moai-domain-design-dna

Reverse-engineer a reference design — a screenshot, an image set, or a live URL — into a portable Design DNA JSON across three dimensions (measurable tokens, qualitative style, special-rendering effects), then generate a new self-contained artifact from that JSON. Carries the extraction rules (dominance-based colour roles, relative radius measurement, multi-reference conflict resolution), a performance-tier technology map for Canvas / WebGL / shader / scroll effects, and a delivery gate covering contrast, reduced motion, and animation-loop hygiene.

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/moai-domain-design-dna/SKILL.md

Quality

Content

85%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 content is a well-structured, actionable overview with clear phased workflow, explicit validation checkpoints, and clean progressive disclosure into three real reference files; its only weakness is light narrative framing that slightly dilutes token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence without explaining basic concepts, but the opening narrative ('Most make it look like this requests fail the same way...') and some rationale prose are mild over-explanation that could be trimmed.	4 / 5
Actionability	Concrete, specific guidance pervades — numbered extraction rules ('Measure radius relatively', 'Infer type scale from ratios'), an ordered generation sequence, and a delivery-gate checklist with exact thresholds (4.5:1 contrast, requestAnimationFrame) — though implementation detail is delegated to references rather than given as inline code.	4 / 5
Workflow Clarity	Three phases are explicitly sequenced, Phase 3 lists a constrained generation order, the delivery gate is a verification checklist, polish iteration is a feedback loop (re-read, audit six axes, merge), and profile persistence has confirm-before-overwrite and verify-by-re-read checkpoints.	5 / 5
Progressive Disclosure	The body is an overview that signals three real one-level-deep references (dna-schema.md, diagram-profiles.md, effects-implementation.md, all present in references/) via inline callouts and a dedicated References section, with schema, persistence, and effects detail appropriately split out.	5 / 5
	Total	18 / 20 Passed

Description

63%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.

The description is specific and comprehensive about what the skill does, but it front-loads technical vocabulary over natural user trigger phrases and relies on a separate when_to_use field for the 'when' half of the trigger guidance.

Suggestions

Fold a brief 'Use when ...' trigger clause (with natural phrasings like 'build this in the same style as this screenshot' or 'copy this design') into the description field itself so completeness is not capped by the separated when_to_use field.

Soften jargon like 'dominance-based colour roles' and 'performance-tier technology map' in favor of terms a user would actually say, improving trigger_term_quality.

Add a short negative boundary ('not for charts, reports, or static diagrams') inside the description to reduce overlap risk with sibling design skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Reverse-engineer a reference design ... into a portable Design DNA JSON', 'generate a new self-contained artifact', plus carried extraction rules, a technology map, and a delivery gate — giving comprehensive coverage rather than vague abstraction.	5 / 5
Completeness	The description gives a clear 'what' but contains no 'Use when...' trigger clause, which per the guidelines caps completeness at 3; the 'when' guidance is segregated into the separate when_to_use field rather than the description itself.	3 / 5
Trigger Term Quality	Relevant keywords like 'screenshot', 'image set', 'live URL', and 'reference design' appear, but the language leans technical ('Design DNA JSON', 'dominance-based colour roles', 'performance-tier technology map') and omits the natural user phrasings ('build this in the same style as...', 'copy this look') that live in when_to_use instead.	3 / 5
Distinctiveness Conflict Risk	The reverse-engineer-a-reference-into-JSON-then-generate niche is clearly distinct from authoring-from-scratch skills, though there is minor overlap risk with closely related design skills (moai-domain-html-report, moai-ref-ui-polish) that the description does not explicitly disambiguate.	4 / 5
	Total	15 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: modu-ai/moai-adk
Path: .claude/skills/moai-domain-design-dna/SKILL.md
Commit: 2213871

Reviewed: 4 hours ago

Table of Contents

Discovery Implementation Validation

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.