Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →microsoftdocs/azure-custom-vision
Expert knowledge for Azure AI Custom Vision development including best practices, decision making, limits & quotas, security, integrations & coding patterns, and deployment.
Passed 22 of 22 test cases with the skill, and 13 of 22 without it.
and 6 more in the full report
9 fixed13 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
When fetching Microsoft documentation content via preferred remote tools for Azure Custom Vision, what specific tracking query parameter must be appended to the request?
| Checked | Without skill | With skill |
|---|---|---|
| from=learn-agent-skill | Missed | Passed |
The instructions your model reads when the skill loads.
This skill provides expert guidance for Azure AI Custom Vision. Covers best practices, decision making, limits & quotas, security, integrations & coding patterns, and deployment. 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 |
|---|---|---|
| Best Practices | L34-L39 | Improving Custom Vision model quality with better data collection/labeling strategies and using Smart Labeler to speed and automate image annotation |
| Decision Making | L40-L45 | Guidance on selecting the best Custom Vision domain for your scenario and planning migrations from Custom Vision to other Azure or third‑party vision services. |
| Limits & Quotas | L46-L50 | Details on Custom Vision usage limits per pricing tier, including training/prediction quotas, project and image caps, and how limits affect model training and deployment. |
| Security | L51-L57 | Managing Custom Vision security: encryption with customer-managed keys, secure data handling/export/deletion, and configuring Azure RBAC roles and permissions. |
| Integrations & Coding Patterns | L58-L68 | Using Custom Vision models and APIs in apps: exporting via SDK, running ONNX/TensorFlow in Windows ML/Python, calling classification/detection APIs, and integrating with Azure Storage. |
| Deployment | L69-L73 | Deploying Custom Vision models: copying/backing up projects across regions and exporting models for offline, edge, and mobile (TensorFlow, ONNX, iOS/Android) use. |
| Topic | URL |
|---|---|
| Apply Custom Vision data strategies to improve models | https://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/getting-started-improving-your-classifier |
| Speed up Custom Vision labeling with Smart Labeler | https://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/suggested-tags |
| Topic | URL |
|---|---|
| Plan migration from Custom Vision to alternative services | https://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/migration-options |
| Choose the right Custom Vision domain for your project | https://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/select-domain |
| Topic | URL |
|---|
test cases passed, vs 13 / 22 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.