Agentic UX Design Relationship Centric Interfaces

bencium/bencium-claude-code-design-skill

This one's about designing interfaces that remember and adapt across sessions instead of treating every interaction like it's the first time. The core idea is that systems should build understanding over time, learning preferences and context to create ongoing relationships rather than just responding to isolated requests. You'd reach for this when building AI products where continuity matters, like assistants that need to recall past conversations or apps that should evolve with user behavior. It's more of a design philosophy than a technical framework, so expect conceptual guidance on memory-aware patterns rather than ready-made components. The relationship-centric framing makes sense for agentic systems, though you'll need to figure out the implementation details yourself.

GitHub stars: 267
last updated: Jun 3, 2026

View on GitHub

Install

$ npx -y skills add bencium/bencium-claude-code-design-skill --skill 'Agentic UX Design - Relationship-Centric Interfaces' --agent claude-code

Installs into .claude/skills of the current project.

Files

Agentic UX Design - Relationship-Centric Interfaces

Overview

The paradigm shift from screen-centric to relationship-centric design.

Traditional UX optimizes individual screens and isolated interactions. Agentic UX designs for ongoing relationships where systems learn, remember, and evolve alongside users across sessions, devices, and contexts.

Core principle: Every interaction builds on learned preferences and user history. Systems don't just respond—they develop understanding that compounds over time.

Announce at start: "I'm using the Relationship Design skill to create an agentic, memory-aware interface that builds long-term relationships with users."