CtrlK
BlogDocsLog inGet started
Tessl Logo

ui-designer

Extract design systems from reference UI images and generate implementation-ready UI design prompts. Use when users provide UI screenshots/mockups and want to create consistent designs, generate design systems, or build MVP UIs matching reference aesthetics.

64

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

50%

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

The skill has a solid, well-sequenced workflow with real bundle assets, but loses points to inline duplication of asset content, a lack of validation checkpoints, and an abstract final implementation step.

Suggestions

Remove the inline Template Assets descriptions (lines 104-135) and rely on the one-line signaled references to assets/*.md to reduce duplication and token cost.

Add explicit validation checkpoints for generation outputs (e.g., 'verify the design system covers all template sections before proceeding; if gaps, re-run Step 2').

Make Step 6 (Implement UI) concrete with the actual component-scaffold steps or a pointer to an executable reference, instead of 'use the prompt to implement UI'.

DimensionReasoningScore

Conciseness

The workflow is mostly efficient, but the Template Assets sections (104-135) restate asset file contents inline that already live in assets/, the Notes section repeats Best Practices, and phrases like 'a good library'-style elaboration add padding rather than earning their tokens.

2 / 3

Actionability

Concrete templates, save paths, and copy-paste bash setup are strong, but Step 6 ('Use the final composed prompt... to implement UI') is abstract direction rather than concrete executable steps, and the actual implementation step is under-specified.

2 / 3

Workflow Clarity

A clear 6-step sequence is present, but there are no validation checkpoints or error-recovery feedback loops for the generation outputs (design system, PRD); the only verification checks the React environment. Per the rubric, missing validation in multi-step generation caps this at 2.

2 / 3

Progressive Disclosure

It points to well-signaled one-level-deep assets (assets/design-system.md, app-overview-generator.md, vibe-design-template.md), but the body duplicates those asset contents inline in the Template Assets section — content that should stay separate is inlined.

2 / 3

Total

8

/

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.

The description is concise, third-person, and clearly articulates both capabilities and explicit trigger conditions. It mirrors the strong reference examples in the rubric.

DimensionReasoningScore

Specificity

Names multiple concrete actions: 'Extract design systems from reference UI images', 'generate implementation-ready UI design prompts', plus build MVP UIs — matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers both what (extract design systems, generate prompts) and when via the 'Use when users provide UI screenshots/mockups...' trigger clause.

3 / 3

Trigger Term Quality

Covers natural user terms — 'UI screenshots/mockups', 'design systems', 'consistent designs', 'MVP UIs matching reference aesthetics' — terms a user would actually say when needing this skill.

3 / 3

Distinctiveness Conflict Risk

A clear niche — design-system extraction from reference UI images — with distinct triggers unlikely to fire for unrelated 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
daymade/claude-code-skills
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.