create-flow

作者: microsoft

引導式流程建立精靈。當使用者想以互動方式建立新流程時使用。

npx skills add https://github.com/microsoft/power-platform-skills --skill create-flow

Guided Flow Creation Wizard

Walk the user through creating a Power Automate flow step by step.

Tools

This skill uses the FlowAgent MCP tools. Clients surface them with a client-specific prefix — mcp__flowagent__<tool> (Claude Code) or flowagent-<tool> (Copilot CLI) — so they're referred to by bare name below (e.g. create_flow). Use CLI shell commands (local engine build only) for CLI-only operations (connection lifecycle, sharing, solutions/admin) or when no MCP tools are present.

Steps

  1. Gather requirements: Ask what the flow should do. Identify triggers, actions, connectors.

  2. Select environment: Call list_environments (use query to filter). Let user pick or auto-select.

  3. Check for templates: Call list_templates. If a template matches (approval, digest, webhook, etc.), offer to use scaffold_flow as a starting point.

  4. Discover connectors: For each connector, call get_connector with query to find the operation, then get_operation_details for exact parameters. Never guess parameter names or types.

  5. Verify connections: Call list_connections filtered by each connector. Confirm Connected status.

  6. Resolve dynamic values: For params with dynamicValues/dynamicTree annotations, call invoke_operation to get actual values (Teams channels, SharePoint sites, etc.).

  7. Review with user: Present the flow design. Use AskUserQuestion to confirm trigger, actions, and connections before creating.

  8. Generate definition: Build following all rules:

    • Always declare $authentication (SecureObject) and $connections (Object) parameters
    • Use correct action type: OpenApiConnection or OpenApiConnectionWebhook (from get_operation_details)
    • Do NOT include authentication in action inputs
    • Use Embedded source in connection references
    • HTTP Request triggers require Premium; prefer Button kind
  9. Validate: Call validate_flow (and optionally preflight_flow) to pre-check. For expressions, look up syntax with get_expression_help.

  10. Create: Call create_flow in Stopped state. Report ID and name.

  11. Optionally publish: Ask if user wants to enable. If yes, call publish_flow. For later one-off tweaks, use edit_flow (surgical) rather than resending the whole definition.

來自 microsoft 的更多技能

oss-growth
microsoft
開源增長駭客角色
agent-framework-azure-ai-py
microsoft
使用Microsoft Agent Framework Python SDK(agent-framework-azure-ai)构建Azure AI Foundry代理。适用于使用AzureAIAgentsProvider创建持久化代理、使用托管工具(代码解释器、文件搜索、网络搜索)、集成MCP服务器、管理对话线程或实现流式响应。涵盖函数工具、结构化输出和多工具代理。
development
airunway-aks-setup
microsoft
在AKS上設定AI Runway——從裸叢集到執行模型。涵蓋叢集驗證、控制器安裝、GPU評估、供應商設定及首次部署。時機:「設定AI Runway」、「上線AKS叢集」、「安裝AI Runway」、「airunway設定」、「部署模型至AKS」、「在AKS上進行GPU推論」、「在AKS上設定KAITO」、「在AKS上執行LLM」、「在AKS上使用vLLM」、「在AKS上設定模型服務」、「AI Runway控制器」。
devops
appinsights-instrumentation
microsoft
使用Azure Application Insights檢測Web應用程式的指南。提供遙測模式、SDK設定與組態參考。適用時機:如何檢測應用程式、App Insights SDK、遙測模式、什麼是App Insights、Application Insights指南、檢測範例、APM最佳實踐。
devops
applicationinsights-web-ts
microsoft
使用Application Insights JavaScript SDK(@microsoft/applicationinsights-web)為瀏覽器/Web應用程式進行檢測。適用於真實使用者監控(RUM)——頁面檢視、點擊、AJAX/fetch依賴、例外、自訂事件,以及與後端OpenTelemetry追蹤關聯的瀏覽器端GenAI代理追蹤。涵蓋SDK載入器指令碼與npm設定、框架擴充(React、React Native、Angular)、點擊分析、遙測初始化器,以及從瀏覽器發出的代理/工具/模型span的OTel GenAI語意慣例。
devops
azure-ai-anomalydetector-java
microsoft
使用適用於 Java 的 Azure AI 異常偵測器 SDK 建置異常偵測應用程式。在實作單變量/多變量異常偵測、時間序列分析或 AI 驅動監控時使用。
development
azure-ai-language-conversations-py
microsoft
使用 azure-ai-language-conversations Python SDK 實作對話語言理解(CLU)。當使用 ConversationAnalysisClient 分析對話意圖與實體、建置 NLP 功能,或將語言理解整合至應用程式時使用。
development
azure-ai-ml-py
microsoft
Azure Machine Learning SDK v2 for Python。用於機器學習工作區、作業、模型、資料集、計算資源與管線。 觸發詞:「azure-ai-ml」、「MLClient」、「workspace」、「model registry」、「training jobs」、「datasets」。
development