# Hve Artifact Authoring

Create and validate HVE Core agents, prompts, instructions, and skills with current...

- Repository: https://github.com/microsoft/hve-core (1591 stars)
- Category: AI and agents
- License: MIT
- Last updated: 2026-11-01
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add microsoft/hve-core --skill hve-artifact-authoring -g -a claude-code -y`
Codex: `npx skills add microsoft/hve-core --skill hve-artifact-authoring -g -a codex -y`
Cursor: `npx skills add microsoft/hve-core --skill hve-artifact-authoring -g -a cursor -y`
Gemini CLI: `npx skills add microsoft/hve-core --skill hve-artifact-authoring -g -a gemini-cli -y`

## Description

Create and validate HVE Core agents, prompts, instructions, and skills with current frontmatter, package membership, delegation, tracking, documentation, and validation conventions. Use when authoring a GitHub Copilot customization artifact in this repository.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# HVE Artifact Authoring

## Goal

Create agents, prompts, instructions, and skills that follow HVE Core's current authoring,
distribution, documentation, and validation contracts. Use the `hve-builder` skill when the work
requires lifecycle-managed authoring, a review pass, or host validation.

## Artifact Selection

Choose each artifact from its responsibility and activation model.

| Artifact                         | Responsibility                                                | Activation                         |
|----------------------------------|---------------------------------------------------------------|------------------------------------|
| Prompt (`.prompt.md`)            | Parameterized user entry point                                | Slash invocation                   |
| Agent (`.agent.md`)              | User-selected workflow or isolated subagent work              | Agent picker or parent dispatch    |
| Instruction (`.instructions.md`) | Conventions applied to matching paths                         | `applyTo` glob                     |
| Skill (`SKILL.md`)               | Reusable workflow, domain knowledge, references, or utilities | Semantic match or slash invocation |

Keep reusable behavior in a skill. Add a thin prompt or agent only when it provides a distinct
entry point. Delegate isolated work only when the dispatch cost is justified.

## Flow

The rest: https://github.com/microsoft/hve-core/blob/HEAD/.github/skills/coding-standards/hve-artifact-authoring/SKILL.md