Design & UX

Design skill for external, non-YURI, non-Kagami surfaces. Use when building client work, external products, public-facing sites, or any UI that is NOT YURI HUD or Kagami. Enforces high-end intentional design systems, prevents AI slop. For YURI/Kagami surfaces, use design-master instead.

Turn a design system or design reference into a reusable pack and portable skill. Use when extracting visual language from docs, PDFs, or curated design sources into a build/style/audit workflow.

Extract, define, and apply design DNA across three dimensions: design system (tokens), design style (qualitative feel), and visual effects (Canvas, WebGL, 3D, particles, shaders, scroll effects, etc.). Use this skill when: (1) a user wants to see the full 3-dimension design structure/schema, (2) a user provides images, screenshots, or URLs of reference designs and wants them analyzed into a structured JSON profile covering all three dimensions, (3) a user has a Design DNA JSON and content and...

Systematic QA testing for web applications, desktop apps, and workflows. Three tiers: QUICK (critical/high severity only — 5 min), STANDARD (+ medium severity — 15 min), EXHAUSTIVE (+ cosmetic — 30+ min). Tests user flows, finds bugs, reports with severity classification, and optionally auto-fixes with atomic commits. Produces before/after health scores and ship-readiness summary. Use when user says "test this", "QA", "find bugs", "does this work?", or "is it ready to ship?". Voice triggers: ...

Build a motion website implementation plan (and optional starter structure) from motion prompt briefs using accessible 3D/animated UI patterns.

Route technical planning and review between Decisions Mermaid viewer, BuilderIO visual-plan/recap skills, and Open Design when the work needs richer artifacts.

Run before implementing UI — research real product patterns (Refero/Mobbin MCP), pick a design direction, and output tokens or a short DESIGN.md before writing code.

Research and normalize MotionSites-style prompt directions, then output a clean motion prompt brief for implementation.

Use Mermaid diagrams in DecisionsAI to explain technical topics — architecture, flows, sequences, and data models via the freestanding diagram viewer.

Playbook for Aceternity UI, Refero MCP, Mobbin MCP, and Godly when building or polishing web UI — what each source is for and how agents should use it.

Turn ordinary text plans into rich interactive visual plans with diagrams, file maps, annotated code, open questions, and UI/prototype review when useful.

Polished, business-ready design with modern typography, structured layouts, and a trustworthy visual identity.

Stripped-back design emphasizing whitespace, clean typography, and restrained color for maximum clarity and focus.

Dark-themed cloud-platform aesthetic with modular grids, glass-like panels, and strong data hierarchy for productivity dashboards.

Modular grid layout with card-like blocks, clear hierarchy, soft spacing, and subtle visual contrast for organized, scannable interfaces.

Systematic QA testing for web applications, desktop apps, and workflows. Three tiers: QUICK (critical/high severity only — 5 min), STANDARD (+ medium severity — 15 min), EXHAUSTIVE (+ cosmetic — 30+ min). Tests user flows, finds bugs, reports with severity classification, and optionally auto-fixes with atomic commits. Produces before/after health scores and ship-readiness summary. Use when user says "test this", "QA", "find bugs", "does this work?", or "is it ready to ship?". Voice triggers: ...

Run before implementing UI — research real product patterns (Refero/Mobbin MCP), pick a design direction, and output tokens or a short DESIGN.md before writing code.

Playbook for Aceternity UI, Refero MCP, Mobbin MCP, and Godly when building or polishing web UI — what each source is for and how agents should use it.

Create an on-brand social video post: render a short video with HyperFrames (video from HTML) in your Marky brand colors, fonts, and logo, then upload it to Marky, caption it in your voice, and schedule it everywhere you're connected. Use when you want a video post — a promo, explainer, stat animation, countdown sting, or captioned clip — produced and queued from one conversation. Reads auth and endpoints from the marky-api skill. Also triggers on "make a video post", "turn this into a reel",...

Design branded diagram images for social posts — layer diagrams, flows, loops, quote + stat cards, sequence diagrams, numbered steps — as hand-authored HTML rendered to PNG, styled from the business's own brand settings pulled from the Marky API. Use this when a post announces, teaches, or compares something and a designed diagram would beat a stock photo: "make a diagram for this post", "turn these steps into an image", "make an infographic". A companion to plan-social-content and schedule-p...

Create PowerPoint presentations (PPTX) using Python and python-pptx. Handles timelines, charts, diagrams, slide layouts, custom colors, shapes, connectors, text formatting, and slide transitions. Knows WPS compatibility pitfalls. Use when the user asks to: generate a PPT/PPTX file, create a presentation, make a slide deck, draw a timeline, visualize data as slides, or export something to PowerPoint. Also use when the user says "做成 PPT"、"生成幻灯片"、 "做个演示文稿"、"做个 pptx".

The Autonomous Construction and Synthesis Engine. Standardizing the process of turning abstract intent into concrete digital and physical structures.

Analyzes design image files or Figma links (when Figma MCP is available) and generates a structured design context document. Handles three output formats: (1) User Flow Document — sequential multi-screen journeys with screen-by-screen breakdowns, state transitions, and error handling; (2) Design Description — screen/component documentation covering visual design, layout, and interaction behavior; (3) Context Summary — structured six-context analysis (Business/Product/UX) used as input for req...

Designs location-based augmented reality experiences with geospatial anchoring, GPS integration, and real-world interactive overlays.