azure-health-bot — Claude Code skill: what it does, how to install
Hands the agent a reference on Azure Health Bot: auth providers, Teams and web chat channels, telemetry, voice safeguards. Live documentation pages come from Microsoft Learn.
CC-BY-4.0 167 installs ★ 818 updated 2026-10-25
npx skills add MicrosoftDocs/Agent-Skills --skill azure-health-bot -a claude-codeWhat azure-health-bot does
The skill ships a SKILL.md with a category index. Error handling covers failure detection in healthcare scenarios and recovery paths that stay safe for the user. Security spans authentication providers, end-user consent, personal data deletion and export, customer-managed encryption keys, secrets and endpoints, abuse monitoring for generative scenarios, and health safeguards. Configuration covers welcome messages, help behaviour, cancellation and interruptions, human and Teams handoff, conversation cards, instance variables, scenario snapshots.
Integrations are the fourth block: Direct Line, Facebook Messenger and Workplace, Dynamics Omnichannel, Teams, embedded web chat, triggering scenarios from APIs or JavaScript, Application Insights telemetry, and voice. The agent picks a category, reads the line range with read_file or opens the linked reference file, then fetches the actual page through mcp_microsoftdocs:microsoft_docs_fetch.
Network access is required. Without the docs MCP server the skill falls back to fetch_webpage, and if neither is available only the local notes remain — it will ask you to install mcp_microsoftdocs. Scope is Azure Health Bot alone; Azure AI Bot Service and Azure Communication Services have their own skills.
What it helps with
- Set up end-user sign-in and consent for a healthcare bot
- Connect a Teams channel and hand a conversation to a person
- Turn on App Insights telemetry for bot scenarios
- Keep Health Bot work apart from Azure AI Bot Service
- Handle a user request to delete personal data
Example prompts for the agent
- Configure authentication providers for our Health Bot and walk through the consent flow.
- Connect the bot to Microsoft Teams and set up handoff to a live agent.
- Enable Application Insights telemetry for the Health Bot scenarios.
How to install azure-health-bot
1Skills CLI (Vercel)
npx skills add MicrosoftDocs/Agent-Skills --skill azure-health-bot -a claude-code2Manually: put the files in place
~/.claude/skills/azure-health-bot/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/azure-health-bot/
1Skills CLI (Vercel)
npx skills add MicrosoftDocs/Agent-Skills --skill azure-health-bot -a codex2Manually: put the files in place
.agents/skills/azure-health-bot/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add MicrosoftDocs/Agent-Skills --skill azure-health-bot -a cursor2Manually: put the files in place
.cursor/skills/azure-health-bot/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install MicrosoftDocs/Agent-Skills skills/azure-health-bot2Manually: put the files in place
.github/skills/azure-health-bot/SKILL.md1Skills CLI (Vercel)
npx skills add MicrosoftDocs/Agent-Skills --skill azure-health-bot -a gemini-cli2Platform CLI
gemini skills install https://github.com/MicrosoftDocs/Agent-Skills --path skills/azure-health-botManually: put the files in place
.devin/skills/azure-health-bot/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add MicrosoftDocs/Agent-Skills --skill azure-health-bot -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about azure-health-bot
How do I install azure-health-bot in Claude Code?
Run npx skills add MicrosoftDocs/Agent-Skills --skill azure-health-bot -a claude-code. The skill file lands at ~/.claude/skills/azure-health-bot/SKILL.md.
What does azure-health-bot do?
It gives the agent a map of the Azure Health Bot docs: authentication, scenario configuration, channels, telemetry, safeguards. The agent reads the relevant section and pulls the matching page from Microsoft Learn.
What does the skill need to work?
Network access plus the mcp_microsoftdocs:microsoft_docs_fetch tool, with fetch_webpage as the fallback. Without either it cannot reach the documentation pages.
Source text
SKILL.md · CC-BY-4.0
--- name: azure-health-bot description: Expert knowledge for Azure Health Bot development including best practices, security, configuration, and integrations & coding patterns. Use when configuring Health Bot auth, Teams/web chat, channel integrations, App Insights telemetry, or voice safeguards, 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). compatibility: Requires network access. Uses mcp_microsoftdocs:microsoft_docs_fetch or fetch_webpage to retrieve documentation. metadata: generated_at: "2026-10-25" 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-L50 | Security, compliance, and privacy for Health Bot: auth providers, end-user auth/consent, data access/deletion, encryption keys, secrets/keys, abuse monitoring, safeguards, and portal permissions | | Configuration | L51-L68 | 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 | L69-L89 | Integrating Azure Health Bot/Agent with channels (Teams, SMS, WhatsApp, Facebook), embedding web chat, calling/triggering scenarios via APIs/JS, telemetry with App Insights, and enabling voice and clinical safeguards. | ### 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 | |-------|-----| | Set up authentication providers for healthcare agent integrations | https://learn.microsoft.com/en-us/azure/health-bot/authentication_providers | | 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 authentication for Healthcare agent service | https://learn.microsoft.com/en-us/azure/health-bot/end-user-authentication | | Manage secrets, keys, and endpoints in Healthcare agent service | https://learn.microsoft.com/en-us/azure/health-bot/keys | | Manage portal user permissions with Microsoft Entra ID | https://learn.microsoft.com/en-us/azure/health-bot/portal-users | ### Configuration | Topic | URL | |-------|-----| | Configure automatic welcome messages in healthcare bots | https://learn.microsoft.com/en-us/azure/health-bot/automatic_welcome_howto | | Configure scenario cancellation behavior in healthcare agents | https://learn.microsoft.com/en-us/azure/health-bot/bot_docs/cancelling | | Configure end-user feedback collection in healthcare bots | https://learn.microsoft.com/en-us/azure/health-bot/bot_docs/feedback | | Configure help command behavior in healthcare agents | https://learn.microsoft.com/en-us/azure/health-bot/bot_docs/help | | Configure interruptible scenarios in healthcare conversations | https://learn.microsoft.com/en-us/azure/health-bot/bot_docs/interruptions | | Configure terms and privacy links for healthcare agents | https://learn.microsoft.com/en-us/azure/health-bot/bot_docs/terms | | Configure interrupting scenarios for healthcare conversations | https://learn.microsoft.com/en-us/azure/health-bot/configuring_interruptions | | Configure human handoff in healthcare agent service | https://learn.microsoft.com/en-us/azure/health-bot/handoff | | Configure Microsoft Teams handoff for healthcare bots | https://learn.microsoft.com/en-us/azure/health-bot/handoff-teams | | Configure and use conversation cards in healthcare bots | https://learn.microsoft.com/en-us/azure/health-bot/scenario-authoring/adding-cards | | Use and manage instance variables in healthcare scenarios | https://learn.microsoft.com/en-us/azure/health-bot/scenario-authoring/instance-variables | | Manage and organize healthcare bot scenarios in the portal | https://learn.microsoft.com/en-us/azure/health-bot/scenario-authoring/scenario_management | | Use scenario snapshots to manage healthcare bot versions | https://learn.microsoft.com/en-us/azure/health-bot/scenario-authoring/snapshots | | Use resources and static variables in healthcare bot scenarios | https://learn.microsoft.com/en-us/azure/health-bot/tenant-resources | ### Integrations & Coding Patterns | Topic | URL | |-------|-----| | Configure Direct Line channel for healthcare agent service | https://learn.microsoft.com/en-us/azure/health-bot/channels/directline | | Connect healthcare bot to Facebook Messenger and Workplace | https://learn.microsoft.com/en-us/azure/health-bot/channels/facebook | | Integrate healthcare agent service with Dynamics Omnichannel | https://learn.microsoft.com/en-us/azure/health-bot/channels/oc_channel | | Connect healthcare agent service to Microsoft Teams | https://learn.microsoft.com/en-us/azure/health-bot/channels/teams | | Connect healthcare bot to Twilio SMS channel | https://learn.microsoft.com/en-us/azure/health-bot/channels/twilio | | Embed healthcare agent web chat into web applications | https://learn.microsoft.com/en-us/azure/health-bot/channels/webchat | | Configure WhatsApp via Twilio for healthcare agent service | https://learn.microsoft.com/en-us/azure/health-bot/channels/whatsapp | | Integrate healthcare bot telemetry with Application Insights | https://learn.microsoft.com/en-us/azure/health-bot/custom_telemetry | | Configure healthcare agent data connections to external APIs | https://learn.microsoft.com/en-us/azure/health-bot/data_connection | | Use Clinical Safeguards API with Azure Health Agent Service | https://learn.microsoft.com/en-us/azure/health-bot/integrations/clinicalsafeguardsapi | | Use healthcare agent service management API for automation | https://learn.microsoft.com/en-us/azure/health-bot/integrations/managementapi | | Invoke healthcare bot scenarios proactively across channels | https://learn.microsoft.com/en-us/azure/health-bot/integrations/proactive | | Invoke healthcare bot scenarios from client-side JavaScript | https://learn.microsoft.com/en-us/azure/health-bot/integrations/programmatic_invocation | | Enable voice interactions in healthcare web chat and apps | https://learn.microsoft.com/en-us/azure/health-bot/integrations/voice | | Extend healthcare scenarios with advanced integration elements | https://learn.microsoft.com/en-us/azure/health-bot/scenario-authoring/advanced_functionality | | Extend healthcare scenarios with advanced integration elements | https://learn.microsoft.com/en-us/azure/health-bot/scenario-authoring/advanced_functionality | | Extend healthcare scenarios with advanced integration elements | https://learn.microsoft.com/en-us/azure/health-bot/scenario-authoring/advanced_functionality | | Extend healthcare scenarios with advanced integration elements | https://learn.microsoft.com/en-us/azure/health-bot/scenario-authoring/advanced_functionality |
© MicrosoftDocs · CC-BY-4.0 · MicrosoftDocs/Agent-Skills