Design Skill
SkillMediaThe design skill is a repo-local workflow that keeps a DESIGN.md file as the source of truth for product, UI/UX, and frontend decisions. It has the agent inspect existing design docs, code, themes, and screenshots, ask targeted questions about anything missing, then write or refresh a structured DESIGN.md covering branding, personas, IA, visual language, accessibility, and constraints. Later UI work cites this file so decisions stay consistent.
Available today. Use it from your connected AI after setup.
No other account needed.
Have a repository with product, UI, or frontend work that needs a design source of truth.
Then ask your AI: use the Design Skill skill
What your AI can do with it
- Inspect existing DESIGN.md, design docs, README, specs, and issues
- Review routes, pages, layouts, components, stories, and theme files
- Examine assets, screenshots, mockups, and Storybook or Playwright baselines
- Ask targeted questions only for design-critical gaps
- Create or refresh a structured DESIGN.md with defined sections
- Record assumptions and open questions when answers are unavailable
Getting started
- Have a repository with product, UI, or frontend work that needs a design source of truth.
- Invoke the design skill so the agent can discover local design evidence.
- Answer the agent's targeted questions about missing context.
- Review the generated or refreshed DESIGN.md at the repository root.
- Cite DESIGN.md in later UI work so decisions stay consistent.
What this skill tells your AI
The instructions your AI receives, as published by yeachan-heo/oh-my-codex in skills/design/SKILL.md and read by ahel’s review.
Use $design to discover product and UI evidence, close only design-critical context gaps, and create or refresh the repository’s durable DESIGN.md contract. It is a maintained design brief, not a pixel-matching loop or one-off critique.
Shared operating, delegation, state, hook, team, cancellation, and verification invariants live in templates/AGENTS.md. Follow that source instead of duplicating its rules here.
Use when
- Product, UX, frontend, or design-system decisions need a repo-local source of truth.
- A feature needs a design brief before a designer lane or implementation.
- Existing UI, assets, screenshots, or constraints need an actionable design summary.
Do not use it for visual-reference implementation matching (use $visual-ralph), screenshot comparison alone, or backend/infrastructure work without user-facing design impact.
Relationship to $visual-ralph
$design owns product goals, users, information architecture, visual language, components, accessibility, constraints, and open questions in DESIGN.md. $visual-ralph owns implementation against an approved visual reference or live-URL baseline, measured verdicts, and pixel-diff evidence. Run $design first when both are needed; DESIGN.md supports but does not replace the visual verdict target.
Workflow
1. Discover local evidence
Inspect and cite existing DESIGN.md, design/UX/frontend docs, README/specs/issues, routes/pages/layouts/components/stories, theme and token files, assets, screenshots/mockups, Storybook or Playwright baselines, and accessibility/responsive/i18n/platform constraints. Separate observations from inferences; note absent evidence.
2. Interview only missing context
Ask concise questions only for gaps the repository cannot resolve: users/jobs, goals/non-goals, brand personality and forbidden aesthetics, primary flows, accessibility/device/browser targets, or unavailable assets/references. If answers are unavailable, record explicit assumptions and open questions rather than blocking.
3. Create or refresh DESIGN.md
Preserve useful content, remove contradictions, mark unknowns, and keep decisions actionable. The root file must contain these sections:
Design
Source of truth
Status (Draft | Active | Needs refresh), date, product surfaces, evidence reviewed.
Brand
Personality, trust signals, avoid.
Product goals
Goals, non-goals, success signals.
Personas and jobs
Primary personas, user jobs, contexts of use.
Information architecture
Navigation, routes/screens, content hierarchy.
Design principles
Principles and tradeoffs.
Visual language
Color, typography, spacing, shape/elevation, motion, imagery/iconography.
Components
Existing/new components, variants/states, token ownership.
Accessibility
Target standard, keyboard/focus, contrast, semantics, reduced motion/sensory concerns.
Responsive behavior
Breakpoints/devices, layout adaptations, touch/hover differences.
Interaction states
Loading, empty, error, success, disabled, offline/slow network where applicable.
Content voice
Tone, terminology, microcopy rules.
Implementation constraints
Framework/styling, tokens, performance, compatibility, test/screenshot expectations.
Open questions
[ ] question, owner, and impact.
4. Apply the contract
Before UI decisions, cite relevant DESIGN.md sections, reuse documented components/tokens, and update the file or add an open question when implementation exposes a contradiction. Do not invent a parallel design-system layer.
5. Handoff
For normal frontend work, provide the relevant sections, repo evidence, and acceptance criteria. For visual-reference, image, or live-URL matching, hand off to $visual-ralph with the approved baseline and identify DESIGN.md as supporting context only.
Evidence and completion
Complete only when design docs/assets/components/screenshots were inspected or noted absent; missing context is answered, assumed, or listed; root DESIGN.md contains every required section; recommendations cite it; and any Visual Ralph handoff is clearly separated from design governance.
Task: {{ARGUMENTS}}
Signals
- GitHub stars
- 33k
- Forks
- 3k
- Last commit
- Oct 2026
Questions
- What is a design skill?
- It is a repo-local workflow that keeps a DESIGN.md file as the source of truth for product, UI/UX, and frontend decisions.
- What is a design claude skill?
- It is the same design skill: it inspects existing design evidence, asks about gaps, and writes or refreshes a structured DESIGN.md.
- What is a design agent skill?
- It is a skill an AI agent uses to discover product and UI evidence, close design-critical context gaps, and maintain a durable DESIGN.md contract.
Advanced
- Item type
- skill
- Key
design-yeachan-heo- Source
- github.com/yeachan-heo/oh-my-codex