design-audit
Premium UI/UX design audit and refinement skill. Conducts systematic visual audits of existing apps and produces phased, implementation-ready design plans. Use this skill whenever the user asks to audit a UI, improve an app's visual design, make an interface feel more polished or premium, review design consistency, fix visual hierarchy, or refine spacing/typography/color. Also trigger when the user says "design review", "make it look better", "UI polish", "visual refinement", "design pass", "audit the design", or references making an app feel more professional. This skill is purely visual — it does not touch functionality, logic, or features. It elevates what exists.
68
81%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
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.
This is an excellent skill description that hits all the marks. It provides specific concrete actions, comprehensive natural trigger terms, explicit 'Use when' guidance, and clear boundary definitions that distinguish it from other skills. The scope exclusion ('does not touch functionality, logic, or features') is a particularly strong differentiator.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: 'conducts systematic visual audits', 'produces phased, implementation-ready design plans', and specifies scope areas like 'spacing/typography/color', 'visual hierarchy', 'design consistency'. Also clearly scopes what it does NOT do (functionality, logic, features). | 3 / 3 |
Completeness | Clearly answers both 'what' (conducts visual audits, produces phased design plans, refines spacing/typography/color/hierarchy) and 'when' (explicit 'Use this skill whenever...' clause with detailed trigger scenarios and phrases). Also includes boundary clarification ('purely visual'). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would actually say: 'audit a UI', 'make it look better', 'UI polish', 'visual refinement', 'design pass', 'design review', 'make an app feel more professional', 'polished or premium'. These are highly natural phrases. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly carved niche: visual-only UI/UX auditing and refinement, explicitly excluding functionality/logic/features. The boundary statement 'purely visual — it does not touch functionality, logic, or features' strongly differentiates it from general coding or feature-building skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured design audit skill with a clear multi-step workflow and strong scope discipline. Its main weaknesses are the lack of concrete, executable examples (no code snippets, token examples, or sample output formats inline) and some philosophical verbosity that doesn't add actionable value. The referenced bundle files don't exist, which undermines the progressive disclosure strategy.
Suggestions
Include a concrete example of audit output (even abbreviated) inline rather than deferring entirely to 'references/audit-template.md', so the skill is actionable even if the reference file is missing.
Trim philosophical framing ('feel inevitable', 'like no other design was ever possible') — Claude doesn't need motivational design philosophy to execute the audit protocol.
Add a small concrete example of a design system token proposal format, so the instruction 'propose it — don't invent it silently' is actionable rather than abstract.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some unnecessary philosophical framing ('feel inevitable', 'like no other design was ever possible', 'If a user needs to think about how to use it, you've failed') that Claude doesn't need. The audit table and scope sections are well-structured but could be tighter in places. | 2 / 3 |
Actionability | The audit dimensions table provides clear evaluation criteria and the phased plan structure is concrete, but there are no executable code examples, no specific CSS/token snippets, and the guidance relies on reading external templates ('references/audit-template.md') for the actual output format rather than showing it inline. The 'Reduction Filter' is philosophical rather than actionable. | 2 / 3 |
Workflow Clarity | The four-step workflow (Audit → Reduce → Compile Plan → Wait for Approval) is clearly sequenced with explicit checkpoints: present plan before implementing, get approval, execute surgically, present results before next phase. The post-implementation checklist adds a validation/documentation step. The approval gate is a strong feedback loop for a design-oriented skill. | 3 / 3 |
Progressive Disclosure | The skill references external files like 'references/design-principles.md' and 'references/audit-template.md' which is good progressive disclosure structure, but no bundle files are provided, meaning those references are unverifiable. The main content is somewhat long and the detailed audit dimensions table could potentially be in a reference file, with just the high-level process in the SKILL.md. | 2 / 3 |
Total | 9 / 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- bencium/bencium-marketplace
- Commit
2e2fa33
- 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.