boards-backlog-summary

作者: microsoft

獲取團隊的需求層級待辦清單(Product Backlog Items 與 Bugs),篩選為指派給目前使用者的 Active 項目。顯示父子階層…

npx skills add https://github.com/microsoft/azure-devops-skills --skill boards-backlog-summary

Get team backlog summary

This skill retrieves the team's Requirements-level backlog, filters to Active items assigned to the current user, enriches them with parent and child work item details, and displays them sorted by priority.

Project selection

  • If the user provides a project name in their request (for example, "for Contoso"), use that project directly and do not call core_list_projects.
  • If the project name is not provided, ask the user once to provide it.
  • If the project name is still not provided after asking once, call core_list_projects to return a list of projects the user can choose from.
  • Do not continue if no project has been provided or selected.

Team selection

  • If the user provides a team name, use it directly and do not call core_list_project_teams.
  • If the team name is not provided, ask the user once to provide it.
  • If the team name is still not provided after asking once, call core_list_project_teams for the selected project so the user can pick a team.
  • Do not continue if no team has been provided or selected.

Tools

Use Azure DevOps MCP Server tools for all interactions with Azure DevOps.

  • core_list_projects: Get the list of projects the user can choose from.
  • core_list_project_teams: Get the list of teams for a project.
  • wit_backlog (action: list_work_items): Get the work items on the team's backlog at a specific backlog level.
  • wit_work_item (action: get_batch): Get work item details in batch by their IDs. Use this to fetch fields and relations for backlog items, their parents, and their children in as few calls as possible.

Steps

  1. Resolve project and team using the rules above.

  2. Call wit_backlog with action list_work_items for the resolved project and team, using backlog level Microsoft.RequirementCategory (the Requirements / Product Backlog Items level).

  3. From the returned work items, filter to items that meet all of the following criteria:

    • System.State = Active
    • System.AssignedTo matches the current user
    • System.WorkItemType is one of: Product Backlog Item, Bug
  4. If no items match the filter, display a message stating there are no active backlog items assigned to the current user for this team and stop.

  5. Call wit_work_item with action get_batch for all filtered item IDs with expand=relations and the following fields:

    • System.Id
    • System.Title
    • System.State
    • System.AssignedTo
    • System.WorkItemType
    • System.ChangedDate
    • System.IterationPath
    • Microsoft.VSTS.Common.Priority
    • System.Parent
  6. From the relations of each item, collect all parent IDs (System.LinkTypes.Hierarchy-Reverse) and child IDs (System.LinkTypes.Hierarchy-Forward). Call wit_work_item with action get_batch once with the combined set of those IDs (excluding any IDs already fetched) to get their System.Id, System.Title, and System.State.

  7. Display the results as described in the Display results section below.

Display results

Sort all items by Microsoft.VSTS.Common.Priority ascending (Priority 1 first). For each item, display:


{ID} — {Title}

FieldValue
State{System.State}
Priority{Microsoft.VSTS.Common.Priority}
Changed Date{System.ChangedDate formatted as MM/DD/YYYY}
Iteration{last segment of System.IterationPath}
Work Item Type{System.WorkItemType}

Parent:

  • If a parent exists: {ParentID} {Parent Title}
  • If no parent exists: (none)

Child Items:

If there are child items, display them in a table:

IDTitleState
{ChildID}{Child Title}{Child State}

If there are no child items, display: (none)


After all items are listed, display a summary line:

Showing {N} active backlog item(s) assigned to you on team {team name} in project {project name}.

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