Skip to content
| Marketplace
Sign in
Visual Studio Code>AI>Multi-Role Engineering ChatbotNew to Visual Studio Code? Get it now.
Multi-Role Engineering Chatbot

Multi-Role Engineering Chatbot

Skills Chatbot

|
6 installs
| (0) | Free
AI chat with 7 built-in engineering roles — Developer, QA, DevOps, Architect, BA, Security, Data Engineer. Powered by GitHub Copilot. No API key needed.
Installation
Launch VS Code Quick Open (Ctrl+P), paste the following command, and press enter.
Copied to clipboard
More Info

Multi-Role Engineering Chatbot

A role-based AI assistant for software delivery teams. Describe your task in plain language and the correct engineering role — Developer, QA Engineer, DevOps, Solution Architect, Business Analyst, Security Engineer, or Data Engineer — is automatically applied with its full set of procedures, templates, and quality gates.

No API key required. Uses your existing GitHub Copilot subscription.


Install — 2 Steps

No cloning. No npm. No API keys. Just install and chat.

Step 1 — Install the extension

Option A — VS Code Marketplace

  1. Press Ctrl+Shift+X to open the Extensions panel
  2. Search Multi-Role Engineering Chatbot
  3. Click Install

Option B — Install from .vsix (offline / internal sharing)

  1. Download the .vsix file shared by your team
  2. Ctrl+Shift+X → click ... (top-right) → Install from VSIX… → select the file

Step 2 — Open the chat

Ctrl+Shift+P  →  Skills Chatbot: Open Chat

Type any engineering task. The correct role is detected automatically. No configuration needed.


Available Roles

Role What it produces
Developer Code, unit tests, PR templates, commit messages
QA Engineer Test cases, test plans, defect reports, coverage summaries
DevOps Engineer CI/CD pipelines, IaC, deployment runbooks, monitoring config
Solution Architect HLD, ADRs, C4 diagrams, NFR register, API contracts
Business Analyst User stories, BRD, RTM, acceptance criteria
Security Engineer Threat models, OWASP findings, CVSS scores, SAST/DAST guidance
Data Engineer ETL/ELT pipelines, data models, dbt, data quality rules

How to Verify it Works

Skill Chatbot (this extension)

  1. Ctrl+Shift+P → Skills Chatbot: Open Chat
  2. Type: Write unit tests for the account lockout logic
  3. Expected: Response starts with ### Role → Developer, followed by ### Task Understanding, ### Execution, ### Output, ### Assumptions
  4. A Developer Skill tag appears below the response

If you see an error, ensure GitHub Copilot Chat is installed and you are signed in (Ctrl+Shift+P → "GitHub Copilot: Sign In").


GitHub Copilot Chat

The extension auto-copies .github/copilot-instructions.md into every workspace you open. To verify Copilot is using the skill templates:

  1. Open Copilot Chat (Ctrl+Alt+I)
  2. Type: Write test cases for the password reset flow
  3. Expected: Copilot responds with ### Role → QA Engineer and uses the TC-ID template format
  4. If the response is generic (no ### Role header), run: Ctrl+Shift+P → Skills Chatbot: Install Skill Files into Workspace — this forces the skill files into the current project

To attach a skill file directly for maximum precision:

#file:.github/skills/quality-analyst/SKILL.md
Write test cases for the password reset flow

Claude Code

  1. Open Claude Code in this workspace
  2. Type: /developer Write a REST endpoint for user registration
  3. Expected: Response follows the five-section format with the Developer code template

Or use the auto-router:

/skills Design an ADR for PostgreSQL vs MongoDB

What Gets Installed Automatically

When you open any workspace folder, the extension silently copies these files in (only on first open — never overwrites):

File Purpose
.github/copilot-instructions.md Auto-loaded by Copilot — role detection active immediately
.github/skills/*/SKILL.md Attach with #file: in Copilot Chat for deep per-role context
.claude/commands/*.md Slash commands (/developer, /quality-analyst, etc.) for Claude Code

Response Format

Every response follows this structure regardless of which tool you use:

### Role
[Developer / QA Engineer / DevOps Engineer / Solution Architect / Business Analyst / Security Engineer / Data Engineer]

### Task Understanding
[What the assistant understood you to be asking for]

### Execution
[The phased workflow steps followed to produce the output]

### Output
[The artefact — code, test cases, ADR, user story, pipeline YAML, threat model, data pipeline spec]

### Assumptions (if any)
[Any assumptions applied; "None" if not applicable]

Example Prompts

Developer

Write a REST endpoint in Python (FastAPI) to create a new customer order with input validation
Write unit tests for the account lockout logic
Implement retry logic with exponential backoff for the payment service HTTP client

QA Engineer

Write test cases for the password reset flow
Draft a defect report: checkout total is wrong when a discount code is applied
Write a test plan for the Sprint 5 payment feature release

DevOps Engineer

Write a GitHub Actions CI/CD pipeline for a Python FastAPI service using Docker
Draft a deployment runbook for the v3.0.0 production release
Write a Terraform module to provision an Azure App Service with PostgreSQL

Solution Architect

Write an ADR for choosing between PostgreSQL and MongoDB for a multi-tenant SaaS product
Produce a C4 context diagram for the order management system
Define NFRs for the payment service — performance, availability, and security

Business Analyst

Write a user story for the customer profile update feature with acceptance criteria
Draft BRD section 3 — functional requirements for the notification service

Security Engineer

Review the login endpoint for OWASP Top 10 vulnerabilities
Write a STRIDE threat model for the payment processing service
Score this vulnerability with CVSS v3.1: unauthenticated access to admin API

Data Engineer

Design an incremental ELT pipeline to sync orders from PostgreSQL to Snowflake
Write a dbt model for the customer lifetime value report
Define data quality rules for the fact_orders table

Troubleshooting

Problem Solution
Chat opens but shows an error Ensure GitHub Copilot Chat is installed and signed in
Copilot gives generic responses (no ### Role header) Run Skills Chatbot: Install Skill Files into Workspace from the command palette
Skill files already exist warning Normal — the extension skips copy if files are already present
Claude Code slash command not found Ensure .claude/commands/ exists in the workspace root — run Install Skill Files
Want skills in every project globally Copy .claude/commands/*.md to %USERPROFILE%\.claude\commands\ (Windows) or ~/.claude/commands/ (Mac/Linux)

For Developers — Build from Source

Only needed if you want to modify and repackage the extension.

# 1. Clone
git clone <repository-url>
cd skill_chatbot

# 2. Install the packager (one-time)
npm install -g @vscode/vsce

# 3. Package
vsce package
# → creates skill-chatbot-x.x.x.vsix
  • Contact us
  • Jobs
  • Privacy
  • Manage cookies
  • Terms of use
  • Trademarks
© 2026 Microsoft