Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →microsoftdocs/azure-language-service
Expert knowledge for Azure AI Language development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment.
Passed 9 of 15 test cases with the skill, and 14 of 15 without it.
2 fixed13 passed either way0 still failing10 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.
When fetching remote Azure AI Language documentation pages from learn.microsoft.com for an agent workflow using documentation tools, what tracking query parameter should be attached to the request URL?
| Checked | Without skill | With skill |
|---|---|---|
| Includes the query parameter from=learn-agent-skill in the request | Missed | Passed |
The instructions your model reads when the skill loads.
This skill provides expert guidance for Azure AI Language. Covers troubleshooting, best practices, decision making, architecture & design patterns, 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 | L37-L42 | Diagnosing and fixing common issues in Azure Language custom NER and conversational question answering (CQA), including model errors, configuration problems, and troubleshooting workflows. |
| Best Practices | L43-L53 | Best practices for designing and authoring CLU, custom NER, PII, and CQA projects, including data prep, schemas, lifecycles, chitchat personas, and document formatting. |
| Decision Making | L54-L63 | Guides for choosing regions and app types, planning CQA solutions, and deciding or executing migrations from LUIS, QnA Maker, Text Analytics, and Language Studio to Azure Language/Fountry. |
| Architecture & Design Patterns | L64-L71 | Designing and implementing regional failover and high-availability patterns for CLU, custom NER, custom text classification, and orchestration workflow models in Azure AI Language. |
| Limits & Quotas | L72-L95 | Limits, quotas, languages, and model lifecycles for Azure Language features (CLU, NER, text classification, CQA, health), including data size, rate, throughput, and container constraints. |
| Security | L96-L107 | Securing Azure Language and CQA: encryption at rest (including CMK), RBAC, managed identities, SAS tokens, network isolation/Private Link, and secure deployment/data access configuration. |
| Configuration | L108-L124 | Configuring Azure AI Language features: CLU fine-tuning, containers, custom/health NER, orchestration None intent, CQA scoring/telemetry, FHIR output, and related project/skill settings. |
| Integrations & Coding Patterns | L125-L144 | How to call Azure Language/TA/health/CLU/CQA APIs and SDKs for NER, entity linking, key phrases, language detection, sentiment, PII redaction, relations, and orchestration workflows. |
| Deployment | L145-L155 | Guides for deploying and running custom language/NER/CQA/sentiment/health models across regions, on-prem via Docker containers, and moving projects between environments. |
| Topic | URL |
|---|---|
| Resolve common issues with custom NER in Azure Language | https://learn.microsoft.com/en-us/azure/ai-services/language-service/custom-named-entity-recognition/faq |
| Troubleshoot common CQA issues and errors | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/how-to/troubleshooting |
| Topic | URL |
|---|---|
| Apply CLU project authoring best practices | https://learn.microsoft.com/en-us/azure/ai-services/language-service/conversational-language-understanding/concepts/best-practices |
| Adapt PII detection to custom domain terminology | https://learn.microsoft.com/en-us/azure/ai-services/language-service/personally-identifiable-information/how-to/adapt-to-domain-pii |
| Implement CQA project best practices | https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/concepts/best-practices |
test cases passed, vs 14 / 15 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.