In this article
Engineer Guide
This guide is for you if you write code, implement features, fix bugs, review pull requests, or maintain production systems. Engineers get the deepest tooling in HVE Core, with 28+ addressable assets spanning research, planning, implementation, review, and delivery.
Recommended Installation
TIP
Install the HVE Core extension from the VS Code Marketplace for the complete active component set with zero configuration.
For clone-based setup, use the included hve-core-installer skill to choose the starter profile or a custom selection that includes RPI and language-specific coding components. See the Installation Guide.
- Researches codebase patterns, external APIs, and architecture before you write code
- Creates structured implementation plans with step-by-step task breakdowns
- Implements features following plans with phase-based execution and progress tracking
- Reviews code changes against standards, patterns, and architectural guidelines
- Generates conventional commit messages and pull request descriptions
- Activates language-specific coding standards automatically based on file type (C#, Python, Bash, Bicep, Terraform, GitHub Actions)
- Manages Git workflows including merge, rebase, and conflict resolution
Your Lifecycle Stages
NOTE
Engineers primarily operate in these lifecycle stages:
Stage 2: Discovery: Research requirements, investigate codebase, gather context Stage 3: Product Definition: Transform research into structured implementation plans Stage 6: Implementation: Build features, write code, execute plans Stage 7: Review: Review code, validate changes, ensure quality Stage 8: Delivery: Commit, create PRs, merge changes
Stage Walkthrough
- Stage 2: Discovery. Use
/rpi-researchto investigate requirements, explore codebase patterns, and gather evidence for your approach. - Stage 3: Product Definition. Use
/rpi-planto transform adequate evidence into a structured implementation plan with phases, tasks, and success criteria. - Stage 6: Implementation. Execute the approved plan with
/rpi-implement, or useRPI Agentor/rpiwhen you want full lifecycle coordination. - Stage 7: Review. Run
/rpi-reviewto validate implementation against the plan, check coding standards, and ensure architectural compliance. - Stage 8: Delivery. Use
/git-commitfor conventional commit messages,/pull-requestfor PR creation, and/git-mergefor merge workflows.
Starter Prompts
/rpi Implement the user notification preferences API endpoint from work
item #4523. Follow the REST conventions in src/api/handlers/ and add
integration tests covering email, SMS, and push notification channels.
Use /rpi-research:
Research the best approach for implementing a rate limiter in the API
gateway. Compare token bucket vs sliding window algorithms, evaluate
Redis vs in-memory storage for distributed deployments, and review
existing patterns in src/middleware/.
Use /rpi-plan and reference the research artifact:
Create an implementation plan for the webhook delivery system. Include
phases for the event dispatcher, retry queue, and dead-letter handling.
Reference patterns in src/services/.
Use /rpi-implement and reference the approved plan artifacts:
Implement the webhook delivery system following the attached plan. Start
with the event dispatcher phase and execute the retry queue phase
second.
Use /rpi-review and reference the changes record:
Review my webhook delivery system implementation. Check for error
handling gaps, verify retry logic correctness, and validate compliance
with coding standards.
/git-commit Commit changes with a conventional message
/pull-request Create a PR for the current changes
Key Agents and Workflows
| Agent or skill | Purpose | Docs |
|---|---|---|
| rpi-research | Deep codebase and API research | RPI Overview |
| rpi-plan | Structured implementation planning | RPI Overview |
| rpi-implement | Evidence-led implementation of approved plans | RPI Overview |
| rpi-review | Implementation review and outcome routing | RPI Overview |
| RPI Agent | Full RPI lifecycle coordination | RPI Overview |
| code-review | Pull request review automation | Agent file |
| hve-builder | Create and refine prompt engineering artifacts | Skill file |
Auto-activated instructions apply coding standards based on file type: C# (*.cs), Python (*.py), Bash (*.sh), Bicep (bicep/**), Terraform (*.tf), and GitHub Actions workflows (*.yml).
Tips
| Do | Don't |
|---|---|
| Research before implementing multi-file changes | Jump straight to coding complex features |
Use /rpi for planned, multi-step work | Manually coordinate research, planning, and implementation |
| Let coding standards auto-activate by file type | Override or skip language-specific instructions |
| Review the research doc before starting the planning phase | Skip research for unfamiliar codebases or APIs |
Clear context between RPI phases with /clear | Carry stale context across research, plan, implement, and review |
Related Roles
- Engineer + Tech Lead: Feature development benefits from architecture review and standards enforcement. The Tech Lead validates design decisions while the Engineer implements. See the Tech Lead Guide.
- Engineer + Data Scientist: Analytics pipeline development pairs data specification and notebook prototyping with production-grade integration. See the Data Scientist Guide.
- New Contributor to Engineer: Contributors progress from guided mode through autonomous engineering. See the New Contributor Guide.
Next Steps
TIP
Run your first RPI workflow: First Workflow Guide Explore the full RPI methodology: RPI Documentation See how your stages connect: AI-Assisted Project Lifecycle
🤖 Crafted with precision by ✨Copilot following brilliant human instruction, then carefully refined by our team of discerning human reviewers.