oma-design

AI design specialist skill with DESIGN.md management, anti-pattern enforcement, optional Stitch MCP integration, and component library guidance. Covers typography, color systems, motion design (motion/react, GSAP, Three.js), responsive-first layouts, and accessibility (WCAG 2.2).

Quality

65%

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 ./.agents/skills/oma-design/SKILL.md

Quality

Content

62%

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

The skill body has a clear, well-validated workflow and good concrete anchors, but suffers from duplicated inline content and a critical progressive-disclosure defect: all referenced detail files (resources/*, reference/*, examples/*) are missing from the bundle.

Suggestions

Provide the referenced bundle files (resources/anti-patterns.md, resources/execution-protocol.md, resources/design-md-spec.md, reference/*.md, examples/*.md) or remove the dangling references.

Remove the inline anti-pattern quick reference from SKILL.md since it duplicates resources/anti-patterns.md, keeping only a pointer to preserve token efficiency.

Inline the minimal executable skeleton for DESIGN.md's 9 sections (or ensure resources/design-md-spec.md exists) so the core deliverable is actionable without a missing file.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and avoids explaining known concepts, but pads the body with a full inline anti-pattern quick reference that is also stated to live in resources/anti-patterns.md, plus 'SSL primitive' jargon (READ/INFER/CALL_TOOL) that adds tokens without clear value.	2 / 3
Actionability	Provides concrete executable anchors (bunx getdesign@latest list, the system font stack, CJK font ordering, motion timings, 375px/8px grid), but the central deliverable — generating DESIGN.md's 9 sections — is delegated to a missing resources/design-md-spec.md, leaving the core task's executable detail absent.	2 / 3
Workflow Clarity	Presents a clearly sequenced 7-phase workflow (Setup → Extract → Enhance → Propose → Generate → Audit → Handoff) with explicit validation checkpoints (VERIFY audits WCAG/Nielsen/slop, 'revise before handoff') and feedback loops (getdesign retry/continue/abort dialog), matching the score-3 anchor.	3 / 3
Progressive Disclosure	The body signals one-level-deep references well (Resources, References, Examples sections with per-file descriptions), but every referenced bundle file (resources/, reference/, examples/*) is absent from disk, so the references are dangling, and the anti-pattern catalog is duplicated inline rather than truly offloaded.	2 / 3
	Total	9 / 12 Passed

Description

67%

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 clearly conveys a broad, concrete capability set but omits any explicit 'Use when…' trigger guidance, which caps trigger_term_quality and completeness at 2. Specificity and distinctiveness are strong.

Suggestions

Add an explicit 'Use when…' clause naming natural user triggers (e.g., 'Use when the user wants a design system, DESIGN.md, visual direction, typography/color/motion direction, or an accessibility/UI design audit').

Reframe specialist terms like 'anti-pattern enforcement' and 'Stitch MCP integration' into phrasings a user would naturally say (e.g., 'review for AI-slop design patterns', 'pull vendor design inspiration').

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions and capabilities — 'DESIGN.md management, anti-pattern enforcement, optional Stitch MCP integration, and component library guidance' plus 'typography, color systems, motion design (motion/react, GSAP, Three.js), responsive-first layouts, and accessibility (WCAG 2.2)' — matching the score-3 anchor of comprehensive concrete actions.	3 / 3
Completeness	Clearly and comprehensively answers 'what does this do', but provides no explicit 'when should Claude use it' guidance — no 'Use when…' clause — so per the rubric guideline a missing trigger clause caps completeness at 2.	2 / 3
Trigger Term Quality	Contains some natural user keywords (typography, color, motion, accessibility, design system) but frames them as specialist capabilities ('anti-pattern enforcement', 'Stitch MCP integration') without a 'Use when…' trigger phrasing, missing common natural variations a user would actually say.	2 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (project design systems, DESIGN.md, visual direction) with distinct triggers (Stitch MCP, GSAP, Three.js, WCAG 2.2) and explicit sibling-skill boundaries, making it unlikely to trigger for the wrong skill.	3 / 3
	Total	10 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: first-fluke/oh-my-agent
Path: .agents/skills/oma-design/SKILL.md
Commit: 3021301

Reviewed: about 21 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.