Official agent skill

Engineering Principles

by Azure in Azure/agent-app-orchestrator

GPT-RAG Orchestrator architecture and implementation principles.

OfficialMITAuto-check passedBackend & APIs

Install Engineering Principles

skills CLI
$ npx skills add Azure/agent-app-orchestrator --skill engineering-principles -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Azure/agent-app-orchestrator engineering-principles --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Azure/agent-app-orchestrator.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.github/skills/engineering-principles .claude/skills/engineering-principles && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
engineering-principles
GitHub stars
103
Token cost
~276 tokens
SKILL.md length
81 words
Files
5 (incl. references)
Skills in repo
5
Repo updated
First seen
Licence
MIT

At a glance

GPT-RAG Orchestrator architecture and implementation principles.

  • Meaningful refactoring
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Runtime strategies
  • Azure integration

What it does

Engineering Principles is an agent skill from Azure/agent-app-orchestrator, published by the product's own GitHub organization. GPT-RAG Orchestrator architecture and implementation principles. Use for design, review, meaningful refactoring, runtime strategies, FastAPI, Azure integration, security, testing, or operations.

Its SKILL.md is about 280 tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `references/orchestrator-architecture.md`, `references/python-fastapi.md` and `references/security-and-operations.md`).

It sits in Backend & APIs, covering Backend development, Design review and critique and Retrieval-augmented generation. It works with Microsoft Azure, FastAPI and Python. The repository describes itself as: The GPT-RAG Orchestrator service is an agentic orchestration layer built on Microsoft Foundry Agent Service and the Microsoft Agent framework. It enables agent-based RAG… The licence is MIT.

When your agent uses it

  • Meaningful refactoring
  • Runtime strategies
  • Azure integration

Example prompts

  • “/engineering-principles”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit f202e25. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Engineering Principles loads about 276 tokens when it runs, and up to ~2k if it reads all its reference files. Until then it costs about 54 tokens; SKILL.md has 81 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~54
When it runs · the whole SKILL.md, loaded when a task matches
~276
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Azure/agent-app-orchestrator at commit f202e25, republished under its MIT licence (© Azure). 81 words, ~276 tokens.

Download SKILL.mdSave it as .claude/skills/engineering-principles/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
engineering-principles
description
GPT-RAG Orchestrator architecture and implementation principles. Use for design, review, meaningful refactoring, runtime strategies, FastAPI, Azure integration, security, testing, or operations.

GPT-RAG Orchestrator engineering principles

Load only the references needed for the task:

When the task involvesRead
Repository purpose, boundaries, runtime strategies, or component ownershipOrchestrator architecture
Python, FastAPI, async code, modularity, or implementation clarityPython and FastAPI
Tests, validation, compatibility, or evidenceTesting and evidence
Identity, secrets, networking, retrieval, MCP, telemetry, or operationsSecurity and operations

Use these principles as design questions rather than dogma. Task requirements, executable configuration, versioned contracts, and the current implementation remain the sources of truth.

© Azure, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (references) in .github/skills/engineering-principles of Azure/agent-app-orchestrator.

  • SKILL.md
  • references/orchestrator-architecture.md
  • references/python-fastapi.md
  • references/security-and-operations.md
  • references/testing-and-evidence.md

Open the folder on GitHubat commit f202e25

Compare with similar skills

Engineering Principles next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Engineering Principles compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Engineering Principles this skillAzure/agent-app-orchestrator103—~276Automated safety check: PassMIT
Python Appservice Deploymicrosoft/GitHub-Copilot-for-Azure2551 repos~688Automated safety check: PassMIT
Azure Cosmos DB Pymicrosoft/skills3.1k—~2.8kAutomated safety check: PassMIT
Documentation Guidevolfpeter/holm132—~1.4kAutomated safety check: PassMIT
Framework Migration AssistantArabelaTso/Skills-4-SE253—~1.9kAutomated safety check: PassApache-2.0
Specx Diwire Compositionmaksimzayats/specx202—~1.1kAutomated safety check: PassMIT

Similar skills

  • Python Appservice Deploy

    microsoft/GitHub-Copilot-for-Azure

    Official

    Deploy Python (Flask/Django/FastAPI) code to Azure App Service Linux.

    255 GitHub starsUsed in 1 repo~688 tokens
    Backend & APIsAuto-check passed
  • Azure Cosmos DB Py

    microsoft/skills

    Official

    Build Azure Cosmos DB NoSQL services with Python/FastAPI following production-grade patterns.

    3.1k GitHub stars~2.8k tokensUpdated yesterday
    DatabasesAuto-check passed
  • Documentation Guide

    volfpeter/holm

    A skill your agent uses when writing or modifying documentation, guides, or example READMEs.

    132 GitHub stars~1.4k tokensUpdated 21 days ago
    Backend & APIsAuto-check passed
  • Framework Migration Assistant

    ArabelaTso/Skills-4-SE

    Automatically migrate Python web applications between frameworks (Flask → FastAPI, Django → FastAPI).

    253 GitHub stars~1.9k tokensUpdated 1 mo ago
    Backend & APIsAuto-check passed
  • Specx Diwire Composition

    maksimzayats/specx

    Wire dependency injection for a specx Python service with diwire.

    202 GitHub stars~1.1k tokensUpdated 2 mo ago
    Backend & APIsAuto-check passed
  • Databricks Apps Python

    databricks/databricks-agent-skills

    Official

    Python backend for Databricks Apps — FastAPI (default), Flask, Dash, Streamlit, Gradio, Reflex.

    345 GitHub stars~3k tokensUpdated yesterday
    Backend & APIsAuto-check passed

More from Azure/agent-app-orchestrator

  • Release

    Azure/agent-app-orchestrator

    Official

    Prepare and reconcile GPT-RAG Orchestrator releases, including authoritative version discovery, semantic version selection, release branches, VERSION and CHANGELOG updates, release notes, tags…

    103 GitHub stars~2.5k tokensUpdated yesterday
    Auto-check passed
  • Architecture Decision

    Azure/agent-app-orchestrator

    Official

    Conducts and records a verifiable GPT-RAG Orchestrator architectural decision.

    103 GitHub stars~314 tokensUpdated yesterday
    Auto-check passed
  • Documentation Consistency

    Azure/agent-app-orchestrator

    Official

    Keeps GPT-RAG Orchestrator user and operator documentation aligned with shipped behavior.

    103 GitHub stars~335 tokensUpdated yesterday
    Auto-check passed
  • Orchestrator Release

    Azure/agent-app-orchestrator

    Official

    Prepares and validates GPT-RAG Orchestrator releases. An agent skill from Azure/agent-app-orchestrator.

    103 GitHub stars~420 tokensUpdated yesterday
    Auto-check passed

Questions about Engineering Principles

What does Engineering Principles do?

GPT-RAG Orchestrator architecture and implementation principles. Engineering Principles is an agent skill from Azure/agent-app-orchestrator, published by the product's own GitHub organization. GPT-RAG Orchestrator architecture and implementation principles.

When should I use Engineering Principles?

Engineering Principles fits situations like: meaningful refactoring; runtime strategies; azure integration.

How do I install Engineering Principles in Claude Code?

Run `npx skills add Azure/agent-app-orchestrator --skill engineering-principles -a claude-code`. Or copy the skill folder (.github/skills/engineering-principles in Azure/agent-app-orchestrator) into .claude/skills/engineering-principles in your project. Claude Code loads it when a task matches its description.

How do I install Engineering Principles in Codex?

Run `npx skills add Azure/agent-app-orchestrator --skill engineering-principles -a codex`. Or copy the skill folder (.github/skills/engineering-principles in Azure/agent-app-orchestrator) into .agents/skills/engineering-principles in your project. Codex loads it when a task matches its description.

Can I use Engineering Principles in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Azure/agent-app-orchestrator --skill engineering-principles -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/engineering-principles, .gemini/skills/engineering-principles, .github/skills/engineering-principles and .opencode/skills/engineering-principles in your project.

What does Engineering Principles need to run?

SKILL.md names no scripts, command-line tools or credentials: Engineering Principles is instructions for the agent only. Our summary lists: Python 3.

Does Engineering Principles access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Engineering Principles safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Engineering Principles use?

Engineering Principles is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Engineering Principles use?

About 276 tokens (SKILL.md is roughly 1.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.8k tokens, read only when the agent opens those files.

What are the alternatives to Engineering Principles?

Skills that share tags, products or a category with Engineering Principles: Python Appservice Deploy (microsoft/GitHub-Copilot-for-Azure, 255 stars), Azure Cosmos DB Py (microsoft/skills, 3.1k stars), Documentation Guide (volfpeter/holm, 132 stars) and Framework Migration Assistant (ArabelaTso/Skills-4-SE, 253 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Engineering Principles?

Azure (a GitHub organization, an official publisher) maintains it in Azure/agent-app-orchestrator, which has 103 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 6, 2026.

Source: Azure/agent-app-orchestrator on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.