CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

80

1.64x
Quality

71%

Does it follow best practices?

Impact

97%

1.64x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./data/skills-md/0xdesign/design-plugin/design-lab/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

60%Weight 40%Scale 1-5

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

The body is a thorough, actionable workflow with strong sequencing and real safety awareness, but it is long and repetitive and suffers from progressive-disclosure failures: large templates are inlined and referenced files (DESIGN_PRINCIPLES.md, FeedbackOverlay template) are absent from the bundle.

Suggestions

Add the referenced bundle files (DESIGN_PRINCIPLES.md and the FeedbackOverlay template under design-and-refine/templates/feedback/) or remove the references, so the skill does not point Claude at files that do not exist.

Extract the full DESIGN_PLAN.md and DESIGN_MEMORY.md templates into reference files linked from the body, leaving only the schema/shape inline, to reduce the ~921-line monolith.

De-duplicate the FeedbackOverlay emphasis and the lab-creation message (repeated in Phases 4 and 5), and consider dropping or shortening the "Example Session Flow" section that restates the phases.

DimensionReasoningScore

Conciseness

The 921-line body is mostly efficient and actionable but padded in places — the FeedbackOverlay importance is restated multiple times ("CRITICAL - NEVER SKIP", "CRITICAL - NEVER OMIT", "THIS IS THE MOST IMPORTANT REQUIREMENT"), the lab-creation message is duplicated across Phases 4 and 5, and the final "Example Session Flow" rehashes the phases. It does not over-explain concepts Claude already knows, but it could be tightened.

3 / 5

Actionability

Provides concrete, mostly executable guidance — exact AskUserQuestion options, a design-brief JSON schema, a directory tree, and a copy-paste-ready page.tsx example. Minor gaps (variant component bodies and the FeedbackOverlay template are described/referenced rather than fully coded) keep it just below a 5.

4 / 5

Workflow Clarity

A clear phased sequence (Phase 0–8) with confirmation checkpoints at each decision point and explicit safety rules for the destructive cleanup ("Verify file paths before deletion", "NEVER delete user-authored files"). It avoids the destructive-ops cap, but lacks an explicit validate-then-retry feedback loop for cleanup, so it sits below the 5-anchor.

4 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are empty), yet the body references DESIGN_PRINCIPLES.md and design-and-refine/templates/feedback/FeedbackOverlay.tsx that are not in the bundle. Content that clearly belongs in separate files — the full DESIGN_PLAN.md and DESIGN_MEMORY.md templates and the FeedbackOverlay template — is inlined, and the referenced template paths are effectively missing.

2 / 5

Total

13

/

20

Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: third-person voice, concrete actions, and an explicit "Use when..." clause with multiple natural triggers. It is comprehensive on completeness and only slightly shy of the top anchor on specificity, triggers, and distinctiveness.

DimensionReasoningScore

Specificity

Lists several concrete actions ("Conduct design interviews, generate five distinct UI variations... collect feedback, and produce implementation plans") with minor gaps in coverage; falls short of the fully comprehensive 5-anchor.

4 / 5

Completeness

Explicitly answers both what (interview, 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 to compare") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Good natural keyword coverage ("explore UI design options, redesign existing components, create new UI, multiple approaches to compare") but a few natural phrasings users might say are absent; not quite comprehensive enough for a 5.

4 / 5

Distinctiveness Conflict Risk

The "five distinct UI variations in a temporary design lab" framing carves a clear niche with mostly distinct triggers, though minor overlap with general UI/design skills keeps it just below the minimal-conflict 5-anchor.

4 / 5

Total

17

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (921 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
NeverSight/skills_feed
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.