microsoft/hve-core

A refined collection of Hypervelocity Engineering components (instructions, prompts, agents, and skills) to start your project off right, or upgrade your existing projects to get the most out of GitHub Copilot

What it solves

HVE Core addresses the lack of repeatability and scalability in AI-assisted software development. It provides a structured system to ensure that work performed by AI agents is standards-aligned, repeatable, and scalable across teams by moving away from ad-hoc prompting toward a convention-driven workflow.

How it works

It functions as a prompt library and agentic SDLC framework for GitHub Copilot. It integrates into VS Code or the GitHub Copilot CLI via an extension, providing users with a set of building blocks:

  • Agents: Specialized AI personas for research, planning, implementation, and review.
  • Prompts: Standardized entry points for repeatable workflows.
  • Instructions: Automated coding standards that the AI follows.
  • Skills: Reusable tool capabilities that extend the AI's functionality.

Who it’s for

Software engineering teams and individuals who use GitHub Copilot and want to implement a standardized, agentic software development lifecycle (SDLC) to ship faster while maintaining high quality.

Highlights

  • RPI Methodology: A deep-dive workflow focused on Research, Plan, Implement, and Review.
  • Integrated Ecosystem: Works directly within VS Code and the GitHub Copilot CLI.
  • Customizable: Supports forking and extending the core library to build independent, team-specific implementations.
  • Validated Artifacts: Includes a CI/CD validation pipeline to ensure the quality of AI prompts and instructions.

Related

  • Project
    HoangNguyen0403/agent-skills-standard

    A portable SDLC standards layer for AI coding agents that turns engineering rules into modular, version-controlled skills to ensure consistent code quality while reducing token waste.

  • Project
    github/copilot-cli

    A terminal-based AI coding agent that allows developers to build, debug, and refactor code using natural language and GitHub integration.

  • Project
    jabrena/plinth

    An AI-native SDLC workflow for Java Enterprise applications that provides reusable skills, agents, and commands to standardize analysis, design, and implementation.

  • Project
    microsoft/AI-Engineering-Coach

    A VS Code extension and GitHub Copilot app canvas that analyzes local AI session logs to help developers detect anti-patterns and improve their agentic engineering skills.

  • Project
    MengTo/Skills

    A curated library of procedural agent skills and prompt playbooks designed to help AI coding agents build high-quality UIs, games, and frontend systems consistently.