teams-daily-digest
$
npx mdskill add openai/plugins/teams-daily-digestCreates a daily Microsoft Teams digest from specified chats, channels, or teams upon user request for a recap.
- Helps users summarize today's Teams activity from selected sources.
- Integrates with Microsoft Teams APIs for resolving and reading messages.
- Uses explicit user input to scope content and avoids guessing channels.
- Presents results as a digest anchored to the user's local timezone.
SKILL.md
.github/skills/teams-daily-digestView on GitHub ↗
--- name: teams-daily-digest description: Create a daily Microsoft Teams digest from selected chats, channels, or workstreams. Use when the user asks for a daily Teams recap or summary of today's Teams activity. --- # Teams Daily Digest Use this skill to produce a daily digest of important Teams activity from selected chats, channels, or teams. ## Related Skills | Workflow | Skill | | --- | --- | | Create or update Microsoft Planner tasks from digest follow-ups | [../teams-planner-task-management/SKILL.md](../teams-planner-task-management/SKILL.md) | ## Start Here - If the user did not name chats, channels, teams, or topics, ask first before making Teams tool calls. - Do not guess the user's "main channels." - For requests like "today" or "this morning," anchor the digest to explicit local dates in the user's timezone. ## Workflow 1. Confirm the scope: named chats, named channels, named teams, or named topics. 2. Resolve the exact containers: - channels: `resolve_team`, `resolve_channel` - existing chats: `resolve_chat` 3. Prefer direct container reads over broad search: - channels: `list_channel_messages` - chats: `list_chat_messages` 4. If the user named a team but not a channel, use `list_recent_threads` scoped to that team to discover recent channel threads, then expand only the highest-signal channels with direct reads. 5. If the user named topics but not exact containers, use `list_recent_threads` as a shortlist and expand only chats or channels whose recent activity plausibly matches the topic. 6. Prioritize decisions, blockers, asks, ownership changes, timeline shifts, and notable replies. 7. Group the digest by channel, chat, or workstream, depending on what makes the summary easiest to scan. 8. If the digest identifies follow-ups and the user wants them tracked, route to the Planner skill. Do not create Planner tasks as a side effect of a digest request. ## Formatting Format the digest as: ```md *Teams Daily Digest — YYYY-MM-DD* *Scope:* <containers + time window + coverage note> *Summary:* <1–2 line overview of volume and key signals> *Details* *<group 1>* - ... - ... *<group 2>* - ... - ... *Needs attention* - ... *Planner candidates* - <optional follow-ups that could become tasks, only when task tracking is relevant> *Notes* - <gaps, sparse results, or caveats> ``` - Keep the digest compact; aim for 4–10 bullets total across all sections. - Preserve exact team, channel, and chat names. - Include *Needs attention* only for items requiring user action, decisions, or input. - Include *Planner candidates* only when the user asked for tasks or the Teams activity contains concrete follow-ups worth turning into tasks. - Add a coverage note when the scope is broad, partly unreadable, or based on recent-thread discovery rather than exhaustive reads.
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|