microsoft/hve-core

What it solves

HVE Core addresses the challenge of making AI-assisted software development repeatable, standards-aligned, and scalable across teams. It prevents the inconsistent results often associated with raw LLM prompts by providing a structured system of validated artifacts for the software development lifecycle (SDLC).

How it works

It functions as a prompt library and workflow system for GitHub Copilot. It provides four primary building blocks:

• Agents: Specialized AI personas for specific tasks like research, planning, implementation, and review.
• Prompts: Standardized entry points for repeatable workflows.
• Instructions: Rules that automatically apply coding standards to AI output.
• 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 convention-driven, agentic SDLC framework to ship code faster while maintaining high standards.

Highlights

• RPI Workflow: A dedicated methodology focusing on Research, Plan, Implement, and Review.
• VS Code Integration: Available as a VS Code extension for seamless integration into the editor.
• CLI Support: Compatible with the GitHub Copilot CLI via marketplace plugins.
• Validated Artifacts: Includes a CI/CD validation pipeline and quality gates to ensure the reliability of prompts and instructions.