CtrlK
BlogDocsLog inGet started
Tessl Logo

frontend-design

Build distinctive, production-quality UI. Use when creating or reshaping user-facing interfaces, components, pages, layouts, visual redesigns, responsive behavior, loading/error/empty states, or accessibility-sensitive frontend work.

80

Quality

100%

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

SKILL.md
Quality
Evals
Security

Quality

Content

100%

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

A dense, well-structured instruction skill that provides opinionated, concrete frontend-design guidance with specific thresholds, a two-pass build workflow with a critique checkpoint, and a verification checklist. It assumes Claude's competence and avoids basic-concept padding, though a few prose passages could be tightened.

DimensionReasoningScore

Conciseness

The body is opinionated and assumes Claude's competence — e.g. "Choose the simplest state that works: useState for component UI state... context for read-heavy/write-rare concerns" — with no padding explaining basic concepts. It is not a 2 because every section encodes specific design direction rather than restating what Claude already knows, even though a few manifesto-style lines ("Elegance is executing the chosen vision well") could be trimmed.

3 / 3

Actionability

Gives concrete, executable specifics: "4-6 named hex values", "one h1 per page, no skipped heading levels", contrast ratios "4.5:1 for normal text, 3:1 for large text", breakpoints "320px, 768px, 1024px, and 1440px", and exact aria attributes (aria-busy, role="status"). Although this instruction-only skill has no code, the guidance is specific and copy-applicable, matching the actionable anchor; it is not a 2 because thresholds and attributes are exact, not pseudocode or vague direction.

3 / 3

Workflow Clarity

The Process section sequences a clear two-pass flow — "First, create a compact design plan... Second, critique the plan against the brief before building. Only then write code" — with a critique checkpoint, plus a closing "Verification Checklist". It is not a 2 because an explicit critique-before-build checkpoint and a final checklist are present, not just an implicit sequence; this design work is not a destructive/batch operation, so the cap-at-2 rule does not apply.

3 / 3

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ absent), so per the rubric it is scored against the actual self-contained structure: a single SKILL.md organized into well-numbered sections (## 1 Aesthetic Direction through ## 5 plus Verification Checklist) with easy navigation. It is not a 2 because the content is well-organized and no deeply nested or poorly-signaled references are present; inline guidance is appropriate for this opinionated design skill.

3 / 3

Total

12

/

12

Passed

Description

100%

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

A strong, third-person description that pairs a concrete capability statement with an explicit, well-enumerated 'Use when' trigger clause. It is specific, well-keyworded, and clearly distinguished from sibling skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions and targets — "creating or reshaping user-facing interfaces, components, pages, layouts, visual redesigns, responsive behavior, loading/error/empty states" — matching the anchor for listing several specific concrete actions rather than vague language. It is not a 2 because it enumerates many concrete surface areas, not just a domain plus a couple actions.

3 / 3

Completeness

Clearly answers both what ("Build distinctive, production-quality UI") and when ("Use when creating or reshaping...") with an explicit trigger clause, matching the anchor for explicit what-and-when triggers. It is not a 2 because the when is stated explicitly with an enumerated trigger list, not merely implied.

3 / 3

Trigger Term Quality

Includes natural terms a user would say — "UI", "frontend", "interfaces", "components", "pages", "layouts", "responsive", "redesigns" — giving good coverage of common phrasings rather than jargon-only or generic terms. It is not a 2 because the keyword set is broad and spans the common ways users request frontend work.

3 / 3

Distinctiveness Conflict Risk

It carves a clear frontend-design niche with distinct triggers (visual redesigns, states, accessibility-sensitive frontend work), making accidental triggering for unrelated skills unlikely. It is not a 2 because the scope is sharply scoped to UI/frontend work rather than broadly overlapping with general coding or document skills.

3 / 3

Total

12

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
MODSetter/SurfSense
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.