meeting-prep
Skill5 starsChanged 6 months agoMITView on GitHub
Produces a one-page brief before a meeting — who's attending, what's been discussed before, what to expect, what to ask. Pulls from calendar, email threads with the attendees, any prior meeting notes, and project context. Use when the user asks to prep for a meeting, get ready for a call, or brief me on an upcoming meeting.
We split this skill into the rules it gives an agent
12 rules. 0 are common, 10 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 47 edited versions we read keep these.
10
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 12
Read context/about-me.md — to frame the meeting from the user's side
- Very specific: line 13
Read context/preferences.md — format defaults
- Distinctive: line 14
Ask the user which meeting if it's not obvious.
- Distinctive: line 15
Check the project folder for any prior notes on this attendee or topic
- Distinctive: line 38
Search the project folder for any prior mention of the person or the company
- Distinctive: line 39
Read prior meeting-prep or meeting-debrief files for this person if they exist
- Distinctive: line 45
Do not include the entire email thread.
- Distinctive: line 46
Do not invent background on the attendees.
- Distinctive: line 47
Do not write generic questions.
- Distinctive: line 48
Do not skip the red flags section even if you don't think there are any.
- Distinctive: line 78
Recurring 1-1s: If this is a recurring meeting with the same person, lean hard on "where we left off." Pull from the last 2–3 …
- Distinctive: line 81
Pitch/sales meetings: Add a sixth section: "Objections to be ready for" — based on prior thread and common patterns.
“Common” is measured: kept by at least 6 in 10 of the 47 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Meeting Prep
Walk into every meeting knowing who you're talking to and why. Two minutes of reading instead of 20 minutes of panicky tab-opening.
Before starting
- Read
context/about-me.md— to frame the meeting from the user's side - Read
context/preferences.md— format defaults - Ask the user which meeting if it's not obvious. Calendar title is best; date + attendee name works.
- Check the project folder for any prior notes on this attendee or topic
What to produce
A markdown file saved to /output/meeting-prep-{YYYY-MM-DD}-{attendee-or-topic}.md with five sections:
- Who's in the room — attendee(s), their role, their company, anything notable from past interactions. One paragraph per person.
- Where we left off — the last time this person or topic came up. Pull from email threads, prior meeting notes, any project docs. Summarize. This is the most valuable section — it's the context the user forgot.
- What's likely on their mind — your read of what the attendee is probably coming to discuss, based on the thread, the calendar invite, any recent context. Hedge when you're guessing. Say "likely" not "will."
- What to ask or propose — 3 sharp questions or proposals for the user to drive the conversation with. Specific to this person and this context, not generic "what are your goals."
- Red flags / things to not miss — if there are open questions, pending decisions, or sensitive topics, list them. Include any prior commitments the user made to this person that haven't been fulfilled.
Inputs
- The calendar event (required — title, attendees, description)
- Email threads with the attendees in the last 90 days (via Gmail connector)
- Any prior meeting notes in the project folder or
/output/ - Any relevant project docs the user has referenced
How it works
- Get the meeting from the calendar — parse title, attendees, time, any linked docs
- For each external attendee, search email for the last 90 days — pull the most recent substantive thread
- Search the project folder for any prior mention of the person or the company
- Read prior meeting-prep or meeting-debrief files for this person if they exist
- Synthesize the five sections — keep each one tight
- Save the file, tell the user one-line what's most important ("Heads up — she emailed last week with an unresolved question about pricing. I've flagged it in red flags.")
What not to do
- Do not include the entire email thread. Summarize.
- Do not invent background on the attendees. If you don't know something, don't make it up.
- Do not write generic questions. "What are your priorities?" is useless. "You mentioned last quarter you were rebuilding ops — where did that land?" is useful.
- Do not skip the red flags section even if you don't think there are any. Say "no open items" if that's the case — but check first.
Example output structure
# Meeting Prep — 2026-04-18 — Sarah Chen (Northwind)
## Who's in the room
**Sarah Chen** — VP of Operations at Northwind. A 200-person B2B SaaS, mid-market workflow tools. You met her at SaaStr last fall. She owns ops, RevOps, and half of finance. Direct communicator, impatient with filler.
## Where we left off
Last substantive thread was 2026-03-22. She asked for references on the implementation timeline for a team her size. You sent two — she replied "thanks, reviewing" and went quiet. No follow-up from either side.
Prior call (2026-02-15) — she said budget approval was "likely by end of Q1" and she'd come back with a signed SOW or a clear no. Q1 ended; no update.
## What's likely on their mind
Either she's ready to sign and wants to walk through implementation, *or* something internal blocked it and this call is a re-evaluation. The fact that she requested the call (not you) tilts toward the first.
## What to ask or propose
1. "Where did the Q1 budget conversation land?" — open with the elephant.
2. "If we sign this quarter, what's your internal rollout timeline?" — test for real momentum.
3. "What's one thing that would make this a no for you?" — surfaces objections early.
## Red flags
- You promised to send an implementation timeline customized to their team size. You sent references instead. She may ask.
- Legal review was pending on your side last time. Check with Alex before the call.Customization notes
- Recurring 1-1s. If this is a recurring meeting with the same person, lean hard on "where we left off." Pull from the last 2–3 meeting-debrief files for this person.
- First meetings. Section 2 ("where we left off") becomes "what we know about them" — LinkedIn, company, any public mentions.
- Internal meetings. Skip section 3 ("what's likely on their mind") if it's a routine internal — it adds noise.
- Pitch/sales meetings. Add a sixth section: "Objections to be ready for" — based on prior thread and common patterns.
Other versions51 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 51
- openai/plugins★ 7.4ksame name
- gnekt/My-Brain-Is-Full-Crew★ 3.9ksame name
- ShenSeanChen/waku-agent★ 2ksame name
- QuixiAI/agi-memory★ 617same name
- QuixiAI/Hexis★ 617same name
- davekilleen/Dex★ 509same name
- glebis/claude-skills★ 404same name
- sonichi/sutando★ 396same name
- explorium-ai/gtm-skills★ 346same name
- mgonto/executive-assistant-skills★ 118same name
41 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
Used alongsideProjects with it also use email-digest, social-listening and 7 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
QuixiAISkillemail-digest
Digest and ingest emails into memory, surfacing important threads and action items
Also in 3 projects that use this
vivy-yiSkillsocial-listening
Use when needing to understand audience needs, monitor brand mentions, track competitor activities, discover trends, or gather market intelligence from Xiaohongshu conversations
Also in 3 projects that use this
yakatotechSkillmeeting-followup
Create meeting minutes and follow-up email from meeting notes in one workflow. Execute all post-meeting tasks at once
Also in 3 projects that use this
refly-aiSkillzoom
Integrate with Zoom for video meetings. Use when you need to: (1) schedule Zoom meetings, (2) create instant meetings, or (3) manage meeting details and invitations programmatically.
Also in 3 projects that use this
vijpatel7Skillcold-outreach
Write highly effective cold emails and LinkedIn messages to recruiters, hiring managers, founders, and engineers at target companies. Based on Ben Lang's proven cold outreach framework (Next Play). Use when the user wants to: (1) write a cold email to someone at a company they want to work for, (2) craft LinkedIn messages or InMail to recruiters or hiring managers, (3) reach out about unadvertised positions, (4) follow up on outreach or applications, (5) network with founders or executives for job opportunities, (6) prepare an outreach campaign to multiple companies. Triggers on: cold email, outreach, reach out to, contact recruiter, email founder, write to hiring manager, job email, networking email, LinkedIn message, InMail.
Also in 4 projects that use this
QuixiAISkillweekly-review
Review the past week across goals, tasks, calendar, journal, and commitments, then propose the next week
Also in 10 projects that use this
In this repository6 other files it gives its agents.
- doc-summarizeSkill
- inbox-triageSkill
- meeting-debriefSkill
- morning-briefSkill
- research-briefSkill
- weekly-reportSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

