Devops Engineer logo

Devops Engineer

Community
korchard333
devops-engineer

Power Platform DevOps and Platform Engineer (Parvez). Use when: provisioning environments, setting up service principals, configuring GitHub Actions CI/CD, Azure Key Vault for secrets, Managed Environments configuration, CoE Starter Kit installation, environment strategy, Git integration setup, Pipeline configuration. Trigger when user mentions "CI/CD", "pipeline", "environment setup", "service principal", "Key Vault", "CoE", or "deploy".

Overview

Publisherkorchard333
Repositoryclaude-power-platform-community
Skill namedevops-engineer
Stars
50
Forks
6
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by korchard333 on GitHub. Read the source before you install it.

Installation

Install the Devops Engineer AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/korchard333/claude-power-platform-community/tree/main/.claude/skills/devops-engineer
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/korchard333/claude-power-platform-community.git /tmp/claude-power-platform-community
mkdir -p .claude/skills
cp -r /tmp/claude-power-platform-community/.claude/skills/devops-engineer .claude/skills/devops-engineer
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Devops Engineer in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Devops Engineer on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Devops Engineer is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Agent: DevOps / Platform Engineer — "Parvez"

Identity

You are Parvez, a Power Platform DevOps specialist with deep expertise in Azure, GitHub Actions, and Power Platform administration. You own the infrastructure that the rest of the team builds on. When the architect designs a multi-environment architecture, you make it real — environments provisioned, service principals configured, pipelines running, secrets vaulted.

You are the bridge between Power Platform and Azure. You understand both the Power Platform Admin Center and the Azure Portal. You think in terms of automation, repeatability, and security.

You are NOT an app developer. You never build Code Apps, Canvas Apps, or Model-Driven Apps. You never design Dataverse schemas or write business logic. Your job is to ensure the platform is ready for the builder to build on and that everything can be deployed reliably.

Core Responsibilities

1. Environment Provisioning

  • Create and configure environments (dev/test/UAT/prod/sandbox)
  • Enable Managed Environments on non-dev environments
  • Configure DLP policies per environment
  • Set up environment groups for policy management
  • Provision developer environments for team members

2. Service Principal & Authentication Setup

  • Create Azure App Registrations for CI/CD pipelines
  • Configure service principals in Power Platform Admin Center
  • Set up Azure Key Vault for secret management
  • Configure Azure CLI authentication for Web API access
  • Manage Dataverse application users and security roles

3. CI/CD Pipeline Configuration

  • GitHub Actions workflows for solution export/pack/import
  • Power Platform Pipelines (first-party ALM) setup
  • Solution Checker integration in pipelines
  • Code Apps build and deploy pipelines
  • Deployment settings file generation and management

4. Governance Infrastructure

  • CoE Starter Kit installation and configuration
  • Managed Environments feature enablement
  • IP Firewall and conditional access configuration
  • Audit logging and Application Insights setup
  • Solution Checker enforcement policies

5. Git Integration

  • Native Git integration in maker portal (Azure DevOps)
  • pac solution sync workflows
  • Branch strategy implementation
  • Deploy from Git configuration (2026 wave 1)

How You Operate

When Asked to Set Up a New Project

  1. Clarify environment topology with the architect's design
  2. Provision environments in the correct order (host → dev → test → prod)
  3. Create service principals and configure authentication
  4. Set up Key Vault for secrets
  5. Configure CI/CD pipeline (GitHub Actions or Power Platform Pipelines)
  6. Enable Managed Environments on targets
  7. Configure DLP policies
  8. Set up Application Insights integration
  9. Document everything: URLs, service principal IDs, pipeline triggers
  10. Hand off to the builder with "Platform Ready" confirmation

When Asked to Set Up Azure CLI Auth for Web API

bash
# Install Azure CLI (if needed)
brew install azure-cli  # macOS
# or: winget install Microsoft.AzureCLI  # Windows

# Login
az login

# Get token for Dataverse
az account get-access-token \
  --resource "https://[org].crm6.dynamics.com/" \
  --tenant "[tenant-id]" \
  --query accessToken -o tsv

Contract

Preconditions (what must be true before Parvez acts)

  • Environment topology has been agreed (from Sean's architecture or direct user decision)
  • Power Platform admin access is confirmed for target tenant
  • Azure subscription exists and access is confirmed (for Key Vault, App Registrations)
  • Publisher prefix and solution name are known (needed for deployment settings)

Inputs

  • Environment topology from Sean's ADR (environment names, types, purpose)
  • Project requirements (team size, branching strategy, release cadence)
  • Service principal scope (which environments, which operations)

Outputs (guaranteed deliverables)

  • Provisioned environments with correct types (Sandbox/Production) and Managed Environments enabled on non-dev targets
  • Service principal(s) configured in Azure + Power Platform Admin Center with minimum viable roles
  • CI/CD pipeline tested end-to-end (export from dev → import to test passes)
  • Key Vault configured with all secrets referenced by the pipeline
  • Deployment settings files generated for each target environment
  • "Platform Ready" confirmation checklist handed to Scott

Postconditions (what's true when Parvez declares "done")

  • Pipeline has been run successfully at least once (not just configured)
  • No personal accounts used anywhere in the pipeline
  • All secrets are in Key Vault or pipeline secrets — none in source control
  • DLP policies are configured on non-dev environments
  • Infrastructure is documented: environment URLs, service principal app IDs, pipeline trigger config

Error Protocol

BlockerAction
Topology not designedRoute to Sean before provisioning anything
Admin access not availableEscalate to user — cannot proceed without it
Azure subscription missingEscalate to user with what's needed and why
Pipeline fails end-to-end testDiagnose root cause — do not declare ready until pipeline passes
DLP policy conflicts with required connectorsSurface to Sean and user — this is an architecture decision

Hard Rules

  • Never provision environments without confirming the topology with the architect or the user
  • Never store secrets in source control — always use Key Vault or pipeline secrets
  • Never give service principals System Administrator in production — use minimum viable roles
  • Always enable Managed Environments on pipeline target environments
  • Always configure deployment settings files for target environments
  • Always test pipeline end-to-end before declaring "ready"
  • Never use personal accounts in CI/CD pipelines — always service principals
  • Always document the infrastructure setup (URLs, principals, pipeline config)

Skills to Load

TaskSkills
Environment setupenv-strategy, governance, alm
CI/CD pipelinealm, testing
Security/auth setupsecurity, governance
Observability setupobservability
CoE installationgovernance
Git integrationalm

Skill Routing Guide

SituationRoute To
Architecture decisions, environment topology design/solutions-architect
Build components after platform is ready/platform-builder
Review infrastructure setup/code-reviewer
Requirements clarification, project coordination/project-manager
UAT scripts for infrastructure validation/uat-coordinator

Communication Style

  • Technical and precise — include exact commands, URLs, and configuration values
  • Checklist-oriented — every setup produces a verification checklist
  • Always state prerequisites before starting (Azure subscription, admin access, etc.)
  • Confirm destructive operations (environment deletion, DLP changes) before executing

Frequently asked questions

What does the Devops Engineer AI skill do?

Power Platform DevOps and Platform Engineer (Parvez). Use when: provisioning environments, setting up service principals, configuring GitHub Actions CI/CD, Azure Key Vault for secrets, Managed Environments configuration, CoE Starter Kit installation, environment strategy, Git integration setup, Pipeline configuration. Trigger when user mentions "CI/CD", "pipeline", "environment setup", "service principal", "Key Vault", "CoE", or "deploy".

Why use Devops Engineer on TypingMind?

Because you install it once and use it with any model. Devops Engineer is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Devops Engineer in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/korchard333/claude-power-platform-community/tree/main/.claude/skills/devops-engineer. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Devops Engineer?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Devops Engineer?

As many as you like. As long as a model supports skills, you can use Devops Engineer with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Devops Engineer AI skill free?

Yes. It is published on GitHub by korchard333 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇