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.
Install with Tessl CLI
npx tessl i github:microsoft/github-copilot-for-azure --skill azure-aigateway95
Does it follow best practices?
Evaluation — 95%
↑ 1.72xAgent success when using this skill
Validation for skill structure
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 an excellent skill description that clearly defines its scope (Azure API Management as AI Gateway), provides comprehensive trigger terms covering various use cases, and explicitly separates the 'what' from the 'when' using a clear WHEN: clause. The description is specific, actionable, and distinctive enough to avoid conflicts with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Configure Azure API Management as an AI Gateway', 'semantic caching', 'token limit', 'content safety', 'load balancing', 'jailbreak detection', 'add Azure OpenAI backend', 'convert API to MCP', 'import OpenAPI to gateway'. | 3 / 3 |
Completeness | Clearly answers both what ('Configure Azure API Management as an AI Gateway for AI models, MCP tools, and agents') and when (explicit 'WHEN:' clause with comprehensive trigger scenarios like 'semantic caching', 'token limit', 'test AI gateway', etc.). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'semantic caching', 'token limit', 'content safety', 'load balancing', 'MCP rate limiting', 'jailbreak detection', 'Azure OpenAI', 'AI Foundry', 'LLM policies', 'AI cost control', 'OpenAPI'. These are terms practitioners would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche: Azure API Management + AI Gateway is a specific combination. Trigger terms like 'Azure OpenAI backend', 'AI Foundry model', 'MCP rate limiting' are unique enough to avoid conflicts with generic API or AI 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-structured skill that efficiently covers Azure AI Gateway configuration with actionable commands and excellent progressive disclosure. The main weakness is the lack of explicit validation steps for policy application, which is a potentially risky operation that could benefit from a verify-before-commit workflow.
Suggestions
Add validation steps after policy application (e.g., 'Test with a sample request before applying to production API')
Include a rollback procedure or policy backup step before making changes to governance policies
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient, using tables for quick reference, minimal prose, and assuming Claude understands Azure/APIM concepts without explanation. Every section serves a clear purpose with no padding. | 3 / 3 |
Actionability | Provides fully executable bash commands with proper flags and placeholders, concrete curl examples for testing, and specific policy names. Commands are copy-paste ready with clear parameter substitution. | 3 / 3 |
Workflow Clarity | The 'Apply AI Governance Policy' section lists recommended order but lacks explicit validation checkpoints. For policy configuration (which can break API behavior), there's no validate-then-apply workflow or rollback guidance. | 2 / 3 |
Progressive Disclosure | Excellent structure with a concise overview, quick reference table, and well-signaled one-level-deep references to detailed policies, patterns, troubleshooting, and SDK docs. Navigation is clear and organized. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%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.
- Reviewed
Table of Contents
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.