azure-health-bot

The saved excerpt is a snapshot from review. The external source remains the complete and most current version.

---
name: azure-health-bot
description: Expert knowledge for Azure Health Bot development including best practices, security, configuration, and integrations & coding patterns. Use when wiring Teams/SMS/WhatsApp channels, embedding web chat, calling external APIs, configuring handoff, or enforcing consent, and other Azure Health Bot related development tasks. Not for Azure AI Bot Service (use azure-bot-service), Azure Communication Services (use azure-communication-services), Azure Functions (use azure-functions).
compatibility: Requires network access. Uses mcp_microsoftdocs:microsoft_docs_fetch or fetch_webpage to retrieve documentation.
metadata:
  generated_at: "2026-08-02"
  generator: "docs2skills/1.0.0"
---
# Azure Health Bot Skill

This skill provides expert guidance for Azure Health Bot. Covers best practices, security, configuration, and integrations & coding patterns. It combines local quick-reference content with remote documentation fetching capabilities.

## How to Use This Skill

> **IMPORTANT for Agent**: Use the **Category Index** below to locate relevant sections. For categories with line ranges (e.g., `L35-L120`), use `read_file` with the specified lines. For categories with file links (e.g., `[security.md](security.md)`), use `read_file` on the linked reference file

> **IMPORTANT for Agent**: If `metadata.generated_at` is more than 3 months old, suggest the user pull the latest version from the repository. If `mcp_microsoftdocs` tools are not available, suggest the user install it: [Installation Guide](https://github.com/MicrosoftDocs/mcp/blob/main/README.md)

This skill requires **network access** to fetch documentation content:
- **Preferred**: Use `mcp_microsoftdocs:microsoft_docs_fetch` with query string `from=learn-agent-skill`. Returns Markdown.
- **Fallback**: Use `fetch_webpage` with query string `from=learn-agent-skill&accept=text/markdown`. Returns Markdown.

## Category Index

| Category | Lines | Description |
|----------|-------|-------------|
| Best Practices | L32-L36 | Guidance on designing robust error-handling flows in Azure Health Bot scenarios, including detecting failures, user-friendly recovery paths, and safe handling of clinical conversation errors. |
| Security | L37-L49 | Configuring security, privacy, and compliance: user consent, data access/deletion, encryption keys, abuse safeguards, authentication, secrets management, and portal permissions for Healthcare bots/agents. |
| Configuration | L50-L67 | Configuring bot behavior and conversations: welcome/help messages, feedback, interruptions, human/Teams handoff, terms links, and managing scenarios, variables, cards, and versions. |
| Integrations & Coding Patterns | L68-L89 | Connecting Health Bot/Agent to channels (Teams, SMS, WhatsApp, Facebook), embedding web chat/voice, calling external APIs/OpenAPI, telemetry, auth, management APIs, and proactive scenario invocation |

### Best Practices
| Topic | URL |
|-------|-----|
| Design error handling flows in healthcare bot scenarios | https://learn.microsoft.com/en-us/azure/health-bot/errorhandling |

### Security
| Topic | URL |
|-------|-----|
| Configure end-user consent and compliance in healthcare bots | https://learn.microsoft.com/en-us/azure/health-bot/bot_docs/consent |
| Enable end-user deletion of personal data in healthcare bots | https://learn.microsoft.com/en-us/azure/health-bot/bot_docs/deleting_data |
| Allow users to view and export personal data from healthcare bots | https://learn.microsoft.com/en-us/azure/health-bot/bot_docs/viewing_data |
| Configure customer-managed encryption keys for healthcare bots | https://learn.microsoft.com/en-us/azure/health-bot/cmk |
| Monitor and manage abuse in generative healthcare scenarios | https://learn.microsoft.com/en-us/azure/health-bot/copilot/abuse-monitoring |
| Configure health safeguards for generative healthcare agents | https://learn.microsoft.com/en-us/azure/health-bot/copilot/safeguards |
| Configure end-user authent