CtrlK
BlogDocsLog inGet started
Tessl Logo

frontend-design

Expert frontend design guidelines for creating beautiful, modern UIs. Use when building landing pages, dashboards, or any user interface.

53

Quality

61%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/frontend-design/SKILL.md

The canonical home for this skill is frontend-design in jdrhyne/agent-skills

SKILL.md
Quality
Evals
Security

Quality

Content

61%Weight 40%Scale 1-5

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 design reference full of executable code and genuinely curated material (theme presets, font picks, timing standards). Its weaknesses are a workflow that lists steps without validation checkpoints and doesn't map cleanly to its own sections, and sections that re-explain fundamentals Claude already knows at the cost of token budget.

Suggestions

Trim or compress sections Claude already knows well (the Tailwind CDN import, glassmorphism snippet, standard responsive media-query block, and the accessibility checklist) to lift conciseness toward anchor 4-5.

Reconcile the stated 4-step workflow with the 8 numbered sections, and add an explicit validation checkpoint (e.g. a final 'verify contrast ratios and keyboard nav before delivering' step) to raise workflow clarity.

Move the font catalog and full theme-token presets into a references/ file (e.g. references/themes.md) linked from a compact overview, improving the progressive-disclosure split.

DimensionReasoningScore

Conciseness

Curated material Claude would not generate on its own (font catalogs, three oklch theme token presets, animation timing conventions, the ASCII wireframe method) is mixed with concepts Claude already knows — the Tailwind CDN import snippet, glassmorphism CSS, standard responsive media queries, and the accessibility checklist (semantic HTML, aria-labels, 4.5:1 contrast, 44px touch targets). This fits anchor 3 (mostly efficient but includes unnecessary sections that could be trimmed) — the genuinely novel content keeps it above 2, while the known-concept padding is more than minor, keeping it below 4.

3 / 5

Actionability

The body is dominated by concrete, copy-paste-ready code: three complete theme token blocks, CDN script tags for Tailwind/Flowbite/Lucide, specific animation timing values, and full responsive breakpoints. It fits anchor 4 (mostly executable with minor gaps) — the image example 'https://images.unsplash.com/photo-xxx' is a non-executable placeholder and some guidance ('Consider using oklch() for shadow colors too') stays abstract, so it falls short of anchor 5's fully-ready coverage.

4 / 5

Workflow Clarity

A clear 4-step sequence is stated ('1. Layout Design → 4. Implementation') and the numbered sections follow a coherent order, but the stated 4-step workflow and the 8 numbered sections don't map cleanly (two consecutive theme sections, responsive/accessibility/component sections unattached to the workflow), and no validation or review checkpoints exist — e.g. the 4.5:1 contrast rule is stated but no step tells Claude to verify it. This is anchor 3 (sequence present, checkpoints missing or implicit), not 4 because the gaps exceed 'minor', and not 2 because the core sequence is coherent and usable.

3 / 5

Progressive Disclosure

The single ~210-line file is well organized: clear section headers, a quick-reference table, and no nested references, making navigation easy. This fits anchor 4 (good structure, minor organization gaps) — the font catalog and the three theme patterns are reference-style material that could live in references/ files, which keeps it below anchor 5's clean overview-plus-references split, but the inline placement at this size is defensible, keeping it above anchor 3.

4 / 5

Total

14

/

20

Passed

Description

61%Weight 40%Scale 1-5

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 has an explicit and useful 'Use when...' trigger clause with good natural keywords, but the capability statement relies on buzzwords ('Expert', 'beautiful', 'modern') rather than concrete actions, and the 'any user interface' scope is overly broad, raising conflict risk. It is a serviceable but imprecise description.

Suggestions

Replace buzzword padding ('Expert', 'beautiful, modern UIs') with 2-3 concrete capabilities, e.g. 'Generates design tokens and theme presets (oklch, dark mode, neo-brutalism), selects font pairings, and defines animation timing standards for UI work.'

Tighten the trigger scope and add natural synonyms, e.g. 'Use when building or styling landing pages, dashboards, web apps, or UI components, or when the user mentions frontend design, fonts, or themes.'

Add terms users actually say ('frontend', 'web design', 'styling', 'CSS') to improve trigger term coverage toward anchor 5.

DimensionReasoningScore

Specificity

The description names the domain ('frontend design guidelines for creating beautiful, modern UIs') but lists no concrete capabilities — 'Expert', 'beautiful', and 'modern' are buzzword padding rather than actions. It matches anchor 2 (domain named, actions minimal or generic), not 3, since no specific action like 'generates theme tokens' or 'plans responsive layouts' is stated.

2 / 5

Completeness

Both halves are explicitly present: the 'what' ('Expert frontend design guidelines for creating beautiful, modern UIs') and the 'when' ('Use when building landing pages, dashboards, or any user interface'). It sits at anchor 4 rather than 5 because the 'what' is generic and the trigger 'any user interface' is overly broad instead of a concrete trigger phrase, and above 3 because neither half is missing or merely implied.

4 / 5

Trigger Term Quality

'Use when building landing pages, dashboards, or any user interface' gives good natural keyword coverage ('landing pages', 'dashboards', 'user interface'), but common variations like 'frontend', 'web design', 'styling', 'CSS', or 'components' are missing. This fits anchor 4 (good coverage, a few natural terms missing) rather than 5 (synonyms and variants are incomplete) or 3 (coverage is genuinely good, not partial).

4 / 5

Distinctiveness Conflict Risk

'any user interface' would cause this skill to fire on virtually all UI-related work, creating real overlap risk with dataviz, branding, and component-library skills. This matches anchor 3 (somewhat specific — frontend design — but could still overlap with similar skills); the 'any user interface' breadth keeps it below 4.

3 / 5

Total

13

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository
bap-jorkim/agent-skills-fork-feb-25
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.