CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

refactoring-ui

Audit and fix visual hierarchy, spacing, color, and depth in web UIs. Use when the user mentions "my UI looks off" (or amateur/unprofessional), "fix the design", "Tailwind styling", "color palette", "visual hierarchy", "design system", "spacing scale", or "component styling". Also trigger when building consistent design tokens, creating dark mode themes, improving data-visualization clarity, or polishing UI details before launch. Covers grayscale-first workflow, constrained design scales, shadows, and component styling. For typeface selection, see web-typography. For usability audits, see ux-heuristics.

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

71%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.

A well-structured, highly actionable design reference with excellent progressive disclosure and a clear diagnostic workflow. Main weakness is conciseness: rationale paragraphs, author bios, and overlapping tables add tokens that partly restate knowledge Claude already has.

Suggestions

Trim or remove the 'About the Authors' section and consolidate 'Further Reading' to non-affiliate links — these add tokens without aiding task execution.

Collapse the 'Common Mistakes' table into the 'Quick Diagnostic' (or vice versa) since they cover the same failure modes; keep only the actionable checklist.

Shorten the per-principle 'Why it works' paragraphs to a single line or drop them where the rationale is design knowledge Claude already has (e.g., hierarchy, spacing) and keep them only where the opinionated rule is non-obvious.

DimensionReasoningScore

Conciseness

Mostly efficient dense reference tables and CSS patterns, but padded with seven 'Why it works' rationale paragraphs (some restating design knowledge Claude already has), an 'About the Authors' section, affiliate-linked 'Further Reading', and a 'Common Mistakes' table that overlaps the 'Quick Diagnostic'. Could be tightened.

3 / 5

Actionability

Highly concrete guidance — specific px scales (4/8/16/24/32/48/64), modular type scales, hex values (#111827, #64748b), Tailwind class patterns (p-4, shadow-md, text-gray-900), and context→technique→example tables — with only minor gaps in complete component code blocks.

4 / 5

Workflow Clarity

Clear sequenced workflow — grayscale-first, add color last, details last — anchored by an 8-row 'Quick Diagnostic' checklist and an explicit scoring formula with feedback ('state the current score and the specific diagnostic rows to fix to reach 10/10'). Minor gap: no explicit error-recovery loop, though the diagnostic re-score loop partly covers it.

4 / 5

Progressive Disclosure

Clear overview of seven principles with well-signaled, one-level-deep references to five real bundle files (advanced-patterns, theming-dark-mode, accessibility-depth, animation-microinteractions, data-visualization), each introduced with a 'See [references/X.md] when...' trigger so navigation is easy and content is appropriately split.

5 / 5

Total

16

/

20

Passed

Description

100%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.

An exemplary description: concrete capabilities, comprehensive natural triggers, explicit what/when guidance, and clear boundary routing to sibling skills. Third-person imperative voice is used throughout with no first/second person.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Audit and fix visual hierarchy, spacing, color, and depth', 'building consistent design tokens', 'creating dark mode themes', 'improving data-visualization clarity', 'polishing UI details' — giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Explicitly answers both 'what' ('Audit and fix visual hierarchy, spacing, color, and depth in web UIs') and 'when' ('Use when the user mentions...') with concrete trigger phrases and additional 'Also trigger when...' conditions.

5 / 5

Trigger Term Quality

Comprehensive natural trigger phrases users would actually say — 'my UI looks off', 'amateur/unprofessional', 'fix the design', 'Tailwind styling', 'color palette', 'visual hierarchy', 'design system', 'spacing scale', 'component styling' — including synonyms and variations.

5 / 5

Distinctiveness Conflict Risk

Clear niche in visual design refinement with distinct triggers, and explicit boundary routing ('For typeface selection, see web-typography. For usability audits, see ux-heuristics') minimizes overlap with adjacent skills.

5 / 5

Total

20

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

wondelai/skills

Path

refactoring-ui/SKILL.md

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.