CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

39

Quality

36%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/soft-skill/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

55%

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

The skill is impressively actionable with specific, executable Tailwind/CSS patterns and a clear execution workflow with validation checklist. However, it is severely bloated with marketing-style language, unnecessary persona framing, and explanatory commentary that wastes tokens. The monolithic structure with no bundle files means everything is loaded at once, which is particularly wasteful given the skill's length.

Suggestions

Cut all marketing/persona language ('$150k agency build', 'Vanguard_UI_Architect', 'haptic depth', 'cinematic spatial rhythm') — Claude doesn't need motivation, just instructions.

Split into multiple files: keep SKILL.md as a concise overview with the execution protocol and checklist, then reference separate files like ANTI-PATTERNS.md, COMPONENTS.md, MOTION.md, and VARIANCE-ENGINE.md.

Remove explanatory rationales (e.g., 'it causes continuous reflows and kills mobile performance') — state the rule only, Claude understands the why.

Condense the Variance Engine section into a compact lookup table format rather than prose paragraphs for each archetype.

DimensionReasoningScore

Conciseness

Extremely verbose at ~200+ lines with significant padding. Includes unnecessary persona framing ('$150k agency build'), marketing language, and explanatory commentary Claude doesn't need (e.g., explaining why not to use window.addEventListener('scroll')). The creative variance engine section alone could be condensed by 60%+ while preserving all actionable content.

1 / 3

Actionability

Highly actionable with specific Tailwind utility classes, exact CSS values, concrete cubic-bezier curves, precise component structures (Double-Bezel pattern with exact classes), and copy-paste-ready patterns. The banned patterns list is concrete and unambiguous. Every section provides specific implementation details rather than abstract guidance.

3 / 3

Workflow Clarity

Section 7 provides a clear 5-step execution protocol with explicit sequencing. Section 8 provides a comprehensive pre-output checklist that serves as a validation checkpoint before delivery. The workflow covers the full lifecycle from design selection through scaffolding, architecture, motion, and final output with a verification gate.

3 / 3

Progressive Disclosure

Monolithic wall of text with no external references or file splitting. All content—anti-patterns, variance engine, component patterns, motion choreography, performance rules, and checklists—is crammed into a single file. This would benefit enormously from splitting into separate reference files (e.g., ANTI-PATTERNS.md, COMPONENTS.md, MOTION.md).

1 / 3

Total

8

/

12

Passed

Description

17%

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 uses subjective, marketing-style language ('high-end agency', 'feel expensive', 'look cheap') rather than concrete, actionable terms. It violates the voice guideline by using second-person framing ('Teaches the AI') and lacks explicit trigger guidance. The description would benefit significantly from concrete actions, natural user keywords, and a clear 'Use when...' clause.

Suggestions

Add a 'Use when...' clause with natural trigger terms like 'Use when designing websites, landing pages, UI components, or when the user asks for premium/polished web design, CSS styling, or modern layouts.'

Replace subjective language with concrete actions: e.g., 'Applies premium typography scales, box shadows, spacing systems, and micro-animations to web designs. Enforces design tokens for consistent card layouts and component styling.'

Include file type and technology keywords users would naturally mention, such as 'CSS', 'HTML', 'Tailwind', 'landing page', 'UI components', 'web styling'.

DimensionReasoningScore

Specificity

Names the domain (web design) and lists some specific areas like fonts, spacing, shadows, card structures, and animations, but these are categories rather than concrete actions. It describes what it defines rather than what actions it performs (e.g., no verbs like 'generates', 'applies', 'configures').

2 / 3

Completeness

The 'what' is partially addressed (defines design standards), but there is no explicit 'when' clause or trigger guidance. The description lacks any 'Use when...' statement, which per the rubric should cap completeness at 2, and the 'what' is also weak enough to warrant a 1.

1 / 3

Trigger Term Quality

Lacks natural keywords a user would say when needing this skill. Terms like 'high-end agency', 'expensive', and 'cheap or generic' are subjective descriptors rather than trigger terms. Missing terms like 'UI design', 'CSS', 'web design', 'styling', 'landing page', 'premium design' that users would naturally use.

1 / 3

Distinctiveness Conflict Risk

The focus on 'high-end agency' design aesthetics and blocking cheap defaults gives it some distinctiveness, but the broad scope of 'website design' could overlap with general CSS/styling or UI component skills. The niche is somewhat defined but not sharply delineated.

2 / 3

Total

6

/

12

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
Leonxlnx/taste-skill
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.