azure-aigateway

Configure Azure API Management as an AI Gateway for AI models, MCP tools, and agents. WHEN: semantic caching, token limit, content safety, load balancing, AI model governance, MCP rate limiting, jailbreak detection, add Azure OpenAI backend, add AI Foundry model, test AI gateway, LLM policies, configure AI backend, token metrics, AI cost control, convert API to MCP, import OpenAPI to gateway.

Quality

93%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Risky

Do not use without reviewing

Quality

Discovery

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a strong skill description that clearly defines its scope (Azure API Management as AI Gateway), lists concrete capabilities, and provides an extensive set of natural trigger terms via an explicit WHEN clause. The description is well-structured, uses third person voice, and is highly distinctive in its domain focus.

Dimension	Reasoning	Score
Specificity	The description lists multiple specific concrete actions: configuring Azure API Management as an AI Gateway, semantic caching, token limiting, content safety, load balancing, jailbreak detection, adding Azure OpenAI backends, converting APIs to MCP, importing OpenAPI specs, and more.	3 / 3
Completeness	Clearly answers both 'what' (Configure Azure API Management as an AI Gateway for AI models, MCP tools, and agents) and 'when' with an explicit 'WHEN:' clause listing numerous specific trigger scenarios.	3 / 3
Trigger Term Quality	Excellent coverage of natural trigger terms users would say: 'semantic caching', 'token limit', 'content safety', 'load balancing', 'jailbreak detection', 'Azure OpenAI backend', 'AI Foundry model', 'MCP rate limiting', 'convert API to MCP', 'import OpenAPI to gateway'. These are terms practitioners would naturally use.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive — the combination of Azure API Management, AI Gateway, MCP tools, and specific policies like jailbreak detection and semantic caching creates a very clear niche that is unlikely to conflict with other skills.	3 / 3
	Total	12 / 12 Passed

Implementation

87%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a well-crafted skill that efficiently serves as a gateway overview with strong actionability and excellent progressive disclosure. The main weakness is the lack of explicit validation steps after key operations like backend creation and policy application, which prevents workflow clarity from reaching the highest score. Overall, it's a strong skill that respects token budget while providing concrete, executable guidance.

Suggestions

Add validation commands after key operations (e.g., after 'az apim backend create', add a verification step like 'az apim backend show' to confirm creation, and after applying policies, include a test call to verify the policy is active).

Dimension	Reasoning	Score
Conciseness	The content is lean and well-structured. It avoids explaining what APIM is or how AI gateways work conceptually, instead jumping straight to actionable commands and policy references. The trigger table and quick reference table are efficient ways to convey information without verbosity.	3 / 3
Actionability	Provides fully executable Azure CLI commands for getting gateway details, testing endpoints, adding backends, and granting role assignments. The curl example for testing is copy-paste ready with clear placeholders. Policy ordering is specific and numbered.	3 / 3
Workflow Clarity	The 'Add AI Backend' section has a clear sequence (discover → create → grant access), and the policy ordering is well-defined. However, there are no explicit validation checkpoints or feedback loops — after creating a backend or applying policies, there's no 'verify it worked' step before proceeding. For operations involving backend configuration and policy application, this is a gap.	2 / 3
Progressive Disclosure	Excellent progressive disclosure with a concise overview pointing to well-organized one-level-deep references (policies.md, patterns.md, troubleshooting.md, SDK references). The 'Reference Index' table with 'When to Load' guidance and the explicit instruction 'do NOT read all at once' is particularly well done.	3 / 3
	Total	11 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: jonathan-vella/azure-agentic-infraops
Commit: ec7b8ff

Reviewed: 7 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.