AgentStack
Sign in Publish
MCP servers Skills Toolkits Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Azure Openai

skill-ashish7802-awesome-api-skills-azure-openai · by ashish7802

A Claude skill from ashish7802/awesome-api-skills.

↗ Repository
— No reviews yet
0 installs
10 views
0.0% view→install

Install

$ agentstack add skill-ashish7802-awesome-api-skills-azure-openai

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Azure Openai? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Azure OpenAI API Skill

Quick Start

Azure OpenAI provides the same models as OpenAI (GPT-4) but within the Azure compliance boundary, utilizing Active Directory and custom domain endpoints.

npm install openai

Common Workflows

Enterprise Model Deployment

Unlike the public OpenAI API, Azure requires you to explicitly deploy a model in your resource. You must use your unique Deployment ID rather than the generic model name (e.g., gpt-4) in your API calls.

Production Patterns

Content Filtering

Azure OpenAI applies aggressive, customizable content filters. You can detect if a response was filtered by inspecting the finish_reason which will evaluate to content_filter instead of stop.

Error Recovery

Handle 429 Too Many Requests. Azure OpenAI rate limits are based on Tokens-Per-Minute (TPM) assigned to your deployment. If you exceed this, you must retry. Use the @azure/core-rest-pipeline to inject automated retry policies.

Security Notes

Avoid static API keys. Use Managed Identities (Entra ID / Azure AD) to authenticate your application servers to the Azure OpenAI endpoint securely without rotating secrets.

Performance Considerations

Latency is heavily dependent on the Azure region. Deploy your models in the same region as your application servers to minimize network RTT (Round Trip Time).

Testing Guidance

Use the official OpenAI SDK, but configure the baseURL and defaultHeaders to point to your Azure endpoint (https://.openai.azure.com/openai/deployments/).

Troubleshooting

If you receive a 'Resource not found' error, verify that the api-version query parameter is correct and supported by your specific model deployment.

References

Related Skills

  • [OpenAI](/skills/openai)
  • [Anthropic](/skills/anthropic)

Why use this skill

Use this when your agent works with azure-openai — structured patterns beat pasted docs and prevent common hallucinations.

AI pitfalls

  • Using deprecated model IDs or wrong API endpoints
  • Confusing chat vs completions vs embeddings APIs
  • Omitting rate-limit and token budget handling

Production checklist

  • [ ] Secrets in environment variables, not source code
  • [ ] Error handling and logging in place
  • [ ] Rate limits and timeouts configured

Related skills

  • [openai](../openai/SKILL.md) — related to
  • [anthropic](../anthropic/SKILL.md) — related to

> Last Verified: 2026-07-02

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Cloud & Infrastructure