Skip to content
Back to skills

Create Azure Agent

ASecurity

Deploys a skill as an Azure AI Foundry hosted agent. NOT for Docker runtime skills (use `create-docker-skill`) and NOT for MCP server integrations (use `create-mcp-integration`).

  • 7 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added September 2, 2026
ai-agentspythonbashdockerazure

Works with

  • cli
  • mcp

Security analysis

A100/100

Pro scans all 20 files and shows the line behind each finding

Scanned October 3, 2026

npx -y skills add richfrem/agent-plugins-skills --skill create-azure-agent --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Create Azure Agent?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Create Azure Agent
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/richfrem-create-azure-agent-agent-plugins-skills/badge)](https://www.skillsdirectory.com/skills/richfrem-create-azure-agent-agent-plugins-skills)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: create-azure-agent
plugin: agent-scaffolders
description: >
  Deploys a skill as an Azure AI Foundry hosted agent. NOT for Docker runtime skills (use `create-docker-skill`) and NOT for MCP server integrations (use `create-mcp-integration`).
argument-hint: "[skill-dir]"
allowed-tools: Bash, Write, Read
---

# Create Azure Agent (`create-azure-agent`)

Generates Azure AI Foundry deployment wrappers, Bicep infrastructure templates, and Azure AI Projects SDK orchestration scripts for existing skills.

## Contents

- [Critical Constraints](#critical-constraints)
- [Quick start](#quick-start)
- [Workflow](#workflow)
- [Verification](#verification)
- [References](#references)

## Critical Constraints

1. **Scope Boundaries**: Designed specifically for Azure AI Foundry hosted agents. Use `create-docker-skill` for containerized runtimes and `create-mcp-integration` for MCP servers.
2. **Tool Ceiling Limit**: Azure AI Foundry enforces a strict 128-tool limit per agent. The scaffolder generates a focused worker configuration.
3. **Authentication Pre-Condition**: Azure CLI authentication (`az login`) and active subscription context are required before deployment execution.

## Quick start

Scaffold Azure AI Foundry deployment templates for a target skill:

```bash
python3 scripts/scaffold_azure_agent.py --skill-dir plugins/<plugin>/skills/<skill-name>
```

## Workflow

1. **Resolve Target Skill**: Validate that the input path contains a functional `SKILL.md`.
2. **Gather Configuration**: Collect Azure subscription, resource group, region, and project naming preferences.
3. **Generate Artifacts**: Run `scaffold_azure_agent.py` to create `azure_deployment/azure_agent.py` and `azure_deployment/main.bicep`.
4. **Deploy Infrastructure**: Review Bicep parameters and deploy via `az deployment group create`.

## Verification

Validate generated Bicep and Python deployment wrappers against Azure schema:

```bash
az bicep build --file azure_deployment/main.bicep
```

## References

- [acceptance-criteria.md](references/acceptance-criteria.md) — Acceptance gates and deployment wrapper requirements.
- [fallback-tree.md](references/fallback-tree.md) — Fallback resolution when Azure CLI or Bicep validation fails.

Files in this skill

  • SKILL.md1.6 KB
  • acceptance-criteria.md385 B
  • evals/evals.json883 B
  • evals/results.tsv417 B
  • fallback-tree.md1.4 KB
  • references/acceptance-criteria.md42 B
  • references/fallback-tree.md36 B
  • references/hitl-interaction-design.md46 B
  • references/pattern-decision-matrix.md46 B
  • references/patterns/action-forcing-output-with-deadline-attribution.md82 B
  • references/patterns/adversarial-objectivity-constraint.md69 B
  • references/patterns/anti-pattern-vaccination.md59 B
  • references/patterns/anti-symptom-triage.md54 B
  • references/patterns/artifact-embedded-execution-audit-trail.md74 B
  • references/patterns/artifact-generation-xss-compliance-gate.md74 B
  • references/patterns/artifact-lifecycle.md53 B
  • references/patterns/artifact-state-interrogative-routing.md71 B
  • references/patterns/asynchronous-benchmark-metric-capture.md72 B
  • references/patterns/audience-segmented-information-filtering.md75 B
  • references/patterns/category-calibrated-benchmark-anchoring.md74 B

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…