CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

88

Quality

85%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

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 a strong, well-crafted skill description that excels across all dimensions. It provides specific concrete actions, extensive natural trigger terms, explicit 'Use when' guidance, and clear boundaries that distinguish it from other skills. The scope limitation ('purely visual') is a particularly effective touch for reducing conflict risk.

DimensionReasoningScore

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' with an explicit 'Use this skill whenever...' clause plus additional trigger phrases. Also includes a boundary statement clarifying it's 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 out niche: visual-only UI/UX auditing and refinement of existing apps. The explicit boundary ('purely visual — does not touch functionality, logic, or features') and specific trigger terms like 'design audit', 'visual refinement' make it highly distinguishable from general coding or feature-building skills.

3 / 3

Total

12

/

12

Passed

Implementation

70%

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 excellent workflow clarity and progressive disclosure. Its main weakness is actionability — it tells Claude what to evaluate but doesn't show concrete examples of audit output, design token proposals, or implementation notes. The philosophical framing adds some unnecessary tokens but the overall structure is strong and the scope boundaries are clearly defined.

Suggestions

Add a concrete example of what a Phase 1 finding looks like in the output (e.g., a sample audit item with the specific format: problem description, current state, proposed change, implementation note for build agent)

Include an example of a design system token proposal to show the expected format when new values are needed (e.g., proposing a new shadow token with before/after context)

DimensionReasoningScore

Conciseness

The skill is mostly efficient and well-structured, but includes some philosophical framing ('feel inevitable', 'like no other design was ever possible') that doesn't add actionable value. The audit dimensions table is dense but each row earns its place. Some reduction filter questions are somewhat redundant with each other.

2 / 3

Actionability

The skill provides a clear structured process and specific dimensions to evaluate, but lacks concrete executable examples — no code snippets for implementation, no example audit output, no sample design token proposals. The guidance is specific in what to evaluate but abstract in how to produce the deliverable, relying on an external template file for the actual output format.

2 / 3

Workflow Clarity

The four-step workflow is clearly sequenced with explicit checkpoints: audit → reduce → compile plan → wait for approval. The approval gate before implementation is a strong validation checkpoint. Post-implementation steps include verification (before/after comparison) and documentation updates. The phase-by-phase execution with review between phases provides a clear feedback loop.

3 / 3

Progressive Disclosure

Content is well-organized with clear sections. References to external files (design-principles.md, audit-template.md) are one level deep and clearly signaled. The prerequisite reading list is upfront, and the main content stays focused on the audit process rather than inlining reference material.

3 / 3

Total

10

/

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
bencium/bencium-marketplace
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.