design-lab
Conduct design interviews, generate five distinct UI variations in a temporary design lab, collect feedback, and produce implementation plans. Use when the user wants to explore UI design options, redesign existing components, or create new UI with multiple approaches to compare.
81
Quality
73%
Does it follow best practices?
Impact
97%
1.64xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./data/skills-md/0xdesign/design-plugin/design-lab/SKILL.mdQuality
Discovery
85%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 description that clearly articulates a specific multi-step workflow for UI design exploration. It excels at completeness with explicit 'Use when' guidance and distinctiveness through its unique 'design lab' approach. The main weakness is trigger term coverage, which could benefit from additional natural language variations users might employ.
Suggestions
Add more natural trigger terms users might say, such as 'mockups', 'wireframes', 'prototypes', 'design alternatives', or 'A/B design comparison'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'conduct design interviews', 'generate five distinct UI variations', 'collect feedback', and 'produce implementation plans'. Uses third person voice correctly. | 3 / 3 |
Completeness | Clearly answers both what (conduct interviews, generate variations, collect feedback, produce plans) AND when ('Use when the user wants to explore UI design options, redesign existing components, or create new UI with multiple approaches'). | 3 / 3 |
Trigger Term Quality | Includes some natural terms like 'UI design options', 'redesign', 'components', but missing common variations users might say like 'mockups', 'wireframes', 'prototypes', 'layouts', or 'design alternatives'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'design lab', 'five distinct UI variations', and 'design interviews' creates a clear niche that distinguishes it from generic UI or design skills. The specific workflow described is unlikely to conflict with simpler design tools. | 3 / 3 |
Total | 11 / 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 skill provides an exceptionally thorough and actionable design exploration workflow with clear phases, validation checkpoints, and concrete code examples. However, it suffers from severe verbosity—the content could likely be reduced by 50-60% without losing functionality. The monolithic structure makes it harder to navigate despite good internal organization.
Suggestions
Reduce verbosity by removing redundant explanations (e.g., cleanup behavior is stated 3+ times, FeedbackOverlay importance is over-emphasized with warnings that could be a single clear instruction)
Extract interview questions into a separate INTERVIEW_QUESTIONS.md file and reference it, keeping only the flow logic in the main skill
Move the detailed code templates (FeedbackOverlay integration, Lab Page structure, Implementation Plan template) to separate template files in a templates/ directory
Consolidate the framework/styling detection sections into a concise checklist format rather than verbose prose with examples
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~600+ lines with significant redundancy. Explains concepts Claude knows (what PDF is, how frameworks work), repeats instructions multiple times (cleanup behavior mentioned 3+ times), and includes excessive detail that could be condensed significantly. | 1 / 3 |
Actionability | Provides highly concrete, executable guidance throughout. Includes specific file paths, complete code examples, exact directory structures, and copy-paste ready templates for FeedbackOverlay integration and route setup. | 3 / 3 |
Workflow Clarity | Excellent multi-phase workflow with clear sequencing (Phases 0-8), explicit validation checkpoints (confirm abort, confirm final design), and feedback loops (iterate on synthesis until satisfied). Includes error handling and abort procedures. | 3 / 3 |
Progressive Disclosure | References external files appropriately (DESIGN_PRINCIPLES.md, templates), but the main skill file is monolithic with ~600 lines that could be split. Interview questions, variant guidelines, and templates could be separate files with clear navigation. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (921 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- NeverSight/skills_feed
- Commit
5342bca
- 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.