high-end-visual-design

Teaches the AI to design like a high-end agency. Defines the exact fonts, spacing, shadows, card structures, and animations that make a website feel expensive. Blocks all the common defaults that make AI designs look cheap or generic.

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/soft-skill/SKILL.md

Quality

Content

63%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.

The skill body is exceptionally concrete and actionable with a clear execution protocol and validation checklist, but it carries decorative flair that hurts token efficiency and bundles everything into one long monolith with no progressive disclosure to deeper reference files.

Suggestions

Strip persona/marketing flourishes ("Vanguard_UI_Architect", "$150k+ agency-level", "obsessive") to tighten conciseness without losing the concrete guidance.

Move the Vibe/Layout archetype catalogs and motion recipes into separate reference files (e.g. archetypes.md, motion.md) and link to them from SKILL.md for progressive disclosure.

Add a brief fix-and-retry loop to the pre-output checklist (e.g. "if any checkbox fails, revise and re-check before output") to strengthen workflow validation.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly actionable, but decorative persona language ("Vanguard_UI_Architect", "$150k+ agency-level", "obsessive micro-interactions", "cinematic spatial rhythm") adds tokens without instructional value and could be trimmed.	3 / 5
Actionability	Highly concrete guidance throughout — exact Tailwind classes (backdrop-blur-2xl, rounded-[2rem], py-24), hex colors, and cubic-bezier values — but these are class fragments rather than complete copy-paste component code.	4 / 5
Workflow Clarity	Section 7 gives a clear 5-step execution sequence and Section 8 provides an explicit pre-output validation checklist acting as a checkpoint, though there is no fix-and-retry feedback loop.	4 / 5
Progressive Disclosure	The document is well-sectioned into 8 parts, but it is a monolithic single file with no bundle references, exceeds the 50-line simple-skill threshold, and inlines substantial archetype catalogs and motion recipes that could live in separate reference files.	3 / 5
	Total	14 / 20 Passed

Description

58%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 is specific and distinctive about what the skill does, but it omits any explicit "when to use it" trigger guidance, which caps its completeness. Adding a concrete "Use when..." clause with natural user phrases would lift the two lowest dimensions.

Suggestions

Add an explicit "Use when..." clause, e.g. "Use when building marketing sites, landing pages, or portfolios that must look premium or agency-grade."

Include natural trigger terms users actually say — "UI/UX design", "landing page", "premium", "modern", "portfolio" — alongside the existing vocabulary.

Consider noting the tech stack scope (e.g. React/Tailwind) in the description so it triggers only for relevant contexts.

Dimension	Reasoning	Score
Specificity	"Defines the exact fonts, spacing, shadows, card structures, and animations" and "Blocks all the common defaults" name several concrete, specific capabilities rather than vague abstractions, though the actions are framed as 'defines/blocks' rather than a fuller enumeration.	4 / 5
Completeness	The "what" is clearly stated (defines fonts/spacing/shadows/cards/animations, blocks cheap defaults), but there is no "Use when..." clause or equivalent explicit trigger guidance, capping completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Terms like "design", "high-end agency", "website feel expensive", and "cheap or generic" are reasonably natural, but common variations users actually say ("UI/UX", "landing page", "premium", "modern", "portfolio") are missing.	3 / 5
Distinctiveness Conflict Risk	The premium "high-end agency / expensive / anti-cheap-generic" framing carves a fairly distinct niche with minimal overlap risk, though it could still collide with broader web/UI-design skills.	4 / 5
	Total	14 / 20 Passed

Validation

100%

Warnings & errors only

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: Leonxlnx/taste-skill
Path: skills/soft-skill/SKILL.md
Commit: ccbc156

Reviewed: 10 days ago

Table of Contents

Discovery Implementation Validation

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.