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, or applications. Generates creative, polished code that avoids generic AI aesthetics.

Quality

76%

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/04-develop/00-frontend-general/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 well-structured, actionable design-guidance body that appropriately stays lean by omitting bundle files and gives concrete named techniques for each aesthetic area. Its main weakness is redundancy and motivational padding that could be tightened, plus implicit rather than explicit phase checkpoints.

Suggestions

Remove duplicated guidance: the 'NEVER use generic AI-generated aesthetics' paragraph repeats the Typography bullet's font avoid-list — consolidate into one place.

Cut filler lines ('There are so many flavors to choose from.', the closing 'Remember: Claude is capable...' paragraph) and the opening restatement of the description to tighten the body.

Add one or two concrete reference points (e.g., a sample distinctive font pairing or a minimal staggered-reveal CSS snippet) to nudge actionability toward fully executable guidance.

DimensionReasoningScore

Conciseness

The body is mostly directive and assumes design competence, but there is more than minor trimmable material: the opening paragraph restates the frontmatter description; 'There are so many flavors to choose from.' and the closing 'Remember: Claude is capable of extraordinary creative work. Don't hold back...' are filler; and the avoid-generic-fonts guidance is stated twice (the Typography bullet and the 'NEVER use generic AI-generated aesthetics' paragraph both name Inter/Arial/generic fonts). This places it at 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than anchor 4's minor instances.

3 / 5

Actionability

As an instruction-only skill the guidance is actionable via concrete named techniques: 'Avoid generic fonts like Arial and Inter', 'Use CSS variables for consistency', 'staggered reveals (animation-delay)', 'Use Motion library for React', and a specific effects list ('gradient meshes, noise textures, geometric patterns, layered transparencies, dramatic shadows'). Minor gaps — e.g., no example font pairings or a minimal code pattern — keep it below anchor 5.

4 / 5

Workflow Clarity

A clear temporal sequence is present: 'Before coding, understand the context and commit to a BOLD aesthetic direction' (with a Purpose/Tone/Constraints/Differentiation checklist), then 'Then implement working code' followed by per-area guidelines. This is a generative, non-destructive skill so no validation cap applies, but checkpoints between the thinking and implementation phases are implicit rather than explicit, holding it at anchor 4.

4 / 5

Progressive Disclosure

The skill is under 50 lines, has no external references and needs none (confirmed: no references/, scripts/, or assets/ bundle files exist), and is organized into clear sections ('Design Thinking', 'Frontend Aesthetics Guidelines'). This matches the simple-skill exception where well-organized sections alone earn a 5.

5 / 5

Total

16

/

20

Passed

Description

70%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 solid description that clearly answers both what the skill does and when to use it, in proper third-person voice with natural trigger phrasing. Its main weaknesses are heavy reliance on quality adjectives over distinct concrete capabilities and a trigger list that misses common variations like 'UI' and 'design'.

Suggestions

Replace some quality adjectives ('high design quality', 'polished') with distinct concrete capabilities, e.g. 'Design typography, color, motion, and layout systems' to raise specificity.

Broaden the 'Use when' clause with common variations users say, such as 'design a UI', 'redesign a page', or 'landing page', to improve trigger term coverage and completeness.

Narrow the trigger scope slightly (e.g., emphasizing design/styling intent rather than any 'build an application' request) to reduce overlap with a general web-development skill.

DimensionReasoningScore

Specificity

The description names the domain ('frontend interfaces') and 1-2 concrete actions ('Create... interfaces', 'Generates... code'), but the remainder is quality adjectives ('distinctive', 'production-grade', 'high design quality', 'polished') rather than additional distinct capabilities, so it does not reach the 'several specific actions' of anchor 4. Voice is third person, so no voice penalty applies.

3 / 5

Completeness

Both parts are explicit: 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'). The when clause is concrete but could be more specific — it omits frequent triggers like 'design a UI' or 'redesign', keeping it below anchor 5.

4 / 5

Trigger Term Quality

'build web components, pages, or applications' plus 'frontend' are natural phrases users would say, giving good keyword coverage; a few natural terms are missing (e.g., 'UI', 'design', 'landing page', 'redesign'). Not anchor 3 because the included terms are genuinely natural user phrasings, not generic jargon; not anchor 5 because common synonyms are absent.

4 / 5

Distinctiveness Conflict Risk

The 'avoids generic AI aesthetics' framing carves a clear design niche with distinct intent, but the trigger phrase 'build web components, pages, or applications' is broad enough to overlap with a general web-development skill, so minor overlap risk remains rather than the minimal risk of anchor 5.

4 / 5

Total

15

/

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

marchatton/agent-skills

Path

.agents/skills/04-develop/00-frontend-general/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.