Docs · v1.0.0

The skill-driven design harness.

17 skills, 16 sub-agents, a 10-phase pipeline, and 286 reference DESIGN.md files — installed into your AI coding agent in one command. No API keys. No external infra. Then you just talk to your agent.

$npx oh-my-design-cli install-skills
Quick start

Three steps · two minutes

step 01
Install in your project
In your project root:
$npx oh-my-design-cli install-skills
Installs for every detected agent — Claude Code / Codex / OpenCode / Cursor. Pin a single channel with --agent cursor (writes the .cursor/rules shim + the shared reference catalog). Restart your agent (Cmd+Q in Claude Code, then relaunch) so the new skills + agents are loaded.
step 02
Bootstrap a DESIGN.md
Open Claude Code / Codex / OpenCode / Cursor in the project, then say:
“Set up the design system for a calm B2B fintech dashboard.”
Agent picks a reference, proposes a hybrid DESIGN.md, asks you to confirm, writes the file plus shims.
step 03
Talk in natural language
That's it. From here on, you describe what you want — components, screens, copy, charts, 3D — and the agent applies your DESIGN.md, picks the right asset medium, and ships.
“Make the empty-state for the search results page.”
Skills · 9

Loaded into your agent's context, fired by triggers

Skills are markdown rule files that activate based on what you say. They route complex tasks to the right sub-agents.

omd:apply
Apply DESIGN.md
Trigger · Any UI task

Authoritative brand context for every UI request. Routes complex tasks (assets, charts, full screens, a11y audit) to specialist sub-agents.

omd:init
Bootstrap a project
Trigger · First-time setup

Pick from 286 reference design systems. Hybrid variation — preserves the reference voice while shifting only the axes you name.

omd:harness
Run the design pipeline
Trigger · /omd-harness <task>

10-phase pipeline (Discovery → Handoff) with 7 hero archetypes (rule 9 matches brand vibe to layout — center-text / carousel / split-screen / editorial / dashboard / quote-led / left-character). Wordmark-only logo (rule 5), reveal safety net (rule 10).

omd:remember
Capture preferences
Trigger · User correction detected

Append-only log at .omd/preferences.md. Auto-fires when you say things like "we never use uppercase CTAs" or "stop using emoji icons".

omd:learn
Merge preferences into DESIGN.md
Trigger · Fold corrections

Folds pending preferences back into DESIGN.md by scope (global / page / component). Keeps your brand spec the single source.

omd:sync
Sync agent pointers
Trigger · Maintain shims

Keeps CLAUDE.md, AGENTS.md, .cursor/rules/omd-design.mdc up-to-date so every coding agent reads the same DESIGN.md.

omd:reference-capture
Capture live design context
Trigger · Live brand fetch

Navigates the brand's live site via CDP and writes assets/_reference/<id>/ with tokens.json, structure.json, fonts.json, screenshots, and .live-inspect-proof.json. Phase 3.9 browser-harness fast-path auto-detected — 3-5x faster than playwright MCP when the user has it set up.

omd:asset-fetch
Free-license asset catalog
Trigger · Real placeholder assets

Looks up verified CC0 / MIT / SIL OFL CDN URLs (DiceBear avatars, Lucide icons, Picsum / Loremflickr photos, Bricolage Grotesque / Space Grotesk / DM Serif Display / Fraunces display fonts). Handcrafted character SVG is forbidden — every placeholder is a real licensed asset.

omd:experiment-gallery
N-brand comparison gallery
Trigger · Compare multiple runs

Builds a single index.html that previews every brand experiment under a folder as iframe-scaled cards with archetype badges, wow ratings, multi-turn deltas, and IP audit counts. Reusable across batches.

v0.2 agent layer · 6 skills · bundled

Multi-step authoring — orchestrated, KR-first, channel-aware

A supervisor + specialist topology for long-form authoring and image generation. Installed alongside the core skills — KR voice synthesis, locale adaptation, design review, publish QA, deterministic orthography linting, and channel-aware image generation.

omd:orchestrator
Supervisor topology
Trigger · Multi-step authoring

5-stage workflow (write → review → revise → localize → critic → images → handoff) with a hard 2-round revision cap. Anthropic orchestrator-workers + LangGraph supervisor pattern.

omd:kr-writer
Korean prose · 12 presets
Trigger · 한글 글 작성 · KR rewrite

toss-tech-design (default) / karrot-neighborly / brunch-maker / naver-d2 / biz-report / academic / journalism … Each preset has a 9-field voice spec. Anti translation-ese.

omd:locale-adapter
Adapt, don't translate
Trigger · EN/JP/ZH-TW 버전

KR is the source of truth. Cultural reference swaps, JP honorific matching, ZH-TW traditional idioms — voice/register match, not literal translation.

omd:designer-review
Visual + brand audit
Trigger · UI 리뷰 · 디자인 검토

Audits HTML/MD/JSX against DESIGN.md — typo hierarchy, color budget, radius scale, component states, mobile. Severity BLOCK / WARN / FYI with line refs. Read-only advisory.

omd:final-qa
8-item publish rubric
Trigger · 최종 QA · 출간 검수

Read-only critic. Forbids 'looks good' rubber-stamps, requires line refs for every FAIL, hard 2-round revision cap.

omd:codex-image
Channel-aware image gen
Trigger · 이미지 생성 · placeholder 채우기

One <!-- omd:gen-image --> spec, three downstream paths: Codex native generation · omd-asset-curator free-license fallback (Claude Code) · OpenCode user-queue. Idempotent, IP-safe (no logo/face synthesis).

Sub-agents · 16

Specialists, dispatched by the master orchestrator

omd-master runs the harness phases and dispatches the 10 harness specialists below in parallel where independent. The v0.2 agent layer adds 6 more (orchestrator / kr-writer / locale-adapter / designer-review / final-qa / codex-image) — shown in the section above.

opus
omd-master
Orchestrator

Conversational state machine. Runs the harness phases, asks the 3 mandatory user checkpoints, dispatches sub-agents.

opus
omd-ux-researcher
Research

Reads bundled references, validates Tier-1 official design system URLs, drafts the brief.

sonnet
omd-ui-junior
Wireframes & components · generator

Generates wireframes and component manifests strictly from DESIGN.md tokens. Defines all 5 states for every screen.

opus
omd-ux-engineer
Section UX audit · advisor

Section-level interaction / motion / IA / mobile / Web Vitals / WAI-ARIA audit + code-level fixes. NN/g + Refactoring UI integrated. Pairs with ui-junior (generator).

sonnet
omd-asset-curator
Asset medium picker

Picks medium (inline SVG / chart library / Lottie / Rive / Unsplash / 3D). Stack-aware (recharts vs chartjs, lucide vs heroicons).

sonnet
omd-microcopy
Voice copy · generator

Voice-consistent copy generation strictly tied to DESIGN.md §10. Refuses forbidden phrases.

opus
omd-ux-writer
Copy audit · advisor

Section-level copy audit + 2-3 strong alternatives + A/B hypothesis. Podmajersky / Mailchimp / Stripe / GitHub voice docs integrated. Pairs with microcopy (generator).

haiku
omd-a11y-auditor
Accessibility

Deterministic WCAG checks. axe-core + lighthouse + Tier-1 DS URL liveness. Pass/fail is binary.

sonnet
omd-persona-tester
Adversarial QA

Walks the generated UI under 4 strict personas (V/J/F/S) with hard turn budget. Emits 6 quantitative metrics.

opus
omd-critic
Root-cause review

Reads full run output, user feedback, persona ABANDONs. Writes a critique that re-enters at the lowest broken phase, not surface patches.

Pipeline · 4 stages · 10 phases

What happens on /omd-harness <task>

omd-master spawns the right specialists at each phase, asks 3 mandatory user checkpoints, and emits artifacts to .omd/runs/<id>/.

PhaseUser checkpointagentDispatched sub-agentParallel stage
01 · Plan

Define the brief and the constraints.

  • 01Discoverycheck

    Brief · constraints · success metrics

    agentmaster
  • 02Research

    Tier-1 DS scan · competitor URLs

    agentux-researcher
  • 03IA

    Information architecture · sitemap

    agentux-researcher
02 · System

Lock the brand tokens and components.

  • 04Wireframes

    ASCII wireframes · 5 states / screen

    agentui-junior
  • 05Design system

    DESIGN.md · tokens · philosophy

    agentmaster
  • 06Componentscheck

    Component manifest · variants

    agentui-junior
03 · Make∥ parallel

Generate artifacts in parallel.

  • 07Asset sourcing

    Inline SVG / chart / 3D / image picks

    agentasset-curator
  • 08Microcopy

    Voice-consistent copy · §10 cited

    agentmicrocopy
04 · Validate & Ship

Catch issues, package the deliverable.

  • 09Validation

    axe-core + 4-persona walkthrough

    agenta11y-auditor + persona-tester
  • 10Handoffcheck

    Zip · v0/Cursor-ready package

    agentmaster + critic
Parallel dispatch

Once the system is locked, Asset sourcing and Microcopy dispatch in parallel.

Both agents read the same DESIGN.md but emit independent artifacts — fastest end-to-end.

User checkpoints · 3

Three points where the harness pauses for your OK:

  • Discovery — does the brief look right?
  • Components — system tokens locked?
  • Handoff — ready to ship?

Skipping any aborts the run cleanly.

Use cases

Real prompts that route through real skills

What you say · what the agent does. No magic — every transition is a skill firing.

Set up the design system for a calm B2B fintech dashboard.
↳ what happens

Agent picks a reference (likely Linear or Stripe), proposes a hybrid DESIGN.md, asks for confirmation, writes the file plus shims.

Make the empty-state for the search results page.
↳ what happens

Reads DESIGN.md, builds the component with brand tokens, picks an inline SVG matching the voice, drops microcopy that follows §10 voice rules.

Design the entire onboarding from scratch — Toss-style for a family meal-tracking app.
↳ what happens

Invokes the harness — runs the 10-phase pipeline, spawns sub-agents in parallel, asks 3 user checkpoints, hands back a v0/Cursor-ready package.

Add a daily-intake line chart.
↳ what happens

Reads your package.json, sees recharts is installed, builds with brand colors. No library mismatch.

We never use uppercase CTAs.
↳ what happens

Silently appends to .omd/preferences.md. Next CTA anywhere in the project applies the rule. Run "fold preferences" later to merge by scope.

Install layout

Exactly what gets written to your project

Nothing hidden. Every path is documented; every owner is named.

PathOwnerPurpose
.claude/skills/omd-*/SKILL.mdinstall-skillsClaude Code skill bundle — 17 skills (core flow + capture/assets + v0.2 agent layer)
.agents/skills/omd-*/SKILL.mdinstall-skillsCodex skill bundle (same 17 skills — official discovery path)
.opencode/skills/omd-*/SKILL.mdinstall-skillsOpenCode skill bundle (same 17 skills)
.cursor/rules/omd-design.mdcinstall-skillsCursor channel (--agent cursor) — rules shim + shared .claude/data catalog, no skills/hooks
.claude/agents/omd-*.mdinstall-skills16 canonical sub-agents (master + 15 specialists)
.claude/data/*install-skillsreference catalog + ctx-prime, fingerprints, vocabulary, opt-out corpus
.claude/hooks/*.cjsinstall-skillsUserPromptSubmit / SessionStart / PostToolUse hooks
references/*/DESIGN.mdbundled286 real design systems
DESIGN.mdyour agentYour project's authoritative brand spec
CLAUDE.md / AGENTS.md / .cursor/rules/omd-design.mdcomd:syncPointers so every agent reads DESIGN.md
.omd/preferences.mdomd:rememberAppend-only design correction log
.omd/runs/<id>/omd:harnessPer-harness-run artifacts (briefs, wireframes, eval, handoff zips)
FAQ

Common questions

What is DESIGN.md?+

DESIGN.md is a structured markdown file that defines your project's brand spec — tokens (colors, typography, spacing, radius), voice, narrative, principles, personas, states, and motion. AI coding agents (Claude Code, Codex, OpenCode, Cursor) read it as authoritative context before generating any UI, so the output looks like your brand instead of generic 'modern minimalist' slop.

How does oh-my-design work?+

Run `npx oh-my-design-cli install-skills` once in your project. It installs 17 skills (core flow + live-capture + asset + the v0.2 agent layer: orchestrator, kr-writer, locale-adapter, designer-review, final-qa, codex-image), 16 sub-agents (master orchestrator + 15 specialists), 4 hooks, and 221 reference DESIGN.md files. After restarting your AI coding agent, you just talk in natural language — skills route to the right sub-agents automatically.

Does it call any AI provider during install?+

No. The install is a pure markdown copy — zero API calls, zero data leaves your machine. Your AI coding agent (Claude Code, Codex, OpenCode, or Cursor) is the inference layer; install just teaches it where to look.

How do I upgrade when a new release drops?+

Re-run `npx oh-my-design-cli@latest install-skills` in your project. It's idempotent — managed files (those with the `<!-- omd:installed-skill -->` marker) refresh in place; your edits without the marker stay untouched (status `skipped-drift`). Pass `--force` to overwrite custom edits. Then restart your agent. See CHANGELOG.md for what changed each release.

Which AI coding agents are supported?+

Claude Code, Codex, OpenCode, and Cursor — Cursor has a dedicated install channel (--agent cursor) that writes the .cursor/rules shim plus the shared reference catalog. The skill markdown files are agent-agnostic; hooks ship for Claude Code specifically.

Can my agent read a reference without installing anything?+

Yes. Every reference has a raw markdown twin at oh-my-design.kr/design-systems/<id>.md — agents can fetch the full DESIGN.md directly over HTTP. Curated sets by use case live at oh-my-design.kr/collections.

I customized a reference in the web builder — how do I hand it to my agent?+

The builder preview composes your first prompt from your live config (reference, components, token overrides, dark mode). Copy it from the install CTA and paste it into your agent — omd:init reads the prompt and bootstraps a matching DESIGN.md.

Can I bring my own DESIGN.md?+

Yes. If a DESIGN.md exists at repo root, omd:apply uses it as-is. Otherwise omd:init proposes a hybrid from one of the 221 references.

How do preferences differ from DESIGN.md?+

.omd/preferences.md is the running log of corrections (append-only). DESIGN.md is the canonical spec. Run "fold preferences" to merge by scope.

What is the design harness?+

The omd-harness skill runs a 10-phase design pipeline (Discovery → Research → IA → Wireframes → Design system → Components → Asset sourcing → Microcopy → Validation → Handoff). It dispatches sub-agents in parallel where independent, asks 3 mandatory user checkpoints, and emits a v0/Cursor-ready package. Trigger it by saying things like 'design the entire onboarding from scratch' or '/omd-harness <task>'.

What's a harness run?+

Invoking /omd-harness <task> creates .omd/runs/<id>/ and steps through the 10 phases. Each phase emits artifacts. The final zip is v0/Cursor-ready.

Is it free?+

Yes — MIT licensed, open source, no signup, no API key, no paid tier. The references in the bundle belong to their respective companies and are reproduced for educational reference only.