skills.rest
HordRicJr
HordRicJrCOMMUNITY
Explore all skills by this author →
GitHub

bmad-ux

Plan UX patterns and produce DESIGN.md and EXPERIENCE.md design specification documents.

6|Updated Aug 29, 2026
Search Tags:#accessibility#validation#design system#design tokens#ux design#information architecture#wireframes
One-click install
npx skills add https://github.com/HordRicJr/Akomagni --skill bmad-ux-hordricjr
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: bmad-ux
Source: https://github.com/HordRicJr/Akomagni/tree/main/bmad-core/.agents/skills/bmad-ux
Command: npx skills add https://github.com/HordRicJr/Akomagni --skill bmad-ux-hordricjr

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) and assets (resource) components.

What problem does it solve? Turning a product idea into consistent, buildable UX specifications is hard: visual identity, information architecture, states, and accessibility decisions get scattered across conversations and mocks. This Skill facilitates a structured UX discovery process and distills the results into two canonical contract documents — DESIGN.md (visual identity) and EXPERIENCE.md (behavior, IA, flows) — that downstream architecture and development work can consume directly. ## Core Features & Use Cases - Dual specification spines: Generates DESIGN.md following the Google Labs design.md spec (color, typography, spacing, component tokens) and EXPERIENCE.md covering information architecture, state patterns, interaction primitives, accessibility floor, and named-protagonist key flows. - Three operating modes: Create (full discovery to finalized spines), Update (apply changes against prior decisions logged in a memlog), and Validate (multi-lens reviewer gate producing HTML and Markdown validation reports). - Creative tooling and handoffs: Renders HTML color themes, design directions, Excalidraw wireframes, and key-screen mockups on demand, with optional handoff to external producers like Google Stitch, plus headless mode with JSON output schemas for automation. - Use Case: A founder says "help me plan the UX" for a journaling app; the Skill elicits decisions through discovery, renders candidate color themes and wireframes, then finalizes DESIGN.md and EXPERIENCE.md ready for the architecture and story-planning skills. ## Quick Start Ask the AI to create UX design specifications for your product idea and answer its discovery questions about brand, platforms, and key user journeys.

Frequently Asked Questions about bmad-ux

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create UX design specifications with AI?▼

Invoke the skill with a request like "lets create UX design" and it runs a discovery process covering brand, platforms, accessibility, and user journeys. It then distills decisions into DESIGN.md for visual identity and EXPERIENCE.md for behavior and flows.

What is the difference between DESIGN.md and EXPERIENCE.md?▼

DESIGN.md owns how the product looks: color, typography, spacing, shape, and component tokens per the Google Labs design.md spec. EXPERIENCE.md owns how it works: information architecture, state patterns, interaction primitives, accessibility behavior, and key flows, cross-referencing DESIGN.md tokens by name.

Can I update an existing UX specification instead of starting over?▼

Yes. Update mode reads the existing spines plus the memlog of prior decisions, applies your change signal, and surfaces any conflicts with earlier decisions. It also detects prior in-progress runs and offers to resume them.

Does the UX validation produce a report?▼

Yes. Validate mode dispatches reviewer lenses as parallel subagents, then synthesizes findings into validation-report.html and a Markdown twin. Findings are grouped by severity across eight rubric categories like flow coverage and token completeness.

Can it work with design systems like shadcn or MUI?▼

Yes. When a UI system is named in the Foundation section, both spines inherit from it. DESIGN.md specifies only brand-layer token deltas and EXPERIENCE.md specifies only behavioral deltas, rather than restating the system's defaults.

Does it support headless or automated runs?▼

Yes. Headless mode skips greetings and questions, infers intent from provided inputs, and ends with a JSON payload matching defined schemas for create, update, validate, or blocked outcomes. Creative tools are off by default in headless runs.

Related Skills

Explore More Design & Creative Skills→
co-cddoco-cddo
4

bmad-create-prd

Draft a structured PRD with Success Criteria and User Journeys from discovery materials.

Official
Advanced
bmad-code-orgbmad-code-org
212

gds-ux

Generate DESIGN.md and EXPERIENCE.md UX spines for game development projects.

Official
Advanced
vzakharovvzakharov

polish

Runs deduplication and prose-tending passes over a branch's diff and commits the results.

Community
Advanced
Generous-CorpGenerous-Corp
13

import-design

Import external design files into the Pulp framework with automated layout parity validation.

Official
Advanced