outlook-email-inbox-triage

$npx mdskill add openai/plugins/outlook-email-inbox-triage

Triage Outlook inbox into actionable buckets like urgent, needs reply soon, waiting, and FYI using connected data.

  • Helps users manage email overload by categorizing messages for prioritization and response tracking.
  • Integrates with Outlook data and depends on core Outlook Email skill for read and write operations.
  • Uses message listing or searching to filter noise and assess urgency before reading full bodies.
  • Presents results as categorized lists, with optional actions like marking read or moving emails upon request.

SKILL.md

.github/skills/outlook-email-inbox-triageView on GitHub ↗
---
name: outlook-email-inbox-triage
description: Triage an Outlook inbox into actionable buckets such as urgent, needs reply soon, waiting, and FYI using connected Outlook data. Use when the user asks to triage the inbox, rank what needs attention, find what still needs a reply, or separate important mail from noise.
---

# Outlook Email Inbox Triage

## Overview

Use this skill for direct Outlook inbox-triage requests. Build on the core Outlook Email skill at [../outlook-email/SKILL.md](../outlook-email/SKILL.md), especially its read-first and write-safety guidance.

## Relevant Actions

- Use `list_messages` for recent or unread inbox passes where a bounded mailbox slice is enough.
- Use `search_messages` when the triage request includes lexical search terms, sender filters, attachment constraints, or date scoping.
- Use `fetch_message` or `fetch_messages_batch` only when snippets are not enough to classify urgency or reply-needed state.
- Use `mark_email_read_state`, `move_email`, or `set_message_categories` only if the user explicitly asks you to act on the triage results.

## Workflow

1. Default to the inbox and a clear timeframe unless the user asks for a broader audit.
2. Build a shortlist with `list_messages` or `search_messages` before reading full bodies.
3. Exclude obvious noise early if newsletters, calendar churn, or automated alerts dominate the first pass.
4. Expand only the messages whose urgency, ownership, or reply-needed status is unclear from the first pass.
5. Return explicit buckets such as `Urgent`, `Needs reply soon`, `Waiting`, and `FYI`.
6. If the user asks to clean up the mailbox after triage, keep the classification and the mailbox actions clearly separated.

## Bucket Heuristics

- `Urgent`: direct asks with time pressure, blockers, escalation risk, or operational consequences if ignored.
- `Needs reply soon`: direct asks without same-day urgency, active threads where the user is likely the next responder, or follow-ups that will go stale soon.
- `Waiting`: threads where the user already replied or where the current blocker belongs to someone else.
- `FYI`: announcements, newsletters, calendar noise, transactional mail, and items that do not currently require action.

## Output

- Include sender, subject, why each item is in its bucket, and the likely next action.
- State timeframe, search scope, and confidence.
- Treat reply-needed as an inference, not a guaranteed state.
- Avoid claiming the inbox is fully triaged if you only checked a narrow slice.

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|