ux-artifacts

Generate evidence-labelled UX artifacts for needs, journeys, structure, inclusion, and engineering handoff.

1.4k|284|Updated Nov 2, 2025
One-click install
npx skills add https://github.com/microsoft/hve-core --skill ux-artifacts
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ux-artifacts
Source: https://github.com/microsoft/hve-core/tree/main/.github/skills/design-thinking/ux-artifacts
Command: npx skills add https://github.com/microsoft/hve-core --skill ux-artifacts

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

UX practitioners often lose evidence provenance when turning research into durable documents, producing artifacts that blur observed facts, reported claims, and assumptions. This Skill produces one current, evidence-labelled Markdown asset per mode so engineers, designers, and agents can consume UX decisions without inventing research or losing uncertainty.

Core Features & Use Cases

  • Five bounded modes: frame-needs, map-journey, sketch-structure, decide-inclusion, and prepare-handoff, each producing a single canonical Markdown asset under .copilot-tracking/ux-artifacts/.
  • Evidence contract: every output separates Observed, Reported, Assumed, and Unresolved sections and ends with a mandatory human-review gate that only a person can check.
  • Destination mapping: optional Figma, FigJam, or Mural intent generation that shapes content for those tools without authenticating or writing externally.
  • Use Case: A designer with completed user interviews invokes map-journey mode with the interview notes as source, receiving a staged journey asset where every pain point carries its evidence class and unresolved gaps stay explicit.

Quick Start

Ask the agent to use the ux-artifacts skill with mode map-journey, a project slug, a subject, and your research notes as the source to produce an evidence-labelled journey map.

Frequently Asked Questions about ux-artifacts

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

FAQPage Schema
How do I create a user journey map from existing research notes?

Invoke the skill with mode map-journey, a project slug, a subject, and your notes as the source input. It produces a staged journey Markdown file where every action, thought, and pain point carries an Observed, Reported, or Assumed basis with its source.

What UX artifacts can this skill generate?

It supports five modes: frame-needs for user needs, map-journey for staged journeys, sketch-structure for surface composition and states, decide-inclusion for exclusion risks, and prepare-handoff for engineering-facing flow and acceptance inputs.

Can I export UX artifacts to Figma or Mural?

Yes, by supplying a destination of figma or mural plus the required destination-kind, destination-target, and destination-change inputs. The skill returns destination intent and content mapping only; it never authenticates or writes to external tools.

Does the skill conduct user research or interviews?

No. It only transforms supplied evidence into artifacts and never conducts coaching, interviews, or observation. Unsupported claims are labelled Assumed or left Unresolved, and every output ends with a human-review checkbox only a person can mark.

Where are the generated UX artifact files stored?

Each mode writes one current Markdown file to .copilot-tracking/ux-artifacts/{project-slug}/{subject-slug}/{mode}.md. Rerunning a mode updates that file in place rather than creating dated duplicates.

When should I use ux-coaching instead of ux-artifacts?

Use ux-coaching when you need help framing the problem or deciding what to research. Use ux-artifacts when evidence already exists and you need a durable, evidence-labelled document rather than a coached conversation.