AgentStack
SKILL verified MIT Self-run

Meeting Prep

skill-etrebels-claude-code-growth-os-meeting-prep · by etrebels

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.

No reviews yet
0 installs
11 views
0.0% view→install

Install

$ agentstack add skill-etrebels-claude-code-growth-os-meeting-prep

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Meeting Prep? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

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.

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.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.