outlook-calendar-free-up-time

$npx mdskill add openai/plugins/outlook-calendar-free-up-time

Analyzes Outlook Calendar to propose minimal changes that create meaningful uninterrupted free time blocks.

  • Helps users clear schedules, make room for focus time, or create longer uninterrupted blocks.
  • Integrates with Outlook Calendar actions like list_events, fetch_event, find_available_slots, get_schedule, and update_event.
  • Prioritizes movable meetings, optimizes for contiguous blocks, and reduces fragmentation across the day.
  • Presents proposals grounded in calendar data, focusing on the smallest edit set for effective results.

SKILL.md

.github/skills/outlook-calendar-free-up-timeView on GitHub ↗
---
name: outlook-calendar-free-up-time
description: Find ways to open up meaningful free time in Outlook Calendar. Use when the user wants to clear part of their schedule, make room for focus time, create a longer uninterrupted block, or see the smallest set of calendar changes that would give time back.
---

# Outlook Calendar Free Up Time

Use this skill when the goal is to create time, not just inspect time.

## Relevant Actions

- Use `list_events` to map the current fragmentation and identify movable candidates.
- Use `fetch_event` when one candidate needs a closer read before proposing a change.
- Use `find_available_slots` to verify whether a better block exists on the user's own calendar.
- Use `get_schedule` before moving attendee-heavy meetings when cross-attendee availability matters.
- Use `update_event` only after the proposal is grounded and the intended event is unambiguous.

## Workflow

1. Start by identifying the target: today, tomorrow, this afternoon, a specific day, or a broader window.
2. Optimize for contiguous free blocks, not raw free-minute totals.
3. Identify which meetings are likely fixed and which are more movable before proposing changes.
4. Look for the smallest edit set that creates a meaningful uninterrupted block.
5. Prefer solutions that reduce fragmentation across the rest of the day, not just one local gap.
6. Treat `Tentative`, `Free`, self-created placeholders, and lightly attended internal holds as lower-cost candidates than hard external meetings, accepted commitments, or `Out of Office` blocks.
7. When work hours or work location are relevant, prefer openings that produce a useful block inside the user's actual workday.
8. If no clean block exists, show the best partial win and what tradeoff it requires.

## Prioritization Heuristics

- Protect hard anchors such as external meetings, major reviews, commute buffers, and stable lunch windows.
- Move lower-cost meetings first, such as tentative holds, lightweight internal syncs, or self-created placeholders.
- When two meetings are similarly movable, prefer moving a 1:1 over a larger group meeting because it creates less attendee thrash.
- Favor one or two coherent shifts over a chain of many tiny moves.
- Prefer creating one useful block over scattering a few small openings.
- Preserve existing Teams links and attendee lists unless the user wants to change them.
- If a meeting has weak attendee commitment, interpret that in context rather than as a blanket signal. Far-future weak commitment is normal; imminent weak commitment is a much stronger sign that the meeting may be movable or unstable.

## Output Conventions

- Show the before-and-after effect of the proposal.
- Name the block created and the minimum meetings that would need to move.
- If suggesting multiple options, keep them short and explain the tradeoff for each.

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|