CtrlK
BlogDocsLog inGet started
Tessl Logo

design-taste-frontend

Senior UI/UX Engineer. Architect digital interfaces overriding default LLM biases. Enforces metric-based rules, strict component architecture, CSS hardware acceleration, and balanced design engineering.

34

Quality

17%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

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

Quality

Discovery

7%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description reads more like a résumé headline than a functional skill description. It is laden with buzzwords and abstract claims ('overriding default LLM biases', 'balanced design engineering') that do not help Claude determine when to select this skill. It lacks concrete actions, natural trigger terms, and any explicit 'Use when...' guidance.

Suggestions

Replace abstract buzzwords with concrete actions, e.g., 'Creates responsive UI layouts, builds reusable component hierarchies, applies CSS optimizations including transforms and will-change for performance.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks to design a webpage, build a UI component, create a form, style a layout, or work with HTML/CSS/React components.'

Remove the first-person-like role declaration ('Senior UI/UX Engineer') and rewrite in third person describing what the skill does, not what it claims to be.

DimensionReasoningScore

Specificity

The description uses abstract, buzzword-heavy language like 'architect digital interfaces', 'overriding default LLM biases', 'metric-based rules', and 'balanced design engineering' without listing concrete actions a user would recognize. No specific tasks like 'create responsive layouts' or 'build component libraries' are mentioned.

1 / 3

Completeness

There is no 'Use when...' clause or equivalent trigger guidance. The 'what' is vaguely implied through buzzwords but never concretely stated, and the 'when' is entirely missing.

1 / 3

Trigger Term Quality

The terms used are technical jargon ('CSS hardware acceleration', 'component architecture', 'LLM biases') rather than natural keywords a user would say. Users would more likely say 'design a webpage', 'build a UI', 'create a form', or 'style a component' — none of which appear here.

1 / 3

Distinctiveness Conflict Risk

The mention of UI/UX, CSS, and component architecture does narrow the domain somewhat to frontend/interface work, but the vague framing ('architect digital interfaces', 'balanced design engineering') could overlap with general web development or design system skills.

2 / 3

Total

5

/

12

Passed

Implementation

27%

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

This skill is an ambitious and comprehensive frontend design system, but it suffers from extreme verbosity and poor information architecture. While it contains genuinely useful specific rules (Tailwind classes, performance guardrails, anti-patterns), the lack of executable code examples and the monolithic structure make it difficult to follow. The Creative Arsenal (Section 8) and Bento Paradigm (Section 9) sections alone could each be their own reference files, and the overall document would benefit enormously from being split into a concise overview with linked sub-documents.

Suggestions

Split into multiple files: Keep Sections 1-2 and 10 in SKILL.md as the overview, then move Sections 3-5 to DESIGN_RULES.md, Section 6 to DIAL_REFERENCE.md, Section 7 to ANTI_PATTERNS.md, and Sections 8-9 to CREATIVE_PATTERNS.md with clear links from the main file.

Add complete, executable code examples for key patterns—e.g., a full magnetic button component, a proper skeleton loader, a glassmorphism panel—instead of just describing them conceptually.

Reduce the Creative Arsenal (Section 8) to a compact lookup table format (name | one-line description | key CSS/JS technique) rather than prose paragraphs for each concept.

Remove redundant emphasis and repeated rules (e.g., the Inter font ban appears in both Section 3 and Section 7, serif constraints are repeated, motion performance rules appear in multiple places).

DimensionReasoningScore

Conciseness

Extremely verbose at ~400+ lines. Contains extensive explanatory prose, repeated emphasis ('CRITICAL', 'MANDATORY', 'BANNED'), and large inspirational catalogs (Section 8's 'Creative Arsenal') that are essentially lists of design concepts Claude already understands. The 'Bento Paradigm' section alone is massive and could be a separate reference file. Much content describes aesthetic philosophy rather than providing actionable instructions.

1 / 3

Actionability

Provides specific Tailwind classes, concrete CSS values, and some executable patterns (e.g., spring physics config, specific import paths, Tailwind breakpoints). However, there are no complete, copy-paste-ready code examples—most guidance is descriptive ('implement buttons that pull toward the cursor') rather than providing actual working code snippets. The Creative Arsenal section is entirely conceptual with no implementation code.

2 / 3

Workflow Clarity

Section 10 provides a pre-flight checklist which is good, and Section 2 has a dependency verification step. However, there's no clear sequential workflow for building a component or page from start to finish. The document reads more like a reference manual of rules than a step-by-step process. The dependency check is a good validation step but lacks error recovery guidance beyond 'output the install command'.

2 / 3

Progressive Disclosure

This is a monolithic wall of text with 10 major sections all inline. Sections 6 (Technical Reference), 7 (AI Tells), and 8 (Creative Arsenal) are extensive reference material that should be split into separate files. There are zero references to external files. The document tries to be both a quick-reference guide and an exhaustive encyclopedia in one file, making it overwhelming.

1 / 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.