outlook-calendar-group-scheduler
Find and rank good meeting times for several people using Outlook Calendar data. Use when the user wants to schedule a meeting, compare candidate slots across attendees, find the best compromise time, or add a room/resource check after narrowing the attendee-compatible options.
- License 许可
- MIT
- 最近更新
- 2026-07-19
- Stars
- ★ 1
- Forks
- 1
01 前言 Front Matter
- name
- outlook-calendar-group-scheduler
- description
- Find and rank good meeting times for several people using Outlook Calendar data. Use when the user wants to schedule a meeting, compare candidate slots across attendees, find the best compromise time, or add a room/resource check after narrowing the attendee-compatible options.
02 资源文件 1
- 参考文档agents/openai.yaml274 B
03 SKILL.md 正文
Outlook Calendar Group Scheduler
Use this skill when the scheduling problem is the task.
Relevant Actions
- Use
get_schedulefor attendee and room/resource free-busy windows once you know the concrete schedule identifiers. - Use
find_available_slotswhen the problem is mostly about the user's own calendar and buffered openings. - Use
search_eventsorlist_eventswhen you need conflict context before ranking options. - Use
create_eventonly after the winning slot and attendee set are settled.
Outlook Product Framing
- Treat free/busy visibility, work hours, and work location as first-class scheduling evidence when full event detail is unavailable.
- Treat attendee response state and organizer logistics as part of scheduling, not just the final event body.
- When rooms or resources are visible, treat them as Outlook-style scheduling constraints rather than a separate "room finder" workflow.
Workflow
- Ground the scheduling problem first: date window, duration, timezone, required attendees, optional attendees, and any hard constraints such as "this week", "afternoons only", or "avoid lunch".
- If the scheduling window is ambiguous, assess the meeting stakes before choosing a default search window. For relatively high-stakes meetings, go back to the user and suggest tightening the timeline, for example to the next week. For lower-stakes or more casual group scheduling, default to a near-term search such as the next 1 to 3 weeks.
- Normalize the request into explicit candidate windows before ranking anything.
- Rank slots, do not enumerate everything. Optimize for a short list of strong options.
- Treat
BusyandOut of Officeas harder constraints thanTentativeorWorking Elsewhereunless the user says otherwise. - Prefer slots that minimize conflict cost, fit within work hours, and avoid avoidable hybrid-work friction such as forcing an in-office room meeting onto remote-heavy attendees.
- When rooms, resources, or building context are available, prefer slots that keep the meeting logistically coherent instead of treating time as the only variable.
- If shared-calendar visibility is partial, say when a recommendation is based on free/busy signals rather than full event detail.
Ranking Heuristics
- Favor required-attendee fit over optional-attendee fit.
- Favor slots that avoid very early or very late local times for distributed attendees.
- Favor slots that stay inside work hours and avoid consuming the only large free block in someone's day unless the meeting is clearly important.
- Favor a small number of high-confidence options over a long weak list.
- When two slots are similar, prefer the one that causes less calendar fragmentation.
- When one attendee is only
TentativeorWorking Elsewhere, describe that as a softer constraint instead of silently treating it as unavailable. - When one option aligns better with attendees' work locations or room logistics, explain that advantage explicitly.
Output Conventions
- Return 2-4 candidate slots by default.
- For each slot, say why it works and who, if anyone, would be inconvenienced.
- If there is no clean option, say what tradeoff the best slot is making.
04 同仓库更多 Skills
Zotero
Use Zotero Desktop from Codex to enable/probe the local API, search a local Zotero library, list items/collections/tags, export BibTeX, insert citation keys into LaTeX or Markdown drafts, read indexed full text when requested, and import BibTeX/RIS records into Zotero through the connector server. Use when the user mentions Zotero, citations, references.bib, BibTeX export, local Zotero API, localhost:23119, or adding citations from a Zotero library.
zoom-apps-sdk
Use when using Apps SDK.
youtube
Obtain accurate, timestamped YouTube video transcripts (preferring manual captions over auto-generated) as the primary deliverable, then derive summaries, key claims, or notes from that transcript. Use when the user provides a YouTube URL (or video ID) and wants the transcript, a faithful summary, key claims with attribution, timestamped notes, or "what does this video actually say". The skill is transcript-first: never substitute metadata, title, description, or search snippets for the spoken content. Triggers: "youtube transcript", "get the transcript of this video", "summarize this youtube video", "what did they say in https://youtube.com/...", "key claims from this talk".
yeet
Publish local changes to GitHub by confirming scope, committing intentionally, pushing the branch, and opening a draft PR through the GitHub app from this plugin, with `gh` used only as a fallback where connector coverage is insufficient.
x-post-creator
Create X-ready post threads and co-located story packages from the active conversation or referenced project material. Use when the user says turn this into an X-post, /x-post, make this into an X thread, or wants plain-language social posts with supporting images saved to docs/x-posts/[story-name]/.
x-api
Search, read, and write X posts through the local X API MCP server (the same backend used by the Codex x-api skill). Use for searching X/x.com, reading threads and replies, creating lists, staging/publishing posts for @alltheputs, finding high-visibility reply targets for research outreach, ingesting public context, or any request that mentions /x-api or "search X".