outlook-email-task-extraction

$npx mdskill add openai/plugins/outlook-email-task-extraction

Extracts tasks, deadlines, and owners from Outlook emails to create actionable lists for users.

  • Helps users identify action items and commitments from email threads or searches.
  • Integrates with Outlook APIs for message retrieval, attachment handling, and categorization.
  • Focuses on explicit asks, due dates, and ownership while merging duplicate task records.
  • Presents results as organized task lists, distinguishing user-owned items from others' responsibilities.

SKILL.md

.github/skills/outlook-email-task-extractionView on GitHub ↗
---
name: outlook-email-task-extraction
description: Extract action items, deadlines, commitments, and owners from Outlook email threads and mailbox searches. Use when the user wants a task list from one thread, several related messages, or a mailbox slice, including who owes what and when.
---

# Outlook Email Task Extraction

## Overview

Use this skill when the user wants work pulled out of email rather than a general summary. Focus on who owns the next move, what the due date is, what is blocked, and what still needs confirmation.

## Relevant Actions

- Use `search_messages` or `list_messages` to define the message set in scope.
- Use `fetch_message` or `fetch_messages_batch` when body text is needed to resolve owners, due dates, or cross-message dependencies.
- Use `list_attachments` or `fetch_attachment` when the ask or deadline lives in an attached file rather than the email body.
- Use `set_message_categories` only if the user explicitly wants tasks or commitments tagged back into Outlook after extraction.

## Workflow

1. Define the scope clearly: one thread, one sender, one topic, unread mail, or a bounded date window.
2. Extract explicit asks, commitments, deadlines, blockers, approvals, and follow-ups from the messages in scope.
3. Separate user-owned tasks from tasks owned by other people.
4. Distinguish explicit deadlines from inferred urgency.
5. When several messages refer to the same task, merge them into one task record with the freshest status.
6. If the user wants follow-up help after extraction, keep that as a second step so the task list stays auditable.

## Output

- Use a task-oriented format with `Task`, `Owner`, `Due`, `Status`, and `Evidence` when possible.
- Quote or paraphrase the message that establishes the task owner or due date.
- Call out ambiguity explicitly when ownership or due date is implied rather than stated.
- If there are no concrete tasks, say that clearly instead of forcing a weak extraction.

More from openai/plugins

SkillDescription
accessibility-and-inclusive-visualizationMake data visualizations accessible and inclusive. Use when the user needs chart or diagram accessibility guidance, text alternatives for complex visuals, color and contrast review, keyboard support, reduced-motion behavior for animation or parallax, or an accessibility QA workflow for exported figures, UML-like diagrams, and dashboards.
agent-browserBrowser automation CLI for AI agents. Use when the user needs to interact with websites, verify dev server output, test web apps, navigate pages, fill forms, click buttons, take screenshots, extract data, or automate any browser task. Also triggers when a dev server starts so you can verify it visually.
agent-browser-verifyAutomated browser verification for dev servers. Triggers when a dev server starts to run a visual gut-check with agent-browser — verifies the page loads, checks for console errors, validates key UI elements, and reports pass/fail before continuing.
agents-sdkBuild AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, or chat applications. Covers Agent class, state management, callable RPC, Workflows integration, and React hooks. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.
ai-elementsAI Elements component library guidance — pre-built React components for AI interfaces built on shadcn/ui. Use when building chat UIs, message displays, tool call rendering, streaming responses, reasoning panels, or any AI-native interface with the AI SDK.
ai-gatewayVercel AI Gateway expert guidance. Use when configuring model routing, provider failover, cost tracking, or managing multiple AI providers through a unified API.
ai-generation-persistenceAI generation persistence patterns — unique IDs, addressable URLs, database storage, and cost tracking for every LLM generation
ai-sdkVercel AI SDK expert guidance. Use when building AI-powered features — chat interfaces, text generation, structured output, tool calling, agents, MCP integration, streaming, embeddings, reranking, image generation, or working with any LLM provider.
aiq-deploy|
aiq-research|