Skip to content

Latest commit

 

History

History
164 lines (119 loc) · 12.4 KB

File metadata and controls

164 lines (119 loc) · 12.4 KB
title GitHub Copilot Prompts
description Coaching and guidance prompts for specific development tasks that provide step-by-step assistance and context-aware support
author Edge AI Team
ms.date 2026-08-01
ms.topic hub-page
estimated_reading_time 3
keywords
github copilot
prompts
ai assistance
coaching
guidance
development workflows

GitHub Copilot Prompts

This directory contains coaching and guidance prompts designed to provide step-by-step assistance for specific development tasks. Unlike instructions that focus on systematic implementation, prompts offer educational guidance and context-aware coaching to help you learn and apply best practices. Prompts are organized by workflow focus area: planning and RPI, source control, pull requests and review, prompt engineering, Design Thinking, Responsible AI, security, accessibility, data science, and experimental tools.

Backlog and work item workflows are not prompts. They are user-invocable skills that discover the active tracker at runtime and work the same way against Azure DevOps, GitHub, and Jira. See Backlog & Work Item Management.

How to Use Prompts

Prompts can be invoked in GitHub Copilot Chat using /prompt-name syntax (for example, /rpi or /git-commit). They provide:

  • Educational Guidance: Step-by-step coaching approach
  • Context-Aware Assistance: Project-specific guidance and examples
  • Best Practices: Established patterns and conventions
  • Interactive Support: Conversational assistance for complex tasks

Available Prompts

Onboarding, Research & Planning

  • RPI - Coordinates one task through Research, Plan, Implement, Review, and Follow-up with the RPI Agent and matching rpi-* skills

Use /rpi-research, /rpi-plan, /rpi-implement, or /rpi-review when you need one bounded RPI phase. Resume longer work from the durable artifacts owned by that workflow rather than from a generic conversation checkpoint.

Source Control & Commit Quality

Pull Requests & Code Review

  • Pull Request - Generate pull request descriptions from branch diffs
  • PR Review - Review a pull request or local change set via the consolidated Code Review agent

Prompt Engineering & Evaluation

  • Vally Test Write - Author Vally conformance test stimuli for an existing prompt, instructions, agent, or skill
  • Evals Import - Import a CSV or XLSX corpus into Vally eval suites with safety lint and dedupe

Use the hve-builder skill to create, improve, refactor, review, or validate prompt-engineering artifacts. The retained prompt-builder, prompt-analyze, and prompt-refactor skills are compatibility aliases that route legacy requests to hve-builder; they are not prompt files or independent lifecycle owners. Vally conformance authoring remains owned by Vally Test Author and the vally-tests skill.

Backlog & Work Item Management

These workflows are skills rather than prompts. Each resolves the active tracker at runtime, so the same command serves Azure DevOps, GitHub, and Jira instead of requiring a per-platform variant.

  • Backlog Plan - Read-only discovery, assigned work, task planning, triage assessment, sprint planning, and session resume
  • Backlog Execute - Create and update tracker items, either one at a time or from a reviewed handoff file
  • Functional Planner - Turn PRD and BRD artifacts into a planned item hierarchy before anything is written to a tracker
  • Backlog Manager - Orchestrate the above across a longer multi-step backlog session

Platform Setup & Delivery Context

  • Jira Skill - Configure local Jira access and use the CLI directly
  • GitLab Skill - Inspect merge requests, comments, pipelines, jobs, and logs for GitLab-hosted delivery workflows

Azure DevOps Pull Requests & Builds

Design Thinking

Note: The per-method coaching prompts (dt-method-04-*, dt-method-05-*, dt-method-06-*) are driven by the DT Coach agent mid-session and are not typically invoked directly.

Responsible AI

  • RAI Capture - Start RAI assessment planning from existing knowledge (capture mode)
  • RAI Plan from PRD - Start RAI assessment planning from PRD/BRD artifacts (from-prd mode)
  • RAI Plan from Security Plan - Start RAI assessment planning from a completed Security Plan (recommended)

Security

  • Security Capture - Start security planning from existing notes (capture mode)
  • Security Plan from PRD - Start security planning from PRD/BRD artifacts (from-prd mode)
  • Security Review - OWASP vulnerability assessment against the current codebase with configurable mode, scope, and skill selection
  • Security Review - Web - OWASP Top 10 web vulnerability assessment without codebase profiling
  • Security Review - LLM - OWASP LLM and Agentic vulnerability assessments with codebase profiling
  • Security Review - Secure by Design - Secure by Design principles assessment per UK and Australian government guidance
  • SSSC Capture - Start supply chain security planning from existing knowledge (capture mode)
  • SSSC from BRD - Start supply chain security planning from BRD artifacts
  • SSSC from PRD - Start supply chain security planning from PRD artifacts
  • SSSC from Security Plan - Extend a Security Planner assessment with supply chain coverage
  • VEX Scan - Full VEX pipeline: scan dependencies, enrich CVEs, analyze exploitability, and draft an OpenVEX document
  • VEX Triage - Triage CVEs from an existing scan report or SBOM and draft an OpenVEX document
  • VEX Implement - Plan the work to stand up VEX in a target project as a backlog for rpi-implement
  • Incident Response - Incident response workflow for Azure operations with triage, diagnostics, mitigation, and RCA phases
  • Risk Register - Generate a qualitative risk assessment with a P×I matrix and mitigation plans

Accessibility

Data Science

Experimental & Tools

  • PowerPoint - Create, update, or manage PowerPoint slide decks
  • cspell Config - Create or update the project cspell configuration with project words and ignores
  • Graph Research - Research a codebase using an existing graphify knowledge graph with audit-tagged evidence

Prompts vs Instructions vs Custom Agents

  • Prompts (this directory): Coaching and educational guidance for learning
  • Instructions: Systematic implementation and automation
  • Agents: Specialized AI assistance with enhanced capabilities

Quick Start

  1. Coordinating a complete task? Use RPI with /rpi task="<outcome>"
  2. Working on one RPI phase? Use /rpi-research, /rpi-plan, /rpi-implement, or /rpi-review
  3. Authoring an HVE artifact? Use hve-builder; use the Vally prompts above only for conformance-test authoring or corpus import
  4. Committing changes? Use Git Commit Message Generator or Git Commit
  5. Handling merge conflicts? Use Git Merge
  6. Setting up Git? Use Git Setup
  7. Tracking your work? Use the Backlog Plan skill in my-work mode, then task-plan mode
  8. Creating Azure DevOps PRs? Use ADO Create Pull Request
  9. Checking build status? Use ADO Get Build Info
  10. Creating or updating tracker items? Use the Backlog Execute skill
  11. Working on PRs? Use Pull Request
  12. Responding to Azure incidents? Use Incident Response
  13. Discovering or triaging a backlog? Use the Backlog Plan skill in discover or triage mode
  14. Need GitLab delivery context? Review the GitLab Skill for setup and command guidance
  15. Running a security review? Use Security Review for full OWASP assessment

Related Resources

  • Contributing Guide - Complete guide to contributing to the project
  • Instructions - Comprehensive guidance files for development standards
  • Agents - Specialized AI assistance with enhanced capabilities

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