CtrlK
BlogDocsLog inGet started
Tessl Logo

frontend-design

Build web interfaces with genuine design quality, not AI slop. Use for any frontend work - landing pages, web apps, dashboards, admin panels, components, interactive experiences. Activates for both greenfield builds and modifications to existing applications. Detects existing design systems and respects them. Covers composition, typography, color, motion, and copy. Verifies results via screenshots before declaring done.

72

Quality

88%

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

77%

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

The body is a well-structured, highly actionable instruction skill with a clear workflow and verification checkpoint. Its main weakness is conciseness — some motivational prose could be trimmed — and a large single-file footprint where parts could be factored into reference files.

Suggestions

Trim inspirational prose such as the 'Creative Energy' pep talk and aphoristic sentences ('Elegance comes from executing the vision well') to tighten token efficiency.

Consider moving the Context Modules (A/B/C) and/or the Hard Rules & Anti-Patterns into separate reference files referenced one level deep, to reduce the monolithic body and improve progressive disclosure.

Tighten the 'Authority Hierarchy' and 'What to Look For' sections into denser lists so the core workflow reaches a reader faster.

DimensionReasoningScore

Conciseness

Mostly efficient and free of explaining concepts Claude already knows, but includes inspirational padding ('Accessibility and aesthetics are not in tension when done well', 'Elegance comes from executing the vision well') and a pep-talk 'Creative Energy' section that could be tightened.

2 / 3

Actionability

As an instruction-only skill it gives concrete, executable directives throughout — 'Avoid the usual suspects (Inter, Roboto, Arial)', 'One H1 headline. One primary CTA above the fold', and a ranked tool cascade for verification — with specifics a model can act on directly.

3 / 3

Workflow Clarity

A clear four-stage sequence ('Detect context -> Plan the design -> Build -> Verify visually') with Layer 0/1/2 structure, mode classification, and an explicit visual-verification checkpoint plus litmus self-review for error feedback.

3 / 3

Progressive Disclosure

The body is well-organized with clear headers and navigation, but it is a large (~250 line) monolithic file with inline context modules (A/B/C) and reference-style sections that could be split into separate files rather than carried inline.

2 / 3

Total

10

/

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 clearly states capabilities, enumerates concrete user-facing trigger terms, and provides an explicit 'Use for' clause answering both what and when. It is distinctive and unlikely to conflict with unrelated skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions in third person ('Build web interfaces', 'Detects existing design systems and respects them', 'Verifies results via screenshots before declaring done') alongside specific coverage areas, matching the 'multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers both what ('Build web interfaces with genuine design quality') and when ('Use for any frontend work - landing pages, web apps, dashboards...') with an explicit 'Use for' trigger clause.

3 / 3

Trigger Term Quality

Surfaces natural terms users actually say — 'frontend work', 'landing pages', 'web apps', 'dashboards', 'admin panels', 'components' — plus the recognizable 'AI slop' trigger, giving good coverage of common phrasings.

3 / 3

Distinctiveness Conflict Risk

The 'genuine design quality, not AI slop' framing plus a distinct list of frontend artifact types carves a clear niche unlikely to trigger for non-frontend 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
udecode/plate
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.