CtrlK
BlogDocsLog inGet started
Tessl Logo

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).

63

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./benchmarks/runs/oma/.agents/skills/oma-design/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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-organized, actionable skill overview with a strong validated workflow and clear progressive-disclosure structure, slightly held back by verbosity in the vendor section and bundle files that are referenced but not present.

Suggestions

Tighten the "Vendor Inspiration (getdesign)" section — the seed-vs-final rationale and 3-option dialog can be condensed without losing the key rules.

Ship the referenced bundle files (resources/anti-patterns.md, resources/execution-protocol.md, reference/*.md, examples/*.md) so the progressive-disclosure pointers resolve to real content.

Consider moving the inline Anti-Pattern Quick Reference fully into resources/anti-patterns.md and keeping only a 3-4 line summary in SKILL.md to reduce duplication with the Guardrails section.

DimensionReasoningScore

Conciseness

The body is dense and assumes Claude's competence — no basic-concept padding — with concrete DO/DON'T lists, guardrails, and commands; the getdesign/vendor section is somewhat verbose and could be trimmed, keeping it just below a 5.

4 / 5

Actionability

Provides concrete, executable guidance — exact system-font stack, hex color naming, `bunx getdesign@latest list`, shadcn install commands, DO/DON'T thresholds (16px body, 800ms animation) — with only minor gaps where direction remains high-level ("present 2-3 design directions").

4 / 5

Workflow Clarity

A clearly sequenced 7-phase workflow (PREPARE→VERIFY→FINALIZE) with an explicit VERIFY audit scene, a failure-and-recovery section with feedback loops ("If accessibility checks fail, revise before handoff"), and referenced checklists — matching the top anchor.

5 / 5

Progressive Disclosure

Well-structured overview with clearly signaled, one-line-described, one-level-deep references (9 resources, 9 reference files, 2 examples); held at 4 because the referenced bundle files (resources/, reference/, examples/) are not actually present to verify the split.

4 / 5

Total

17

/

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 is specific and well-scoped to a design-system niche with good natural trigger terms, but it omits an explicit "Use when..." trigger clause, which limits completeness.

Suggestions

Add an explicit "Use when..." sentence naming concrete triggers (e.g. defining a design system, creating/auditing DESIGN.md, choosing typography or color direction, UI accessibility review).

Include a few more natural user phrasings as trigger terms ("UI design", "visual direction", "design audit") to broaden keyword coverage.

Briefly signal the boundary ("not for frontend implementation") in the description to further reduce overlap with sibling skills.

DimensionReasoningScore

Specificity

Lists several concrete capability areas — "DESIGN.md management", "anti-pattern enforcement", "optional Stitch MCP integration", "component library guidance", plus typography, color, motion, responsive, and accessibility — giving specific coverage rather than vague language.

4 / 5

Completeness

The "what" is clear and specific, but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guidelines.

3 / 5

Trigger Term Quality

Includes natural keywords a user would say — "design system", "DESIGN.md", "typography", "color", "motion", "accessibility", "WCAG 2.2" — with good coverage, though a few common variants (e.g. "UI design", "visual direction") are only weakly implied.

4 / 5

Distinctiveness Conflict Risk

It carves a clear "AI design specialist" niche centered on DESIGN.md that is mostly distinct from frontend/pm/qa skills, with only minor overlap risk against a sibling frontend skill.

4 / 5

Total

15

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
first-fluke/oh-my-agent
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.