CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/04-develop/01-ui-skills-dot-com/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 skill lays out a genuinely executable multi-phase workflow with concrete interview scripts, file structures, and cleanup safeguards, but it is carried in a ~900-line monolithic body with duplicated blocks and an internal contradiction about starting the dev server. Most seriously, it depends on two files (DESIGN_PRINCIPLES.md and the FeedbackOverlay template) that are absent from the bundle, one of which is marked as the skill's most critical component.

Suggestions

Ship the referenced files: add DESIGN_PRINCIPLES.md and templates/feedback/FeedbackOverlay.tsx to the bundle (e.g., under references/ and assets/), or inline the overlay implementation so the 'copy from templates' step is actually executable.

Split the ~150-line DESIGN_PLAN.md and DESIGN_MEMORY.md templates and the Phase 1 interview question scripts into one-level-deep reference files, keeping SKILL.md as a phase overview, and remove the duplicated 'Design Lab created!' presentation block.

Fix the internal contradiction: Example Session Flow step 8 says 'Plugin starts: pnpm dev' while Phase 4 explicitly forbids starting the dev server — align the example with the do-not-start rule.

DimensionReasoningScore

Conciseness

The body is mostly operational instruction, but contains padded sections: the 'Design Lab created!' output block is duplicated verbatim in Phases 4 and 5, the FeedbackOverlay criticality warning is repeated three times, and ~150 lines of DESIGN_PLAN.md/DESIGN_MEMORY.md templates are inlined. This fits 'mostly efficient but could be tightened' better than level 2 since the padding is a minority of the content.

3 / 5

Actionability

Concrete file trees, lockfile detection rules, a JSON brief schema, an executable TSX integration example, and an exact feedback-paste format give mostly executable guidance. It falls short of 5 because the FeedbackOverlay is sourced from 'design-and-refine/templates/feedback/FeedbackOverlay.tsx', a path that does not exist in the bundle, and variant generation is described directionally without code.

4 / 5

Workflow Clarity

Phases 0-8 are clearly sequenced with abort handling, an error-handling section, and deletion safety rules ('ONLY delete files inside .claude-design/', 'Verify file paths before deletion'). Not level 5 because Example Session Flow step 8 ('Plugin starts: pnpm dev') directly contradicts Phase 4's instruction to never start the dev server, creating ambiguity around a blocking operation.

4 / 5

Progressive Disclosure

No bundle files exist, yet the body instructs 'Read DESIGN_PRINCIPLES.md' and 'copy from templates' at 'design-and-refine/templates/feedback/FeedbackOverlay.tsx' — both references are dangling, and the referenced overlay is declared CRITICAL to the workflow. Combined with the monolithic ~900-line inline structure, this matches 'references are buried/broken and content that belongs in separate files is inlined' more than the merely-imperfect organization of level 3.

2 / 5

Total

13

/

20

Passed

Description

88%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 that states concrete capabilities in third person and pairs them with an explicit 'Use when...' clause covering redesign and new-UI scenarios. The only gaps are a few missing natural synonyms (e.g., mockups, design variations) and slight breadth in the 'create new UI' trigger.

DimensionReasoningScore

Specificity

The description lists four-plus concrete actions covering the full pipeline ('Conduct design interviews, generate five distinct UI variations in a temporary design lab, collect feedback, and produce implementation plans'), matching the comprehensive-coverage anchor rather than the minor-gaps level 4.

5 / 5

Completeness

It 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 concrete trigger phrases, exceeding the level-4 anchor where 'when' could be more explicit.

5 / 5

Trigger Term Quality

Natural trigger phrases like 'explore UI design options', 'redesign existing components', and 'multiple approaches to compare' are present, but common synonyms such as 'mockups', 'wireframes', or 'design variations' are missing, keeping it below the comprehensive level 5.

4 / 5

Distinctiveness Conflict Risk

The five-variant design-lab workflow is a mostly distinct niche with clear triggers, but 'create new UI with multiple approaches' overlaps broadly with general UI-generation skills, so it is not the minimal-conflict level 5.

4 / 5

Total

18

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (922 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository

marchatton/agent-skills

Path

.agents/skills/04-develop/01-ui-skills-dot-com/design-lab/SKILL.md

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.