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.
84
77%
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
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 skill description that clearly articulates a specific workflow (design interviews → UI variations → feedback → implementation plans) and provides explicit trigger guidance. The description is concise yet comprehensive, with natural trigger terms and a distinctive enough process that it would be easily distinguishable from other UI-related skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'conduct design interviews', 'generate five distinct UI variations in a temporary design lab', 'collect feedback', and 'produce implementation plans'. These are clear, actionable steps. | 3 / 3 |
Completeness | Clearly answers both 'what' (conduct design interviews, generate UI variations, collect feedback, produce implementation plans) and 'when' with an explicit 'Use when...' clause covering three trigger scenarios. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'UI design options', 'redesign existing components', 'create new UI', 'multiple approaches to compare', 'design interviews', 'feedback'. These cover a good range of how users would phrase design exploration requests. | 3 / 3 |
Distinctiveness Conflict Risk | The combination of design interviews, five distinct UI variations in a design lab, feedback collection, and implementation plans creates a very specific niche. The 'temporary design lab' and 'five distinct variations' are highly distinctive elements unlikely to conflict with generic UI or design skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
55%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is extremely thorough and actionable with a well-structured multi-phase workflow and excellent error handling, but it is far too verbose for a SKILL.md file. At 500+ lines, it inlines content that should be split into referenced files (interview templates, code templates, variant guidelines). The exhaustive enumeration of every AskUserQuestion option and every detection heuristic wastes significant token budget on details Claude could derive from shorter instructions.
Suggestions
Extract interview question templates into a separate file (e.g., `interview-questions.md`) and reference it from SKILL.md with a one-line summary of each interview phase.
Move the FeedbackOverlay setup instructions, directory structure templates, and code examples into a `templates/` directory referenced by SKILL.md rather than inlining hundreds of lines of implementation detail.
Condense framework/package-manager detection into a simple lookup table rather than spelling out every config file pattern with prose explanations.
Remove explanatory text that Claude already knows (e.g., 'Running pnpm dev starts a long-running process that never exits. If you run it, you'll wait forever.') and reduce option descriptions in interview questions to just the option names.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~500+ lines. Extensively explains interview question formats, option labels, and descriptions that Claude can generate contextually. The full AskUserQuestion templates with every option spelled out, the detailed directory structures repeated multiple times, and lengthy inline code templates bloat the content significantly. Much of this could be condensed to patterns and principles rather than exhaustive enumeration. | 1 / 3 |
Actionability | Highly actionable with specific file paths, directory structures, concrete code examples (TSX integration, JSON schemas, markdown templates), exact detection logic for frameworks/package managers, and copy-paste ready templates for the design brief, implementation plan, and design memory files. | 3 / 3 |
Workflow Clarity | Excellent multi-phase workflow (Phase 0-8) with clear sequencing, explicit validation checkpoints (design brief confirmation, feedback collection, final preview confirmation), abort handling at any point, error recovery paths, and cleanup verification. The feedback loop between phases 5-7 is well-defined with iteration support. | 3 / 3 |
Progressive Disclosure | Monolithic wall of text with everything inline. References DESIGN_PRINCIPLES.md but includes massive amounts of detail that should be in separate files (interview templates, variant generation guidelines, feedback system setup, implementation plan templates). The entire feedback overlay setup, all interview questions, and all template content are inlined rather than referenced from supporting files. | 1 / 3 |
Total | 8 / 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
9f4534c
- 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.