skills.rest
PastaSus
PastaSusCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

bmad-ux

Elicit UX decisions and produce DESIGN.md and EXPERIENCE.md specification documents.

1|Updated Sep 18, 2026
Search Tags:#accessibility#specification#design system#design tokens#ux design#information architecture#wireframes
One-click install
npx skills add https://github.com/PastaSus/egg-defender --skill bmad-ux-pastasus
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: bmad-ux
Source: https://github.com/PastaSus/egg-defender/tree/main/.agents/skills/bmad-ux
Command: npx skills add https://github.com/PastaSus/egg-defender --skill bmad-ux-pastasus

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Turning a vague product vision into concrete, developer-ready UX specifications is slow and inconsistent. This Skill facilitates a structured discovery conversation and distills the results into two canonical documents: DESIGN.md (visual identity per the Google Labs spec) and EXPERIENCE.md (information architecture, behavior, states, and flows). ## Core Features & Use Cases - Facilitated UX Discovery: Elicits the user's vision through probing questions, named-protagonist journeys, and concern scans, logging every decision to a memlog without imposing design opinions. - Dual Specification Output: Produces DESIGN.md (colors, typography, spacing, components as YAML tokens plus prose) and EXPERIENCE.md (IA, state patterns, interaction primitives, accessibility floor, key flows) with cross-referenced tokens. - Creative Rendering Tools: Generates HTML color themes, design directions, Excalidraw wireframes, and key-screen mockups so users can pick visuals instead of describing them. - Validation & Reviewer Gate: Runs rubric-based and lens-selectable parallel reviewer passes that produce consolidated HTML/Markdown validation reports. - Use Case: A founder says "lets create UX design" for a journaling app; the Skill interviews them, renders theme options, and delivers final DESIGN.md and EXPERIENCE.md files ready for architecture and story breakdown. ## Quick Start Ask the assistant to create UX 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 a UX design specification with this skill?▼

Say "lets create UX design" or "help me plan the UX" to activate it. The skill runs a discovery conversation about your product, renders visual options like color themes and wireframes, then distills decisions into DESIGN.md and EXPERIENCE.md files.

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

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

Does it work with design systems like shadcn or Material UI?▼

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

Can it validate an existing UX specification?▼

Yes, the Validate intent critiques an existing DESIGN.md and EXPERIENCE.md pair using a rubric walker covering flow, token, component, and state coverage, plus optional reviewer lenses. It writes consolidated HTML and Markdown validation reports without modifying the spines.

Can I resume an unfinished UX design session?▼

Yes. On Create intent it scans the output path for prior in-progress run folders whose DESIGN.md status is not final and offers to resume. All decisions persist in a .memlog.md file that a resumed run reloads.

Does it support headless or automated runs?▼

Yes. When invoked headless it skips greetings and questions, infers intent from provided inputs, and ends with a structured JSON payload describing status, produced artifacts, assumptions, and open questions.

Related Skills

Explore More Design & Creative Skills→
samura-devsamura-dev

product-manager

Structure product ideas into PRDs, architecture documents, and roadmaps.

Community
Advanced
bmad-code-orgbmad-code-org
212

gds-ux

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

Official
Advanced
AradotsoAradotso
3

figma-to-ai-prompter

Convert Figma design structures into token-optimized prompts for AI prototyping tools.

Official
Advanced
phoenicisfphoenicisf

figma-generate-design

Build or update full-page Figma screens using published design system components and tokens.

Community
Advanced