feat(azure-sdk-python): add azure-ai-language-conversations skill

.github/plugins/azure-sdk-python/skills/azure-ai-language-conversations-py/SKILL.md

@@ -0,0 +1,56 @@
+# Azure AI Language Conversations for Python
+
+## System Prompt
+You are an expert Python developer specializing in Azure AI Services and Natural Language Processing.
+Your task is to help users implement Conversational Language Understanding (CLU) using the `azure-ai-language-conversations` SDK.
+
+When responding to requests about Azure AI Language Conversations:
+1. Always use the latest version of the `azure-ai-language-conversations` SDK.
+2. Emphasize the use of `ConversationAnalysisClient` with `AzureKeyCredential`.
+3. Provide clear code examples demonstrating how to structure the conversation payload.
+4. Handle exceptions properly.
+
+## Best Practices
+- Use environment variables for the endpoint, API key, project name, and deployment name.
+- Always use context managers (`with client:`) to ensure proper resource handling.
+- Clearly map the `participantId` and `id` in the `conversationItem` payload.
+
+## Examples
+
+### Basic Conversation Analysis
+```python
+import os
+from azure.core.credentials import AzureKeyCredential
+from azure.ai.language.conversations import ConversationAnalysisClient
+
+endpoint = os.environ["AZURE_CONVERSATIONS_ENDPOINT"]
+key = os.environ["AZURE_CONVERSATIONS_KEY"]
+project_name = os.environ["AZURE_CONVERSATIONS_PROJECT"]
+deployment_name = os.environ["AZURE_CONVERSATIONS_DEPLOYMENT"]
+
+client = ConversationAnalysisClient(endpoint, AzureKeyCredential(key))
+
+with client:
+    query = "Send an email to Carol about the tomorrow's meeting"
+    result = client.analyze_conversation(
+        task={
+            "kind": "Conversation",
+            "analysisInput": {
+                "conversationItem": {
+                    "participantId": "1",
+                    "id": "1",
+                    "modality": "text",
+                    "language": "en",
+                    "text": query
+                },
+                "isLoggingEnabled": False
+            },
+            "parameters": {
+                "projectName": project_name,
+                "deploymentName": deployment_name,
+                "verbose": True
+            }
+        }
+    )
+
+    print(f"Top intent: {result['result']['prediction']['topIntent']}")

.github/plugins/azure-sdk-python/skills/azure-ai-language-conversations-py/references/acceptance-criteria.md

@@ -0,0 +1,16 @@
+# Acceptance Criteria
+
+## Authentication and Setup
+- [ ] MUST use `AzureKeyCredential` from `azure.core.credentials` for authentication.
+- [ ] MUST initialize `ConversationAnalysisClient` correctly with an endpoint and credential.
+- [ ] MUST NOT hardcode API keys or endpoints in the code examples.
+
+## Payload Construction
+- [ ] MUST properly define the `task` dictionary with `"kind": "Conversation"`.
+- [ ] MUST include a correctly structured `analysisInput` with `conversationItem` details (id, participantId, modality, text).
+- [ ] MUST include required `parameters` (`projectName` and `deploymentName`).
+
+## API Usage and Extraction
+- [ ] MUST demonstrate calling `analyze_conversation`.
+- [ ] MUST show how to correctly parse the response dictionary to extract the `topIntent` or entities.
+- [ ] MUST use a context manager (`with client:`) for the client instance.