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

68%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

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

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable and well-sequenced with concrete Tailwind tokens, a clear execution protocol, and a validation checklist. Its main weaknesses are rhetorical verbosity and a fully monolithic structure with no progressive disclosure into reference files.

Suggestions

Trim rhetorical flourishes ('haptic depth, cinematic spatial rhythm', '$150k+ agency-level digital experiences') and de-duplicate the Section 8 checklist against Section 2's banned list to recover tokens.

Move the archetype catalogs (Section 3) and motion/performance specs (Sections 5-6) into bundled reference files (e.g. references/archetypes.md, references/motion.md) referenced one level deep from SKILL.md to enable progressive disclosure.

Keep a concise overview in SKILL.md that points to those references, preserving the execution protocol and checklist as the in-file spine.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and prescriptive rather than explaining known concepts, but rhetorical flourish ('haptic depth, cinematic spatial rhythm', '$150k+ agency-level') and a checklist that partially restates Section 2's bans add tokens that could be trimmed.	2 / 3
Actionability	Guidance is concrete and copy-paste-ready with exact Tailwind tokens and values ('backdrop-blur-2xl', 'rounded-[calc(2rem-0.375rem)]', 'ease-[cubic-bezier(0.32,0.72,0,1)]', 'min-h-[100dvh]') and explicit structures (outer shell + inner core); per the instruction-skill note, absence of full code files is not penalized when guidance is this actionable.	3 / 3
Workflow Clarity	Section 7 gives a clear 5-step execution sequence (SILENT THOUGHT → SCAFFOLD → ARCHITECT → CHOREOGRAPH → OUTPUT) and Section 8 provides an explicit 11-item pre-output validation checklist, matching the score-3 anchor of a clear sequence with explicit validation/checklist.	3 / 3
Progressive Disclosure	The body is well-organized into eight numbered sections, but it is a monolithic ~94-line file with no bundle files and no one-level-deep references; the archetype catalogs and motion specs are inline content that could be split out, so it sits at 2 rather than the reference-split 3.	2 / 3
	Total	10 / 12 Passed

Description

60%

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 concrete about what the skill does (fonts, spacing, shadows, structures, animations, blocking cheap defaults) but omits any 'when to use it' trigger guidance. Adding an explicit 'Use when...' clause with natural trigger terms would lift completeness and trigger-term quality.

Suggestions

Append an explicit 'Use when...' clause, e.g. 'Use when building or redesigning websites, landing pages, dashboards, or portfolios that must look premium rather than templated.'

Add natural trigger terms users would actually say ('make my site look expensive/premium', 'redesign this landing page', 'Awwwards-tier UI') to broaden trigger coverage.

Tighten distinctiveness by naming the concrete scenarios (SaaS marketing sites, agency portfolios) that distinguish it from a generic web-design skill.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Defines the exact fonts, spacing, shadows, card structures, and animations' and 'Blocks all the common defaults' — matching the score-3 anchor of several specific concrete actions rather than vague language.	3 / 3
Completeness	The 'what' is strong, but there is no 'when' — no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	It includes some natural phrases ('design like a high-end agency', 'make a website feel expensive', 'look cheap or generic') but lacks common variations users would say ('landing page', 'UI redesign', 'make it look premium') and has no explicit trigger keyword list.	2 / 3
Distinctiveness Conflict Risk	The high-end/premium web-design framing is a recognizable niche, but without explicit distinct triggers it could still overlap with general frontend or web-design skills, keeping it at 2 rather than 3.	2 / 3
	Total	9 / 12 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
Commit: b177427

Reviewed: 5 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.