agentleFS
etrebelsetrebels/claude-code-growth-os/.claude/skills/meeting-prep/SKILL.md

meeting-prep

Skill21 starsChanged 2 months agoMITView on GitHub

Build a pre-meeting briefing — who's in the room, what they care about, your goal, and the questions to ask. Trigger when the user asks to prep for a meeting or call, "what should I know before", or names an upcoming meeting.

53 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use email-digest, meeting-followup and 9 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.
  • QuixiAISkill

    email-digest

    Digest and ingest emails into memory, surfacing important threads and action items

    Also in 3 projects that use this

  • yakatotechSkill

    meeting-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

  • vivy-yiSkill

    social-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

  • MicrosoftSkill

    inbox-triage

    Use this skill whenever the user asks to clean up, triage, declutter, or archive low-value Outlook inbox mail - "clean up my inbox", "triage my mail", "declutter my inbox", "sort out newsletters", "archive old resolved threads", "/inbox-triage" - to group only newsletters, auto-notifications, past-event meeting logistics, resolved threads, and redundant duplicates into reviewable move-proposals presented for per-bucket approval before any message moves. Do not use for reading mail, drafting or sending replies, deleting mail, executing moves without explicit per-bucket approval, or acting on messages from the user's manager, direct reports, active threads, flagged mail, or labelled/HR/Legal/Finance/Security senders.

    Also in 8 projects that use this

  • refly-aiSkill

    zoom

    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

  • QuixiAISkill

    weekly-review

    Review the past week across goals, tasks, calendar, journal, and commitments, then propose the next week

    Also in 10 projects that use this

  • +1 more from QuixiAI

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 49 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before a meeting, build a one-screen brief:

    line 8
  2. Distinctive:

    Calibrated questions: start with What or How — never "why" (which sounds like an accusation), never yes/no (which closes things down).

    line 23
  3. Distinctive:

    If a call is repeatedly held without it, the meeting owner cuts the invite list rather than adding more reminders — an unengaged attendee …

    line 58

“Common” is measured: kept by at least 6 in 10 of the 49 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Meeting Prep (pre-meeting briefing)

Before a meeting, build a one-screen brief:

  1. Who's in the room and what each likely cares about.
  2. Where this sits — pull from ops/pipeline.md and any prior notes: last contact, open threads, commitments outstanding.
  3. Your one goal for the meeting, and the single decision you want out of it.
  4. The questions to ask — labels + calibrated questions (see below).
  5. The one risk or objection to be ready for — name it first, before they raise it.

Pull context from ops/ and the relevant meeting notes; don't invent attendees or history you weren't given.

Asking the right kind of questions (Chris Voss, Never Split the Difference)

The questions decide the meeting. Two moves do most of the work:

  • Label, then ask. Name the thing they're likely feeling before you question it: "It seems like…" / "It sounds like…" Then stop talking and let them respond. A label lowers the guard; the silence pulls out the real answer.
  • Calibrated questions start with What or How — never "why" (which sounds like an accusation), never yes/no (which closes things down). They make the other person do the thinking and hand you the information.

Load 3–5 calibrated questions for the meeting. A reusable set:

  • "What's the hardest part of that for your team right now?"
  • "How does that show up in your week?"
  • "What have you already tried that didn't work the way you hoped?"
  • "What does that cost you today?" (time, rework, decisions made on partial information)
  • "How would you know this had been solved?"
  • "How does a decision like this usually get made on your side?" — surfaces the real process and who else matters
  • "What would need to be true for this to be worth doing?"

Close two ways:

  • A summary they confirm — play their situation back so well they say "that's right." (Not "you're right," which usually means let's wrap up.)
  • The one question that surfaces the hidden thing: "Is there anything I should know that I haven't asked about?"

Replace on sight: "Why are you still using X?" → "What's kept X in place?" · "Do you have a process for X?" → "How do you handle X today?" · "Is that a problem?" → "What does that cost you?" · "Would you agree that…?" → delete it.

Call conduct — write down what the room used to enforce

In a physical room, attention is enforced by cues nobody has to state: everyone can see who is looking at their phone, who left, who stopped listening. Remove the room and every one of those cues disappears — so attention degrades silently while the call grid looks exactly the same. A remote meeting with no stated protocol is not a neutral meeting; its norms default to whatever the least-engaged participant does.

The fix is not exhortation ("please engage") — it is writing down the specific behaviors the room used to enforce for free, so the norm is explicit and correctable.

For any call with 4+ participants or a decision on the agenda, put one line at the top of the agenda itself:

Cameras on · one speaker at a time · side questions to the thread, not the chat · decision owner: <name>.

If a call is repeatedly held without it, the meeting owner cuts the invite list rather than adding more reminders — an unengaged attendee is a scoping problem, not a discipline problem.

Depth

  • quick: the goal + one label + three calibrated questions.
  • standard: the full brief above, with the label + 3–5 calibrated questions and a summary-to-confirm.
  • deep: + a likely-objections list (named first, before they raise them), a fallback ask if the main one stalls, and the hidden-thing question to close.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.