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 18 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 326 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.

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.

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 '.

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.

oh-my-design v1.8.6 (2026-06-23)

New skill omd:feel — quantifies the design / frontend industry's "gut-feel" into 113 provenance-graded, machine-checkable interface rules an AI can APPLY (inject motion / spacing / type / a11y defaults during UI work) and AUDIT (BLOCK / WARN / FYI). Inherits Jakub Krehel's make-interfaces-feel-better and extends it with Apple HIG / Material 3 / WCAG / design-system tokens + practitioner research.

17 feel-dimensions, 113 rules. 85 are spec / design-system-token-backed (enforceable); the rest are labelled convention / opinion so folklore is never presented as spec. Core idea: provenance tier → enforcement strength (SPEC/DS = gate, CONV = default, OP/FOLK = suggestion). DESIGN.md tokens always win. Files: skills/omd-feel/{SKILL.md, reference.md, provenance.md} — auto-installs via install-skills. Skill bundle 17 → 18.
Dogfooded on this site's home + docs: fixed a real prefers-reduced-motion a11y gap (framer-motion + animate-ping + smooth-scroll were ungated) via a global CSS net + <MotionConfig reducedMotion="user">, swept transition: all → named props on the landing / docs surfaces, and added text-wrap: balance / pretty. tsc + 553 tests green.
Docs / README: reference count corrected 286 → 326 across localized READMEs + site metadata (catalog grew in 1.8.3–1.8.4; localized surfaces had drifted).

New skill `omd:feel` — quantifies the design / frontend industry's "gut-feel" into 113 provenance-graded, machine-checkable interface rules an AI can APPLY (inject motion / spacing / type / a11y defaults during UI work)