CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

frontend-design-skill

Create distinctive, production-grade frontend interfaces with high design quality — avoids generic AI aesthetics.

Quality

60%

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 ./frontend/frontend-design-skill/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

53%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.

This is a well-organized, single-file instruction skill with genuinely concrete aesthetic guidance (named anti-patterns, specific libraries, specific techniques) that succeeds on direction-setting. Its weaknesses are mild redundancy of the same thesis stated three or four times, absence of any worked example despite emphasizing meticulous refinement, and no explicit pre-delivery validation step despite shipping a ready-made anti-pattern checklist.

Suggestions

Cut the redundant thesis statements — keep either the blockquote or the intro paragraph, and drop the CRITICAL note's restatement ('the key is intentionality, not intensity' duplicates Key Conventions) — to tighten conciseness.

Add one compact worked example (e.g., a sample font pairing and CSS-variable palette for a named aesthetic like 'editorial/magazine') so the demand for meticulous refinement is modeled, not just described.

Reframe the Anti-Patterns section as an explicit final validation step — 'Before finishing, verify: no Inter/Roboto/system fonts, no purple gradients on white, no Space Grotesk default, design varies from prior generations' — to close the workflow loop.

DimensionReasoningScore

Conciseness

The body is mostly tight, directive prose ('Pair a distinctive display font with a refined body font', 'Use Motion library for React'), but the core thesis is stated three times — the blockquote, 'This skill guides creation of distinctive, production-grade frontend interfaces that avoid generic "AI slop" aesthetics', and the CRITICAL note — plus again in Key Conventions ('Elegance comes from executing the vision well, not from the level of intensity'). This matches 'Mostly efficient but includes some unnecessary explanation or could be tightened'. Not a 4 because the redundant restatements and the source-link preamble are trimmable padding.

3 / 5

Actionability

As an instruction-only skill, code absence is not penalized, and there are concrete anchors ('Motion library for React', 'animation-delay', 'CSS variables', named anti-patterns like Inter/Roboto/purple gradients/Space Grotesk). But much of the guidance is abstract direction — 'Choose fonts that are beautiful, unique, and interesting', 'Create atmosphere and depth rather than defaulting to solid colors' — without examples of what to do, matching 'Some concrete guidance but incomplete'. Not a 4 because a skill claiming 'meticulously refined in every detail' offers no worked example (e.g., a font pairing or palette pattern).

3 / 5

Workflow Clarity

A sequence exists — 'Before coding, understand the context' → commit to a BOLD aesthetic direction → 'Then implement working code' — matching 'Steps listed but validation gaps; sequence present but checkpoints missing or implicit'. Not a 4 because there is no review checkpoint: the Anti-Patterns list ('NEVER Use') is exactly a pre-delivery check but is never framed as a validation step, so the loop of draft → check against anti-patterns → revise is left implicit. (The destructive-operation cap does not apply; this is a non-destructive creative skill.)

3 / 5

Progressive Disclosure

No bundle files exist and none are needed for this design-philosophy skill; the content is one well-organized file with clear sections (Design Thinking, Aesthetics Guidelines with sub-sections, Anti-Patterns, Key Conventions, Integration Notes), matching 'Good structure; most content is appropriately placed'. Not a 5 because the body runs ~60 lines — over the 'under 50 lines with just well-organized sections' bar for a 5 — and carries duplication (blockquote + intro + CRITICAL) that should either be cut or split out.

4 / 5

Total

13

/

20

Passed

Description

50%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.

The description states a clear 'what' with an authentic design philosophy, but it is a single action with no 'when to use' trigger clause and thin natural-language keyword coverage. Adding a 'Use when...' clause with concrete trigger phrases would lift completeness, trigger quality, and distinctiveness simultaneously.

Suggestions

Add an explicit trigger clause, e.g., 'Use when building or restyling web UI, components, pages, or apps (HTML/CSS/JS, React, Vue, Svelte), or when the user asks for a distinctive look instead of generic styling.'

Include natural synonyms users actually say — 'UI', 'web design', 'styling', 'landing page', 'dashboard', 'CSS', 'component' — to broaden trigger coverage beyond 'frontend interfaces'.

Enumerate 1-2 more concrete capabilities (e.g., 'picks typography, color palettes, motion, and layout direction') to move specificity beyond a single 'create' action.

DimensionReasoningScore

Specificity

The description names the domain ('frontend interfaces') and one concrete action ('Create'), but adds only modifiers ('distinctive, production-grade', 'high design quality') rather than additional actions — matching 'Names domain and 1-2 concrete actions, but not comprehensive'. Not a 4 because it does not list several specific actions (nothing about typography, color, motion, or implementation).

3 / 5

Completeness

The 'what' is clear (create distinctive, production-grade frontend interfaces with high design quality), but there is no 'Use when...' clause or equivalent trigger guidance; the guideline explicitly caps this at 3. Not a 4 because the 'when' is entirely absent, not merely implicit.

3 / 5

Trigger Term Quality

'frontend interfaces', 'design quality', and 'production-grade' are relevant keywords, but common natural terms users would say — 'UI', 'web page', 'styling', 'CSS', 'React', 'landing page', 'component' — are missing, matching 'Some relevant keywords but missing common variations or synonyms'. Not a 4 since everyday phrasings users actually use when requesting frontend work are absent.

3 / 5

Distinctiveness Conflict Risk

'Frontend interfaces' is somewhat specific and the 'avoids generic AI aesthetics' angle is distinctive, but it would overlap with any general web-dev, styling, or UI skill, matching 'Somewhat specific but could still overlap with similar skills'. Not a 4 because virtually any frontend build request matches, giving real overlap risk with closely related scaffold/styling skills.

3 / 5

Total

12

/

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

achreftlili/deep-dev-skills

Path

frontend/frontend-design-skill/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.