action-item-extractor

作者: microsoft

从会议内容中提取带有负责人、截止日期和优先级的行动项

npx skills add https://github.com/microsoft/work-iq --skill action-item-extractor

Action Item Extractor

Description

Parses Teams meeting chat messages for action-oriented language — commitments, assignments, and deadlines. Cross-references owners against the attendee list and assigns priority levels. Outputs a structured table ready for downstream recipes.

Prerequisites

RequirementDetails
WorkIQ CLIUser profile, meeting details, chat messages (read queries via ask)

Required Inputs

InputTypeDescription
meeting_identifierstringMeeting title, keyword, or "latest"
datestring (optional)Target date (defaults to today)

Execution Steps

Step 1: Retrieve User Profile, Meeting Details, and Attendees

workiq-ask (
  question: "What is my profile including display name and time zone? Also find the meeting matching '<meeting_identifier>' on <date> and list all attendees with their names and email addresses."
)

Extract: displayName, time zone, attendee list with names and emails.

Step 2: Pull Teams Meeting Chat Messages

workiq-ask (
  question: "Get all chat messages from the Teams meeting '<meeting subject>' held on <date>, including sender names and timestamps."
)

Step 3: Parse for Action-Oriented Language

Scan messages for:

  • Explicit assignments: "[name] will...", "AI: [person] to..."
  • Commitments: "I'll handle...", "Let me take care of..."
  • Deadlines: "by Friday", "end of sprint", "before next meeting"
  • Urgency markers: "ASAP", "urgent", "blocker", "critical"

Step 4: Cross-Reference Owners Against Attendee List

Match extracted owner names to attendees[] from Step 1. Flag any unresolved names.

Step 5: Assign Priority

  • P1 (High): Contains urgency markers, blocker language, or executive requests
  • P2 (Medium): Standard commitments with deadlines
  • P3 (Low): Nice-to-haves, "when you get a chance" items

Step 6: Format Action Items Table

#DescriptionOwnerDue DatePriority
1.........P1/P2/P3

Step 7: Output Structured Data

Return action items as structured data, plus inline display for the user.


Error Handling

ErrorSolution
No chat messagesReport "No meeting content found"
Unresolved owner namesList as "[Unresolved: partial name]" for user clarification
No deadlines mentionedMark all due dates as "TBD"

Output

Returns: structured action item list with owners, due dates, and priorities. Usable as input for downstream recipes.

Instructions

This skill is invoked by recipes or orchestration agents — not directly by end users. To invoke it, supply the required inputs and ensure authentication is configured.

  1. Set the meeting identifier: Pass a meeting title keyword (e.g., "sprint planning"), a partial title, or "latest" to target the most recent meeting.
  2. Optionally specify a date: Provide an ISO date string (e.g., "2026-03-03") to scope the calendar lookup. Omit to default to today.
  3. Invoke the skill: Pass meeting_identifier (and optionally date) as inputs. The skill will execute Steps 1–7 automatically.
  4. Consume the output: The structured action item table is returned as data and is also rendered inline for the user.

Examples

Example 1: Extract items from today's sprint planning meeting

{
  "meeting_identifier": "sprint planning",
  "date": "2026-03-03"
}

Output (sample):

#DescriptionOwnerDue DatePriority
1Update API docs with new endpoint schemaFirstname1 Lastname12026-03-07P2
2Fix login blocker bug before releaseFirstname2 Lastname22026-03-04P1
3Review UX mocks when you get a chance[Unresolved: Firstname3]TBDP3

Example 2: Extract items from the latest meeting (no date specified)

{
  "meeting_identifier": "latest"
}

The skill resolves today's date from the user profile time zone, finds the most recently concluded meeting, and parses its chat transcript for action items.


Example 3: Target a specific meeting by keyword on a past date

{
  "meeting_identifier": "Q1 budget review",
  "date": "2026-02-28"
}

The skill searches calendar events on February 28 for a meeting matching "Q1 budget review", fetches its Teams chat, and returns all commitments made — including any flagged with "ASAP" or "before end of quarter" language as P1 items.

来自 microsoft 的更多技能

oss-growth
microsoft
OSS增长黑客角色
agent-framework-azure-ai-py
microsoft
使用Microsoft Agent Framework Python SDK(agent-framework-azure-ai)构建Azure AI Foundry代理。在创建使用AzureAIAgentsProvider的持久化代理、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时使用。涵盖函数工具、结构化输出和多工具代理。
development
airunway-aks-setup
microsoft
在AKS上设置AI Runway——从裸集群到运行模型。涵盖集群验证、控制器安装、GPU评估、提供商设置和首次部署。适用场景:“设置AI Runway”、“接入AKS集群”、“安装AI Runway”、“airunway设置”、“将模型部署到AKS”、“在AKS上进行GPU推理”、“在AKS上配置KAITO”、“在AKS上运行LLM”、“在AKS上使用vLLM”、“在AKS上设置模型服务”、“AI Runway控制器”。
devops
appinsights-instrumentation
microsoft
使用Azure Application Insights对Web应用进行插桩的指南。提供遥测模式、SDK设置和配置参考。适用场景:如何对应用进行插桩、App Insights SDK、遥测模式、什么是App Insights、Application Insights指南、插桩示例、APM最佳实践。
devops
applicationinsights-web-ts
microsoft
使用Application Insights JavaScript SDK(@microsoft/applicationinsights-web)为浏览器/Web应用添加检测。用于真实用户监控(RUM)——页面视图、点击、AJAX/fetch依赖项、异常、自定义事件,以及与后端OpenTelemetry追踪关联的浏览器端GenAI代理追踪。涵盖SDK加载器脚本和npm设置、框架扩展(React、React Native、Angular)、点击分析、遥测初始化器,以及从浏览器发出的代理/工具/模型跨度所遵循的OTel GenAI语义约定。
devops
azure-ai-anomalydetector-java
microsoft
使用适用于 Java 的 Azure AI 异常检测器 SDK 构建异常检测应用程序。在实现单变量/多变量异常检测、时间序列分析或 AI 驱动的监控时使用。
development
azure-ai-language-conversations-py
microsoft
使用azure-ai-language-conversations Python SDK实现对话语言理解(CLU)。当使用ConversationAnalysisClient分析对话意图和实体、构建NLP功能或将语言理解集成到应用程序中时使用。
development
azure-ai-ml-py
microsoft
Azure Machine Learning SDK v2 for Python。用于机器学习工作区、作业、模型、数据集、计算资源和管道。 触发词:“azure-ai-ml”、“MLClient”、“工作区”、“模型注册表”、“训练作业”、“数据集”。
development