一键导入
spark-recipe-topic-timeline
Build a chronological narrative for a topic by interleaving meeting transcript excerpts and email thread summaries across a time range.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Build a chronological narrative for a topic by interleaving meeting transcript excerpts and email thread summaries across a time range.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use the Spark MCP extension to access and act on the user's Spark email data - list emails, search by topic, read threads, check calendar events, find availability, look up contacts, view team info, draft messages (from scratch or saved templates), send drafts, share drafts with teammates, post team comments, triage threads, create/update/delete calendar events and manage attendees, and manage contacts. Use when the user asks about their emails, calendar, contacts, meetings, scheduling, or wants to send, reply, archive, snooze, assign, comment, categorize, or schedule.
Executive assistant persona for Spark. Morning briefings, draft replies, schedule management, and contact lookup.
Founder / CEO persona for Spark. High-volume triage, aggressive delegation, cross-team oversight, and selective engagement.
Freelancer / solo operator persona for Spark. Multi-client management, invoice follow-ups, availability, and quick responses.
Meeting manager persona for Spark. Meeting preparation, transcript review, follow-up drafts, and scheduling.
Project manager persona for Spark. Project thread tracking, stakeholder updates, action item extraction, and cross-team coordination.
| name | spark-recipe-topic-timeline |
| description | Build a chronological narrative for a topic by interleaving meeting transcript excerpts and email thread summaries across a time range. |
| metadata | {"version":"1.0.0","requires":{"skills":["spark"],"accessLevel":"read-only"}} |
For a given project or topic, build a unified chronological narrative by interleaving meeting discussions and email threads. Useful for catching up, briefing someone new, or preparing a status update.
Prerequisite: Read the spark base skill for tool reference and filter syntax.
Access level required: read-only.
Ask the user for:
meetings { "filter": "subject:topic-keyword newer_than:30d" }
If the subject filter misses relevant meetings, broaden:
meetings { "filter": "newer_than:30d" }
For each relevant meeting, read the summary:
meeting { "meeting_id": "<id>" }
Pull full detail only for meetings where the topic was a major agenda item:
meeting { "meeting_id": "<id>", "transcript": true, "notes": true }
Record: date, participants, and the key points related to the topic.
search { "query": "topic keyword" }
For threads that are clearly relevant, read the full conversation:
thread { "message_id": "<id>" }
If there are specific people associated with the topic, also pull their threads:
emails { "filter": "from:person@co.com subject:keyword newer_than:30d" }
Record: date of each message, participants, and the substance.
Combine all entries (meetings and emails) and sort by date. For each entry:
Layer on editorial notes:
Start with a one-paragraph executive summary of where the topic stands now, then present the full timeline oldest-to-newest. End with:
search is relevance-ranked and returns full bodies — it's the best starting point for email discovery.meeting's transcript for meetings where you need exact quotes or attribution.recipe-decision-tracker — use that recipe when you only need the decision points, and this one when you need the full narrative.