CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

frontend-design

Create distinctive, production-grade frontend interfaces with high design quality, ALIGNED with the Comanda editorial line. Use when the user asks to build web components, pages, or applications and wants polished, memorable design instead of generic AI aesthetics.

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

68%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 tight, highly actionable design-system spec where every rule is a concrete project-specific constraint rather than generic knowledge. Its weaknesses are an implicit rather than explicit workflow with no verification checkpoints, and a couple of underspecified values ('warm shadow') plus motivational filler that could be trimmed.

Suggestions

Add a short final checklist step (e.g., 'Before delivering: verify no forbidden item — gradients, emoji, border+shadow, period decimals — and prefers-reduced-motion is respected') to give the workflow an explicit validation checkpoint.

Replace vague shadow guidance ('warm shadow (no blue tint)') with actual values (color, blur, offset) like the other token rules, or point to where the exact shadow tokens are defined.

Trim motivational repetition ('Don't hold back — but never break the editorial line to do it', 'CRITICAL: Intentionality, not intensity...') and consolidate the overlapping implementation-quality bullets in 'Design thinking' to tighten token usage.

DimensionReasoningScore

Conciseness

Nearly all content is project-specific knowledge Claude cannot know (locked hex tokens, font weights, motion budgets, currency format), so tokens earn their place. Minor motivational padding ('Don't hold back — but never break the editorial line to do it', 'CRITICAL: Intentionality, not intensity...') could be trimmed, keeping it below the lean anchor 5.

4 / 5

Actionability

Highly concrete values are given throughout — radius 16px, min height 44px, max 320ms, 'R$ 1.234,56', exact hex tokens — plus a checkable forbidden list. Minor gaps: 'warm shadow (no blue tint)' provides no actual shadow value and no sample CSS/component demonstrates application, so it stops short of fully copy-paste-ready guidance.

4 / 5

Workflow Clarity

A sequence is implied by section order (locked editorial line -> 'Design thinking (before coding)' -> implement -> creative-freedom bounds) but never made explicit, and validation checkpoints are absent (no self-check against the forbidden list, no a11y verification step). This matches anchor 3: sequence present but checkpoints missing or implicit; not 4 since no verification steps exist at all.

3 / 5

Progressive Disclosure

A single self-contained file with clear section headers and scannable token lists; all content is per-invocation-relevant design constraints so inline placement is defensible. At ~74 lines it exceeds the under-50-line simple-skill exception that would justify a top score, and no reference files split out detail, landing it at anchor 4 (good structure, minor organization gaps).

4 / 5

Total

15

/

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: explicit what and when with concrete trigger phrases, written in third person. Its main weaknesses are limited action coverage (essentially one verb plus qualifiers) and a trigger set that could overlap with a general frontend development skill in the same project.

DimensionReasoningScore

Specificity

Names the domain ('frontend interfaces') and 1-2 concrete capabilities ('Create distinctive, production-grade frontend interfaces', 'ALIGNED with the Comanda editorial line') but lists no further actions. Not 2 because the editorial-line alignment is a specific capability beyond a generic action; not 4 because there is no list of several concrete actions.

3 / 5

Completeness

Explicitly answers both 'what' ('Create distinctive, production-grade frontend interfaces... ALIGNED with the Comanda editorial line') and 'when' ('Use when the user asks to build web components, pages, or applications and wants polished, memorable design instead of generic AI aesthetics') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural trigger phrases like 'build web components, pages, or applications', 'polished, memorable design', and 'generic AI aesthetics' match what users would actually say. A few common terms are missing ('UI', 'website', 'landing page', 'redesign'), so it falls short of comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

The Comanda-specific editorial line and the 'wants polished, memorable design instead of generic AI aesthetics' qualifier carve out a clear niche. Minor overlap risk remains with general frontend/build skills since any frontend build request could match the 'build web components, pages, or applications' trigger.

4 / 5

Total

16

/

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

mazzoty-fjrnf/hug-command-nexus

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.