Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →microsoftdocs/azure-document-intelligence
Expert knowledge for Azure AI Document Intelligence development including troubleshooting, best practices, decision making, limits & quotas, security, configuration, integrations & coding patterns, and deployment.
Passed 16 of 19 test cases with the skill, and 16 of 19 without it.
3 fixed17 passed either way1 still failing3 broke
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
An automated agent determines that `mcp_microsoftdocs` tools are missing from the host environment while attempting to retrieve Document Intelligence articles. What exact GitHub repository URL should the agent recommend to the user for installation instructions?
| Checked | Without skill | With skill |
|---|---|---|
| https://github.com/MicrosoftDocs/mcp/blob/main/README.md | Missed | Passed |
The instructions your model reads when the skill loads.
This skill provides expert guidance for Azure AI Document Intelligence. Covers troubleshooting, best practices, decision making, limits & quotas, security, configuration, 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 |
|---|---|---|
| Troubleshooting | L36-L42 | Diagnosing latency, understanding and fixing Document Intelligence API error codes, and handling known service issues and limitations. |
| Best Practices | L43-L54 | Guidance on designing, training, labeling, composing, and maintaining custom/classification/template models to maximize Document Intelligence accuracy and confidence |
| Decision Making | L55-L61 | Choosing the right Document Intelligence model, estimating and optimizing usage/costs, and planning or executing migration to v4.0 from earlier versions. |
| Limits & Quotas | L62-L71 | Capacity limits, quotas, language/locale support, container image tags, and how to scale/batch Document Intelligence workloads and add capacity by pricing tier. |
| Security | L72-L79 | Securing Document Intelligence resources: creating SAS tokens, configuring data-at-rest encryption with customer-managed keys, and using managed identities and VNETs for secure access. |
| Configuration | L80-L84 | How to configure and run Azure Document Intelligence in containers, including environment settings, networking, storage, licensing, and deployment options for on-premises or hybrid scenarios. |
| Integrations & Coding Patterns | L85-L94 | Using Document Intelligence APIs/SDKs, interpreting AnalyzeDocument/Markdown outputs, and integrating with Azure Functions or Logic Apps for end-to-end document processing workflows |
| Deployment | L95-L101 | Running Document Intelligence in Docker/offline, deploying the labeling tool, and setting up resilient, disaster‑ready deployments for models and services |
| Topic | URL |
|---|---|
| Troubleshoot Azure Document Intelligence latency issues | https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/concept/troubleshoot-latency?view=doc-intel-4.0.0 |
| Reference and resolve Document Intelligence API errors | https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/how-to-guides/resolve-errors?view=doc-intel-4.0.0 |
| Handle known issues in Azure Document Intelligence | https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/reference/known-issues?view=doc-intel-4.0.0 |
| Topic | URL |
|---|---|
| Improve Document Intelligence accuracy and confidence | https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/concept/accuracy-confidence?view=doc-intel-4.0.0 |
| Train custom document classification models | https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/how-to-guides/build-a-custom-classifier?view=doc-intel-4.0.0 |
| Build and train Document Intelligence custom models | https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/how-to-guides/build-a-custom-model?view=doc-intel-4.0.0 |
test cases passed, vs 16 / 19 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.