Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →microsoftdocs/azure-face
Expert knowledge for Azure AI Face development including troubleshooting, best practices, decision making, limits & quotas, security, and integrations & coding patterns.
Passed 6 of 13 test cases with the skill, and 8 of 13 without it.
and 1 more in the full report
3 fixed7 passed either way5 still failing7 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.
When an AI assistant fetches technical articles from Microsoft Learn for Azure AI Face troubleshooting, what required query string parameter must be appended to the URL to signal skill-based fetching?
| Checked | Without skill | With skill |
|---|---|---|
| Identifies the mandatory query parameter string from=learn-agent-skill. | Missed | Passed |
The instructions your model reads when the skill loads.
This skill provides expert guidance for Azure AI Face. Covers troubleshooting, best practices, decision making, limits & quotas, security, and integrations & coding patterns. It combines local quick-reference content with remote documentation fetching capabilities.
IMPORTANT for Agent: Use the Category Index below to locate relevant sections. For categories with line ranges (e.g.,
L35-L120), useread_filewith the specified lines. For categories with file links (e.g.,[security.md](security.md)), useread_fileon the linked reference file
IMPORTANT for Agent: If
metadata.generated_atis more than 3 months old, suggest the user pull the latest version from the repository. Ifmcp_microsoftdocstools are not available, suggest the user install it: Installation Guide
This skill requires network access to fetch documentation content:
mcp_microsoftdocs:microsoft_docs_fetch with query string from=learn-agent-skill. Returns Markdown.fetch_webpage with query string from=learn-agent-skill&accept=text/markdown. Returns Markdown.| Category | Lines | Description |
|---|---|---|
| Troubleshooting | L34-L38 | Diagnosing and fixing Azure Face API failures by interpreting error codes, understanding causes (quota, auth, input issues), and applying recommended resolutions. |
| Best Practices | L39-L47 | Guidance on enrolling faces, scaling PersonGroup/PersonDirectory, optimizing performance/latency, and building consent-aware, high-capacity Azure Face enrollment workflows. |
| Decision Making | L48-L53 | Guidance on choosing, configuring, and tuning Azure Face detection and recognition models, including model types, capabilities, parameters, and selection trade-offs. |
| Limits & Quotas | L54-L59 | Scaling PersonGroup for large face datasets and understanding Face API quotas, rate limits, and maximum sizes for persons, faces, and training operations. |
| Security | L60-L69 | Security and compliance for Face and liveness: abuse monitoring, token-based access control, network isolation, encryption/CMK, shared responsibility, and secure SDK version management. |
| Integrations & Coding Patterns | L70-L73 | How to call Azure Face API endpoints, use key operations (detect, identify, verify, find similar), and structure requests/responses in your applications. |
| Topic | URL |
|---|---|
| Resolve Azure Face API errors using error codes | https://learn.microsoft.com/en-us/azure/ai-services/face/reference-face-error-codes |
| Topic | URL |
|---|---|
| Apply best practices for Azure Face enrollment | https://learn.microsoft.com/en-us/azure/ai-services/face/enrollment-overview |
| Add many faces to PersonGroup efficiently | https://learn.microsoft.com/en-us/azure/ai-services/face/how-to/add-faces |
| Optimize Azure Face performance and reduce latency | https://learn.microsoft.com/en-us/azure/ai-services/face/how-to/mitigate-latency |
| Use PersonDirectory for high-capacity face storage | https://learn.microsoft.com/en-us/azure/ai-services/face/how-to/use-persondirectory |
| Implement consent-focused Face enrollment app | https://learn.microsoft.com/en-us/azure/ai-services/face/tutorials/build-enrollment-app |
test cases passed, vs 8 / 13 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.