meeting-prep

Solid

Prepare a 1-page brief for an upcoming meeting by combining calendar context, recent threads with attendees, and relevant docs

AI & Automation 5 stars 0 forks Updated yesterday MIT

Install

View on GitHub

Quality Score: 83/100

Stars 20%
26
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# meeting-prep — Pre-Meeting Brief Produces a one-page markdown brief so you walk into meetings knowing what's going on. ## Output shape ```markdown ## Meeting: {title} **When:** {datetime} · **Duration:** {duration} · **Where:** {location} **Attendees:** {list with titles where known} ### Context - Last topic we discussed: {summary} - Open asks from them: {list} - Open asks from me: {list} ### Likely agenda 1. {item} 2. {item} ### My position / notes {bulleted; pulled from memory if relevant} ### Warnings - {anything they sent recently that suggests a tough topic} ### Quick links - [last email thread]({url}) - [shared doc]({url}) - [previous meeting notes]({memory-link}) ``` ## Procedure 1. **Resolve meeting** from `lookup:`: - "next" → next calendar event in personal calendar - a time → nearest event at that time - a person → next event where that person is an attendee - event id → that exact event 2. **Gather** (parallel): - Last 10 emails with each attendee (last 90 days) - Last Slack DMs / channel mentions with each attendee (last 30 days) - Relevant docs from memory (`/search` with meeting title + attendee names) - Previous meeting notes if exist in memory 3. **Summarize** each thread to 1–2 lines. Extract open asks (things needing response, either direction). 4. **Produce** the brief. Keep under 400 words. Bias for brevity — this is a read-in-60-seconds doc. 5. **Attach** the brief as a Telegram DM reply to the trigger event, or pr...

Details

Author
Guilhermepelido
Repository
Guilhermepelido/hermes-optimization-guide
Created
2 months ago
Last Updated
yesterday
Language
Shell
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category