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

75%

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

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 body is a well-structured, highly actionable design skill with an explicit phased workflow, validation checkpoints, recovery loops, and excellent progressive disclosure to one-level-deep resources. Its only weak spots are minor conciseness overhead from the formal scheduling/SSL framing and a few actionability gaps where commands are named but not shown.

Dimension	Reasoning	Score
Conciseness	The body is dense and prescriptive (specific font stacks, motion durations, hex-naming rules, AI-slop signals) without explaining concepts Claude already knows, but the formal Scheduling/Structural Flow/Logical Operations framing with SSL primitives adds some overhead that could be trimmed, keeping it just below anchor 5.	4 / 5
Actionability	Mostly executable guidance with concrete commands ("bunx getdesign@latest list", exact font stack, Pretendard > Noto Sans CJK ordering, 150ms/200-500ms motion targets) and code blocks, but some guidance stays at the rule level ("recommend components with install commands (shadcn CLI)" without showing the install command), leaving minor gaps versus copy-paste-ready anchor 5.	4 / 5
Workflow Clarity	Clear 7-phase sequence (Setup -> Extract -> Enhance -> Propose -> Generate -> Audit -> Handoff) with an explicit VERIFY validation phase, a Failure-and-recovery section, feedback loops (vendor fetch retry/continue/abort; accessibility fail -> revise before handoff), and a referenced checklist, matching the explicit-validation-plus-feedback-loops anchor 5.	5 / 5
Progressive Disclosure	The body is an overview that points to well-signaled, one-level-deep resource and reference files, each listed with a one-line description (e.g. "resources/anti-patterns.md: Full DO/DON'T catalog"), with the inlined quick reference appropriately summarized and the full catalog deferred, matching the clear-overview-plus-easy-navigation anchor 5.	5 / 5
	Total	18 / 20 Passed

Description

66%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 clearly communicates a design-system niche with solid natural trigger terms, but it lacks any explicit "Use when..." trigger guidance, which caps completeness and weakens distinctiveness versus the body's routing. Adding a one-line "Use when..." clause would lift the two weakest dimensions.

Suggestions

Append an explicit trigger clause, e.g. "Use when creating or auditing a project design system, DESIGN.md, or visual direction (typography, color, motion, layout, accessibility)."

Reframe capabilities as concrete verbs ("Manages DESIGN.md, enforces anti-patterns, guides component selection") instead of noun forms ("management", "enforcement", "guidance") to push specificity toward anchor 5.

Add a brief disambiguating phrase distinguishing this from frontend implementation (e.g. "design decisions only, not component implementation") to reduce overlap risk with frontend skills.

Dimension	Reasoning	Score
Specificity	Lists several concrete capabilities ("DESIGN.md management, anti-pattern enforcement, optional Stitch MCP integration, and component library guidance") plus coverage areas (typography, color, motion, responsive, accessibility), but the actions are framed as nouns (management/enforcement/guidance) rather than verbs, leaving minor gaps versus the fully concrete anchor 5.	4 / 5
Completeness	Has a clear "what" (design specialist managing DESIGN.md, enforcing anti-patterns, covering typography/color/motion/responsive/accessibility) but no "Use when..." clause or equivalent explicit trigger guidance, so per the judging guideline completeness is capped at 3.	3 / 5
Trigger Term Quality	Good natural keyword coverage ("design system", "DESIGN.md", "typography", "color systems", "motion design", "responsive-first layouts", "accessibility", "WCAG 2.2") that users would plausibly say, but missing some synonyms/common variations; not the comprehensive synonym-plus-extension coverage of anchor 5.	4 / 5
Distinctiveness Conflict Risk	The DESIGN.md-centric design-system niche is mostly distinct with clear triggers, but there is minor overlap risk with closely related frontend/UX skills since the description alone does not state the boundary (the body's "When NOT to use" does, but the description does not).	4 / 5
	Total	15 / 20 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: 032c988

Reviewed: 2 days 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.