microsoft/hve-core

Public

mirrored fromhttps://github.com/microsoft/hve-coreAvailable

CodeCommitsIssuesPull requestsActionsInsightsSecurity
hve-core-v3.3.1

Branches

Tags

  • No tags available.
0Branches0Tags
Go to file
Add file
Code

Clone

HTTPS

Download ZIP

docs/hve-guide/lifecycle/implementation.md

163lines · modecode

1---
2title: "Stage 6: Implementation"
3description: Build features, write code, and create content with the full suite of AI-assisted development tools
4sidebar_position: 7
5author: Microsoft
6ms.date: 2026-02-18
7ms.topic: how-to
8keywords:
9 - ai-assisted project lifecycle
10 - implementation
11 - coding
12 - RPI
13 - development
14estimated_reading_time: 8
15---
16
17## Overview
18
19Implementation is the highest-density stage in the project lifecycle, with 30 assets spanning agents, prompts, instructions, and skills. This stage covers coding, content creation, prompt engineering, data analysis, and infrastructure work. The RPI (Research, Plan, Implement) methodology provides structured execution guidance for complex tasks.
20
21## When You Enter This Stage
22
23You enter Implementation after completing [Stage 5: Sprint Planning](sprint-planning.md) with assigned work items. You also re-enter this stage from [Stage 7: Review](review.md) when rework is needed, from [Stage 8: Delivery](delivery.md) at the start of each new sprint, or from [Stage 9: Operations](operations.md) for hotfixes.
24
25> [!NOTE]
26> Prerequisites: Sprint planned with assigned work items. Development environment configured from [Stage 1: Setup](setup.md).
27
28## Available Tools
29
30### Primary Agents
31
32| Tool | Type | How to Invoke | Purpose |
33|-------------------------|-------|------------------------------------------|-------------------------------------------------------|
34| rpi-agent | Agent | Select **rpi-agent** agent | Orchestrate the full research-plan-implement workflow |
35| task-researcher | Agent | Select **task-researcher** agent | Research requirements and gather codebase evidence |
36| task-planner | Agent | Select **task-planner** agent | Create implementation plans from research findings |
37| task-implementor | Agent | Select **task-implementor** agent | Build components following plans |
38| task-reviewer | Agent | Select **task-reviewer** agent | Validate implementation against plan and research |
39| gen-jupyter-notebook | Agent | Select **gen-jupyter-notebook** agent | Create data analysis notebooks |
40| gen-streamlit-dashboard | Agent | Select **gen-streamlit-dashboard** agent | Generate Streamlit dashboards |
41| prompt-builder | Agent | Select **prompt-builder** agent | Create and refine prompt engineering artifacts |
42
43### Supporting Agents
44
45| Tool | Type | How to Invoke | Purpose |
46|---------------------|-------|--------------------------------------|------------------------------------------|
47| phase-implementor | Agent | Select **phase-implementor** agent | Execute individual implementation phases |
48| prompt-updater | Agent | Select **prompt-updater** agent | Update existing prompts and instructions |
49| researcher-subagent | Agent | Select **researcher-subagent** agent | Conduct focused research within tasks |
50
51### Prompts
52
53| Tool | Type | How to Invoke | Purpose |
54|--------------------|--------|-----------------------|----------------------------------------------|
55| rpi | Prompt | `/rpi` | Start the full RPI workflow |
56| task-research | Prompt | `/task-research` | Research requirements for a task |
57| task-plan | Prompt | `/task-plan` | Create an implementation plan from research |
58| task-implement | Prompt | `/task-implement` | Begin implementation of a specific task |
59| task-review | Prompt | `/task-review` | Review implementation against the plan |
60| prompt-build | Prompt | `/prompt-build` | Create a new prompt engineering artifact |
61| prompt-analyze | Prompt | `/prompt-analyze` | Analyze prompt quality and effectiveness |
62| prompt-refactor | Prompt | `/prompt-refactor` | Refactor and improve existing prompts |
63| git-commit | Prompt | `/git-commit` | Stage and commit changes |
64| git-commit-message | Prompt | `/git-commit-message` | Generate a commit message for staged changes |
65
66### Auto-Activated Instructions
67
68All coding standard instructions activate automatically based on file type:
69
70| Instruction | Activates On | Purpose |
71|-------------------|---------------------------|----------------------------------------|
72| csharp | `**/*.cs` | C# coding standards |
73| python-script | `**/*.py` | Python scripting standards |
74| bash | `**/*.sh` | Bash script standards |
75| bicep | `**/bicep/**` | Bicep infrastructure standards |
76| terraform | `**/*.tf` | Terraform infrastructure standards |
77| workflows | `.github/workflows/*.yml` | GitHub Actions workflow standards |
78| markdown | `**/*.md` | Markdown formatting rules |
79| writing-style | `**/*.md` | Voice and tone conventions |
80| prompt-builder | AI artifacts | Prompt engineering authoring standards |
81| hve-core-location | `**` | Reference resolution for hve-core |
82
83### Skills
84
85| Tool | Type | How to Invoke | Purpose |
86|--------------|-------|--------------------|---------------------------------|
87| video-to-gif | Skill | Referenced in chat | Convert video to optimized GIFs |
88
89## Role-Specific Guidance
90
91Engineers are the primary users of Implementation, spending the majority of their engagement time here. Tech Leads contribute architecture-sensitive implementations. Data Scientists use notebook and dashboard generators. SREs handle infrastructure code. New Contributors start with guided tasks.
92
93* [Engineer Guide](../roles/engineer.md)
94* [Tech Lead Guide](../roles/tech-lead.md)
95* [Data Scientist Guide](../roles/data-scientist.md)
96* [SRE/Operations Guide](../roles/sre-operations.md)
97* [New Contributor Guide](../roles/new-contributor.md)
98
99## Starter Prompts
100
101### Full RPI Workflow
102
103```text
104/rpi Implement the pagination logic for the /api/v2/search endpoint.
105Add cursor-based pagination with a default page size of 50 and a maximum
106of 200 results per request. Follow the existing pagination pattern in
107src/api/handlers/list-resources.py.
108```
109
110### Step-by-Step RPI Agents
111
112Use individual task agents when you want more control over each phase.
113
114```text
115/task-research Investigate how the existing list-resources handler in
116src/api/handlers/list-resources.py implements pagination. Identify the
117cursor encoding strategy, default and maximum page sizes, and response
118envelope structure.
119```
120
121After research completes, plan the implementation:
122
123```text
124/task-plan Create an implementation plan for adding cursor-based pagination
125to the /api/v2/search endpoint following the patterns documented in the
126research output.
127```
128
129Execute the plan:
130
131Select **task-implementor** agent:
132
133```text
134Build the webhook delivery system following the plan in
135.copilot-tracking/plans/webhook-delivery-plan.md. Start with the event
136dispatcher component and implement the retry queue second.
137```
138
139Select **gen-jupyter-notebook** agent:
140
141```text
142Create a data analysis notebook for the Q4 sales transactions dataset in
143data/sales-q4-2025.parquet. Include data quality assessment, revenue trend
144analysis by product category and region, and customer cohort segmentation
145using RFM scoring with matplotlib visualizations.
146```
147
148After implementation, validate the changes:
149
150```text
151/task-review Validate the pagination implementation against the plan.
152Check cursor encoding, page size limits, response envelope consistency,
153and error handling for invalid cursor values.
154```
155
156## Stage Outputs and Next Stage
157
158Implementation produces source code, documentation, notebooks, dashboards, prompt artifacts, and infrastructure definitions. Transition to [Stage 7: Review](review.md) when implementation is complete. Use `/clear` to reset context before starting the review cycle.
159
160<!-- markdownlint-disable MD036 -->
161*🤖 Crafted with precision by ✨Copilot following brilliant human instruction,
162then carefully refined by our team of discerning human reviewers.*
163<!-- markdownlint-enable MD036 -->
164