "styling/beautifying any web UI" clause creates minor overlap risk with closely related styling and design skills, matching the 'mostly distinct; minor overlap risk' anchor.

4 / 5

Total

16

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository

reactive/data-client

Path

.agents/skills/frontend-design/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.