Oma Design logo

Oma Design

OrganizationPopular
first-fluke
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).

Overview

Publisherfirst-fluke
Repositoryoh-my-agent
Skill nameoma-design
Stars
1.4K
Forks
151
Bundled files
20
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 20 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by first-fluke on GitHub. Read the source before you install it.

Installation

Install the Oma Design AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/first-fluke/oh-my-agent/tree/main/benchmarks/runs/oma/.agents/skills/oma-design
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/first-fluke/oh-my-agent.git /tmp/oh-my-agent
mkdir -p .claude/skills
cp -r /tmp/oh-my-agent/benchmarks/runs/oma/.agents/skills/oma-design .claude/skills/oma-design
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Oma Design in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Oma Design on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Oma Design is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

oma-design

Scheduling

Goal

Design specialist that defines, creates, and validates project design systems. DESIGN.md is the central artifact — all design work revolves around it.

Intent signature

  • User asks for design system, DESIGN.md, visual direction, typography, color, motion, accessibility, anti-pattern review, or component guidance.
  • User needs design decisions before frontend implementation or wants UI quality audited from a design perspective.

When to use

  • Defining or revising a project design system
  • Creating or auditing DESIGN.md
  • Selecting typography, color, layout, motion, or component direction
  • Reviewing UI work for responsive behavior, accessibility, and visual quality
  • Using optional vendor inspiration from Stitch MCP or getdesign

When NOT to use

  • Implementing frontend components or application UI -> use oma-frontend
  • Planning product scope or task breakdown -> use oma-pm
  • Backend, database, infrastructure, or mobile implementation -> use the relevant specialist skill
  • General quality/security review outside visual, interaction, and accessibility concerns -> use oma-qa

Expected inputs

  • Product, brand, audience, platform, and UI/design problem
  • Existing .design-context.md, DESIGN.md, screenshots, references, or component constraints
  • Accessibility, responsive, language, and implementation constraints

Expected outputs

  • Design direction, revised DESIGN.md, audit findings, component guidance, or handoff notes
  • Responsive-first, WCAG-aware design recommendations
  • Optional vendor seed attribution when getdesign is used

Dependencies

  • .design-context.md and DESIGN.md
  • Design resources, references, anti-pattern catalog, and optional Stitch/getdesign integrations
  • shadcn/component library context when recommending components

Control-flow features

  • Branches by missing context, CJK language support, vendor seed availability, and anti-pattern audit results
  • May read/write design docs and call optional design/vendor tooling
  • Requires user confirmation before generation when multiple directions exist

Structural Flow

Entry

  1. Check .design-context.md; if missing, run setup before design work.
  2. Identify target audience, platform, content language, and design artifact.
  3. Decide whether vendor inspiration or Stitch integration is relevant.

Scenes

  1. PREPARE: Load design context and constraints.
  2. ACQUIRE: Extract existing design signals, references, and anti-pattern risks.
  3. REASON: Propose directions, typography, color, layout, motion, and accessibility choices.
  4. ACT: Generate or revise DESIGN.md and related guidance.
  5. VERIFY: Audit responsive behavior, WCAG, Nielsen heuristics, and AI-slop patterns.
  6. FINALIZE: Handoff design decisions and attribution where required.

Transitions

  • If .design-context.md is missing, create it before continuing.
  • If CJK support is needed, prioritize CJK-ready fonts.
  • If vendor seed fetch fails, choose retry, continue without seed, or abort.
  • If anti-patterns appear, surface alternatives before finalizing.

Failure and recovery

  • If design context is insufficient, ask for one focused clarification or propose assumptions.
  • If vendor inspiration is unavailable, continue with local design synthesis.
  • If accessibility checks fail, revise before handoff.

Exit

  • Success: design artifact is project-specific, responsive-first, accessible, and audit-ready.
  • Partial success: missing context, vendor failure, or open design decision is explicit.

Logical Operations

Actions

ActionSSL primitiveEvidence
Read design contextREAD.design-context.md, DESIGN.md, references
Select design directionSELECT2-3 directions and recommended option
Infer visual systemINFERTypography, color, layout, motion
Call optional toolingCALL_TOOLStitch/getdesign/shadcn when relevant
Write design artifactWRITEDESIGN.md or audit output
Validate design qualityVALIDATEChecklist, WCAG, anti-patterns
Report handoffNOTIFYFinal design summary

Tools and instruments

  • Design references, anti-pattern catalog, checklist, Stitch integration, getdesign fetcher
  • shadcn CLI recommendations when component guidance is needed

Canonical workflow path

text
1. Check `.design-context.md`; create it if missing.
2. Produce 2-3 design directions and get confirmation.
3. Generate or revise `DESIGN.md`, then run the design checklist.

Optional vendor seed discovery:

bash
bunx getdesign@latest list

Resource scope

ScopeResource target
LOCAL_FS.design-context.md, DESIGN.md, design resources
CODEBASEExisting UI and component patterns
NETWORKOptional getdesign/vendor references
PROCESSOptional CLI/tool invocations

Preconditions

  • Target design problem and artifact are identifiable.
  • Design context exists or setup can create it.

Effects and side effects

  • May create or modify DESIGN.md and design context artifacts.
  • May fetch vendor seed material and append MIT attribution.
  • Does not implement frontend code directly.

Guardrails

  1. Check .design-context.md before any design work. If missing, run Phase 1 (Setup) to create it.
  2. System font stack as default (system-ui, -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif). Add custom fonts only with project justification.
  3. If the service supports CJK languages (ko/ja/zh): prioritize CJK-ready fonts (Pretendard Variable > Noto Sans CJK > system-ui fallback). If latin-only: choose fonts appropriate for the target audience.
  4. Enforce anti-patterns strictly — reject AI slop. See resources/anti-patterns.md.
  5. Name colors semantically with hex values: "Deep Ocean Navy (#1a2332)" not "dark blue".
  6. Recommend components with install commands (shadcn CLI).
  7. ALL output must be responsive-first (mobile layout as default, enhance upward).
  8. WCAG AA minimum for all designs. Respect prefers-reduced-motion.
  9. Stitch MCP is optional — all phases work without it.
  10. Present 2-3 design directions and get user confirmation before generating.

Anti-Pattern Quick Reference

Typography

  • DON'T: Default to custom Google Fonts when system fonts suffice
  • DON'T: Use Inter/Geist alone without considering project context
  • DON'T: Load 3+ font families without justification
  • DON'T: Body text below 16px on mobile
  • DO: System font stack first, custom fonts for brand identity only
  • DO: Test CJK at every size (line-height 1.7-1.8)

Color & Gradient

  • DON'T: Purple-to-blue gradient backgrounds (strongest AI slop signal)
  • DON'T: Gradient orbs/blobs as hero decoration ("AI SaaS look")
  • DON'T: Gradient + glassmorphism + blur combo (triple slop)
  • DON'T: Mesh gradient backgrounds as primary visual
  • DON'T: Pure white (#fff) on pure black (#000) — too harsh
  • DO: Solid colors or subtle single-hue gradients
  • DO: Texture (noise, grain, dither) over plain gradients
  • DO: Derive gradients from brand colors with clear purpose

Layout

  • DON'T: Nested cards inside nested cards
  • DON'T: Desktop-only fixed-width layouts
  • DON'T: Hero with identical 3-metric stats layout (AI pattern)
  • DO: 8px grid, consistent section rhythm
  • DO: Responsive-first, works at 375px minimum
  • DO: Mix layout patterns (chess, grid, bento, full-bleed)

Motion

  • DON'T: Bounce easing on everything
  • DON'T: Animation duration > 800ms for UI transitions
  • DON'T: Ignore prefers-reduced-motion
  • DO: transform + opacity only for 60fps
  • DO: 150ms micro-interactions, 200-500ms transitions

Components

  • DON'T: Glassmorphism everywhere — use sparingly
  • DON'T: Hover-only interactions without touch/keyboard alternatives
  • DO: shadcn/ui for base, Aceternity UI / React Bits for accent effects
  • DO: All interactive elements must have visible focus states

Workflow Summary

7 phases: Setup → Extract → Enhance → Propose → Generate → Audit → Handoff. See resources/execution-protocol.md for full detail.

Vendor Inspiration (getdesign)

Phase 2 can optionally seed from the community getdesign catalog (VoltAgent/awesome-design-md, MIT). Trigger it by listing a supported vendor domain in the ## Reference Sites section of your .design-context.md:

markdown
## Reference Sites
- [linear.app](https://linear.app) — clean dark UI, minimal, professional
- [stripe.com](https://stripe.com) — strong hierarchy, purposeful animation

Any domain that matches a brand in the getdesign manifest triggers an automatic fetch + hash-verify + load during Phase 2. No new fields, no extra config. Full vendor list: see bunx getdesign@latest list (telemetry is always disabled by oma-design).

Seed, not final. oma-design treats vendor templates as inspiration and synthesizes a project-specific DESIGN.md around them. Importantly:

  • Typography is never adopted from the seed. Rule #2 (system font stack default) and Rule #3 (Pretendard Variable / Noto Sans CJK for ko/ja/zh) always win over the vendor's latin-only fonts.
  • Anti-patterns are pre-audited before synthesis. If a vendor uses heavy glassmorphism or purple gradients, Phase 4 will surface the choice explicitly rather than copy the pattern silently.
  • Offline is fine. If the fetch fails, you get a 3-option dialog (retry / continue without seed / abort). Default: continue.

Attribution is appended to the generated DESIGN.md in Phase 7 as a required MIT compliance footer. Full fetcher rules, matching algorithm, injection defenses, and multi-vendor merge policy live in resources/getdesign-fetcher.md.

Resources

  • resources/execution-protocol.md — 7-phase workflow
  • resources/anti-patterns.md — Full DO/DON'T catalog
  • resources/checklist.md — Audit checklist (Responsive + WCAG + Nielsen + Slop)
  • resources/design-md-spec.md — DESIGN.md generation guide (9 sections)
  • resources/design-tokens.md — CSS/Tailwind/shadcn export templates
  • resources/prompt-enhancement.md — Vague request → detailed spec
  • resources/stitch-integration.md — Stitch MCP tool mapping (optional)
  • resources/getdesign-fetcher.md — Vendor seed fetch, hash verify, seed rules
  • resources/error-playbook.md — Design error recovery

References

  • reference/visual-hierarchy.md — 7 hierarchy principles (Alignment, Color, Contrast, Proximity, Size, Texture, Time)
  • reference/typography.md — Font selection, type scale, CJK
  • reference/color-and-contrast.md — Color psychology, WCAG contrast
  • reference/spatial-design.md — 8px grid, breakpoints, spacing
  • reference/motion-design.md — motion/react, GSAP, Three.js, ogl, Temporal UX
  • reference/responsive-design.md — Mobile-first, theme system
  • reference/component-patterns.md — shadcn/Aceternity/React Bits catalog
  • reference/accessibility.md — WCAG 2.2, ARIA, focus, reduced-motion
  • reference/shader-and-3d.md — WebGL, R3F, ogl, performance

Examples

  • examples/design-context-example.md — .design-context.md example
  • examples/landing-page-prompt.md — Detailed landing page prompt

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Oma Design AI skill do?

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).

Why use Oma Design on TypingMind?

Because you install it once and use it with any model. Oma Design is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Oma Design in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/first-fluke/oh-my-agent/tree/main/benchmarks/runs/oma/.agents/skills/oma-design. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Oma Design?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Oma Design?

As many as you like. As long as a model supports skills, you can use Oma Design with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Oma Design AI skill free?

Yes. It is published on GitHub by first-fluke under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇