teams-notification-triage
$
npx mdskill add openai/plugins/teams-notification-triageConvert Teams activity into prioritized task lists.
- Transforms unread chats and recent threads into actionable queues.
- Depends on get_profile, list_chats, and message history APIs.
- Prioritizes unread signals before expanding to recent channel activity.
- Delivers a filtered priority queue based on user-specified scope.
SKILL.md
.github/skills/teams-notification-triageView on GitHub ↗
--- name: teams-notification-triage description: Triage recent Microsoft Teams activity into a priority queue or task list for the user. --- # Teams Notification Triage Use this skill to produce a priority queue or task list from recent Teams activity. This is a proxy workflow over the available Teams signals, not a native notification-feed view. ## Related Skills | Workflow | Skill | | --- | --- | | Turn confirmed follow-ups into Microsoft Planner tasks | [../teams-planner-task-management/SKILL.md](../teams-planner-task-management/SKILL.md) | ## Start Here - If the user provided a time window, use it and anchor it to explicit local dates. - Treat this as best-effort triage over unread chats, recent threads, and recent message-level mentions. - Do not claim access to unread channel markers or a native Teams notification feed. ## Workflow 1. Resolve the current user with `get_profile` so you can match message-level mentions to the signed-in user ID when needed. 2. If the user provided channels, chats, teams, or people, keep the triage inside that scope. 3. With no explicit scope, prioritize: - `list_chats(unread_only=True)` for unread chat signal - `list_recent_threads` for recent channel and chat activity 4. Expand only the containers needed to determine what matters: - unread chats first via `list_chat_messages` - then recent channels or chats via `list_channel_messages` or `list_chat_messages` 5. For mention checks, inspect message-history results and use `TeamsMessageResult.mentions`. Do not use Teams search results as the source of truth for mention detection. 6. Prioritize messages likely needing a reply, creating a follow-up, or changing the user's plan. 7. If some channel activity is unreadable or artifact-only, say so and keep it out of the main triage buckets. 8. If the user asks you to track tasks from triage, show the proposed task list first or route to the Planner skill; do not silently create tasks while presenting an attention queue. ## Formatting Format the triage as: ```md *Teams Attention Triage — YYYY-MM-DD* *Summary:* <1–2 line overview of what most likely needs attention> *Tasks for you* - ... *Worth skimming* - ... *Can ignore for now* - ... *Notes* - <coverage limits, proxy caveats, or unread-channel limitation> ``` - Keep the triage compact; aim for 3–15 bullets total. - Treat *Tasks for you* as the primary section whenever the goal is a personal action list. - Make *Tasks for you* a triage bucket, not proof that a Planner task exists. Say "Planner task" only after reading or writing Planner. - Include *Can ignore for now* only when the user explicitly asked to filter noise. - Preserve exact chat, team, and channel names. - Use *Notes* to explain proxy behavior, coverage gaps, or the lack of channel unread markers.
More from openai/plugins
- 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|