Skip to main content

HVE Core Documentation

HVE Core is a prompt engineering framework for GitHub Copilot designed for team-scale adoption. It provides specialized agents, reusable prompts, instruction sets, and a validation pipeline with JSON schema enforcement. The framework separates AI concerns into distinct artifact types with clear boundaries, preventing runaway behavior through constraint-based design.

Audience

RoleDescriptionStart Here
EngineerWrite code, implement features, fix bugsEngineer Guide
TPMPlan projects, manage requirements, track workTPM Guide
Tech Lead / ArchitectDesign architecture, review code, set standardsTech Lead Guide
Security ArchitectAssess security, create threat modelsSecurity Architect Guide
Data ScientistAnalyze data, build notebooks, create dashboardsData Scientist Guide
SRE / OperationsManage infrastructure, handle incidents, deploySRE Guide
Business Program ManagerDefine business outcomes, manage stakeholdersBPM Guide
New ContributorGet started contributing to the projectNew Contributor Guide
UX DesignerDesign Thinking coaching, user research, prototyping workflowsUX Designer Guide
All RolesCross-cutting utility toolsUtility Guide

Browse All Role Guides →

AI-Assisted Project Lifecycle

HVE Core supports a 9-stage project lifecycle from initial setup through ongoing operations, with AI-assisted tooling at each stage. The project lifecycle guides walk through each stage, covering available tools, role-specific guidance, and starter prompts.

AI-Assisted Project Lifecycle Overview →

Role Guides

Find your role-specific guide for AI-assisted engineering. Each guide maps the agents, prompts, and collections relevant to your responsibilities.

  • Engineer - RPI workflow, coding standards, implementation
  • TPM - Requirements, backlog management, sprint planning
  • New Contributor - Guided onboarding with progression milestones

Browse All Role Guides →

Getting Started

The Getting Started guide walks through installation, configuration, and running your first Copilot workflow.

Getting Started Guide →

Agent Systems

hve-core provides specialized agents organized into functional groups. Each group combines agents, prompts, and instruction files into cohesive workflows for specific engineering tasks.

  • RPI Orchestration separates complex tasks into research, planning, implementation, and review phases
  • GitHub Backlog Manager automates issue discovery, triage, sprint planning, and execution across GitHub repositories
  • Additional systems documented in the Agent Catalog

Browse the Agent Catalog →

Design Thinking

AI-assisted Design Thinking uses the dt-coach agent to guide teams through nine methods across three spaces.

RPI Methodology

Research, Plan, Implement (RPI) is a structured methodology for complex AI-assisted engineering tasks. It separates concerns into three specialized agents that work together.

RPI Documentation →

Prompt Engineering

HVE Core provides a structured approach to building AI artifacts with protocol patterns, input variables, and maturity lifecycle management.

Key Differentiators

CapabilityDescription
Constraint-based designAgents know their boundaries, preventing runaway behavior
Subagent delegationFirst-class pattern for decomposing complex tasks
Maturity lifecycleFour-stage model from experimental to deprecated
Schema validationJSON schema enforcement for all artifact types

Customization

Adapt HVE Core to your team's workflow with these guides, from lightweight instruction files to full fork-and-extend workflows.

  • Customization Overview - Spectrum of customization options and role-based entry points
  • Instructions - Repository-level and file-pattern-scoped coding guidance
  • Agents - Custom agent architecture, subagent patterns, and tool restrictions
  • Prompts - Task-specific prompt files with variables and agent delegation
  • Skills - Self-contained skill packages with scripts and references
  • Collections - Bundle and distribute sets of agents, prompts, instructions, and skills
  • Build System - Plugin generation, schema validation, and CI pipeline integration
  • Forking - Fork setup, customization areas, and upstream synchronization
  • Environment - DevContainer, VS Code settings, and MCP server configuration
  • Team Adoption - Governance, naming conventions, onboarding, and change management

Customization Guide →

Contributing

Learn how to create and maintain AI artifacts including agents, prompts, instructions, and skills.

  • Instructions - Passive reference guidance
  • Prompts - Task-specific procedures
  • Agents - Custom personas and modes
  • Skills - Executable utilities with documentation

Contributing Guide →

Architecture

Technical documentation for system design, component relationships, and build pipelines.

Architecture Overview →

Templates

Pre-built templates for common engineering documents:

Browse Templates →

ResourceDescription
Customization GuideAdapt HVE Core to your workflow
CHANGELOGRelease history and version notes
CONTRIBUTINGRepository contribution guidelines
Scripts READMEAutomation script reference
Extension READMEVS Code extension documentation

🤖 Crafted with precision by ✨Copilot following brilliant human instruction, then carefully refined by our team of discerning human reviewers.