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. Generates creative, polished code that avoids generic AI aesthetics. Do NOT use for design review or audit (use web-design-guidelines or web-quality-audit).

Quality

85%

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

SKILL.md
Quality
Evals
Security

Quality

Content

78%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.

Well-structured creative-design skill with lean directive guidelines, concrete CSS-level specifics, a self-check checkpoint, and exemplary progressive disclosure through seven real one-level reference files. Weakest dimension is the lack of executable code examples and some motivational filler.

Suggestions

Add 1-2 short executable code snippets (e.g. a fluid clamp() type scale or an oklch palette declaration) to lift actionability from concrete guidance to copy-paste ready.

Trim motivational filler such as 'There are so many flavors to choose from' and the closing 'Remember: the AI is capable of extraordinary creative work...' paragraph to tighten conciseness.

Make the AI Slop Test an explicit feedback loop (check -> if AI tells present, revise specific element -> re-check) to strengthen workflow_clarity's validation checkpoint.

DimensionReasoningScore

Conciseness

Largely lean and directive DO/DON'T lists that assume Claude's competence, with only minor filler ('There are so many flavors to choose from', the motivational closing paragraph) that could be trimmed; not 5 due to those padded lines, not 3 because over-explanation of known concepts is absent.

4 / 5

Actionability

Concrete, specific guidance naming real CSS APIs (oklch, color-mix, light-dark, clamp, grid-template-rows, @container, ease-out-quart) and concrete anti-patterns to avoid; not 5 because there are no executable code blocks, not 3 because the guidance is specific and actionable rather than pseudocode-level.

4 / 5

Workflow Clarity

A clear sequence—commit to a Design Direction (Purpose/Tone/Constraints/Differentiation), implement working code, then run the 'AI Slop Test' as an explicit validation checkpoint—with only minor gaps; not 5 because error-recovery feedback loops are implicit, not 3 because the sequence and a checkpoint are present.

4 / 5

Progressive Disclosure

Every guidelines section opens with a clearly signaled one-level-deep reference ('Consult [typography reference](references/typography.md)...'), and all seven referenced files (typography, color-and-contrast, spatial-design, motion-design, interaction-design, responsive-design, ux-writing) exist in references/, giving easy navigation with no nesting.

5 / 5

Total

17

/

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.

A strong, third-person description that clearly states capabilities, gives concrete trigger terms, and disambiguates from related review/audit skills. Minor room for synonyms or file extensions in trigger coverage.

DimensionReasoningScore

Specificity

Lists several concrete actions and targets—'build web components, pages, artifacts, posters, or applications' and 'Generates creative, polished code'—with only minor coverage gaps, matching the 'lists several specific actions' anchor; not 5 because it does not comprehensively enumerate frontend actions, not 3 because it goes beyond 1-2 actions.

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...') with concrete trigger phrases, plus a negative boundary clause.

5 / 5

Trigger Term Quality

Includes natural phrases users say ('build web components, pages, artifacts, posters, or applications') with good coverage, but lacks synonyms or file extensions (e.g. 'websites', 'UI', '.html') that would push it to 5; clearly above the 'some relevant keywords' level of 3.

4 / 5

Distinctiveness Conflict Risk

Clear niche (distinctive frontend interface creation) with distinct triggers and an explicit exclusion ('Do NOT use for design review or audit') naming the conflicting skills, giving minimal conflict risk.

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.

Validation — 15 / 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

tech-leads-club/agent-skills

Path

packages/skills-catalog/skills/(design)/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.