teams-channel-summarization
$
npx mdskill add openai/plugins/teams-channel-summarizationSummarizes Microsoft Teams channel activity into concise recaps or follow-ups for specified time windows.
- Helps users quickly review and condense recent discussions in Teams channels or conversations.
- Integrates with Microsoft Teams APIs to fetch and process messages and replies.
- Uses user-provided time windows or defaults to recent bounded reads for message selection.
- Presents results as a concise summary or a Teams-ready follow-up message.
SKILL.md
.github/skills/teams-channel-summarizationView on GitHub ↗
--- name: teams-channel-summarization description: Summarize activity from one Microsoft Teams channel or one scoped Teams conversation and return a concise recap or post-ready follow-up. --- # Teams Channel Summarization Use this skill to summarize one Teams channel, using a requested time window when provided or a safe recent read otherwise, and optionally turn the result into a Teams-ready follow-up. ## Related Skills | Workflow | Skill | | --- | --- | | Draft or send the final Teams follow-up | [../teams-messages/SKILL.md](../teams-messages/SKILL.md) | ## Start Here - If the user did not name a team or channel, ask which team and channel to review. - If the user provided a relative window such as "today" or "this week," anchor it to explicit local dates in the user's timezone. - If the user did not provide a window, default to a recent bounded read rather than silently claiming full-history coverage. ## Workflow 1. Resolve the team and channel with `resolve_team` and `resolve_channel`. 2. If the user gave a time window, call `list_channel_messages` for that window. 3. If the user did not give a window, start with `list_channel_messages(top=50)` and top-level messages only. 4. Expand replies only when they materially affect the summary: - use `list_channel_messages(... include_replies=True)` for a small bounded pass when thread outcomes matter - use `fetch` for exact wording or a specific message the user points to 5. Consolidate the activity into a concise summary grouped by topic, decision, blocker, or workstream. 6. If the user wants the result delivered in Teams, return a post-ready channel summary and post it when delivery into Teams is the requested action. ## Formatting Format a concise summary as: ```md *Teams Channel Summary — <team> / <channel>* *Window:* <explicit date range or recent snapshot> *Overview:* <1–2 sentence summary of the main themes and biggest updates> *Topic: <topic 1>* - ... - ... *Topic: <topic 2>* - ... - ... *Notes* - <gaps, unresolved threads, or coverage caveats> ``` - Group the summary into 2–4 topics when possible. - Keep each topic to 1–5 bullets. - Start each bullet with the main update. Add an owner or next step only when it is clear from the channel. - If the user asked for a recent snapshot rather than full history, label it explicitly as a snapshot. - If the channel contains only unreadable placeholders or artifacts, say that directly instead of presenting it as confirmed human activity.
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|