Walk in already knowing what the room actually wants.
The Tool you run the night before a meeting that matters. It works out what each attendee actually wants underneath the agenda, the question you should pre-answer, where the conversation will leave the agenda, and what success looks like for you specifically.
The agenda is what the meeting says it's about. It's rarely what the meeting is about. Every attendee walks in with something they want that they haven't written down, and the meeting goes well or badly depending on whether those wants get met, ignored, or collided. Most people prepare for the stated agenda and get ambushed by the real one. Meeting Pre-Read spends fifteen minutes working out what each person actually wants, to be seen to be right, to avoid blame, to protect a budget, to slow a decision, to test you. It names the one question that, if asked and fumbled, costs you the meeting, the one you're hoping won't come up, and makes you draft the answer now rather than improvise it under pressure. It maps where the conversation will pivot off-agenda and what you do when it does. And it defines success concretely, not 'a good meeting' but what has to be true when you walk out. It won't script the meeting. It makes sure you're not the only person in the room who hasn't thought about what's really going on.
What it actually does.
You have a board call tomorrow. Agenda: 'Q3 review and Q4 planning.' Q3 missed by 20%. Meeting Pre-Read reads the room: the lead investor says they want to understand Q3 but really wants to know whether you see the miss clearly and whether it's a blip or a pattern, they're testing your grip more than the numbers. The independent member wants to be seen asking the hard question for the record. Your co-founder wants the blame not to land on their function. The question to pre-answer: 'is this a one-off or a trend', drafted now, naming the cause and the leading indicator that says it's contained. The likely pivot: the call leaves 'review the past' and becomes 'do we trust the Q4 number', so don't defend Q3, move straight to what makes Q4 credible. Success: the board believes the miss is understood and the forecast is credible, not just that the call felt smooth. The one thing to do differently: open with the miss, named plainly, before anyone asks.
- ✦Founders heading into board, investor, or client meetings with tension under the surface
- ✦Operators in negotiations
- ✦Anyone who's left a meeting realizing the real conversation was the one nobody put on the agenda
- →meeting-pre-read.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →meeting-pre-read-skill.md: plain markdown. Works in ChatGPT Custom GPTs, Gemini, Claude Projects, agent system prompts, anywhere
- →A README inside the zip with install steps for Claude, ChatGPT, Gemini, and the API
What it does with a real question.
Tomorrow at 10am I meet our largest customer's COO, their head of procurement and our own account lead. The stated agenda is 'renewal review'. The customer has been quiet for six weeks, a competitor recently visited their office, and our contract renews in 70 days.
Read the silence as the agenda. "Renewal review" is the cover story. Six weeks of quiet plus a competitor visit means this customer has already started a comparison, and tomorrow is where they decide whether to tell you or just collect leverage.
The COO probably wants cover: a defensible reason to either stay or switch, and a sense of whether you're a partner or a vendor. Procurement wants a lever, so expect price to surface early and often. Your account lead wants the relationship protected, which can make them soft on the hard question. Talk to them beforehand.
The question to pre-answer is "What would make us stay?" or its colder cousin, "Why shouldn't we move?" Draft that answer tonight: two specific outcomes you've delivered, one thing you're changing, and a concrete offer for the next twelve months. If you improvise it in the room, you'll sound either defensive or desperate.
The likely pivot comes when procurement steers from review to price. Don't follow it. Let it run briefly, then return to value and what the COO is trying to achieve.
Success is not a warm meeting. It's walking out knowing whether a competitor is in play, who is championing them, and what a second conversation looks like.
One move: open by naming the quiet. Say "we haven't spoken as much lately, and I'd rather ask directly where things stand." Naming it first signals confidence and makes the real conversation possible.
The full Tool runs the whole procedure and writes the complete deliverable, not this excerpt.
Written by claude-sonnet-5-5 with this Tool loaded, 2026-10-11. Checked automatically for length and for copied framework text.
No subscription · free updates within v1.x
Works as a Claude Skill (.zip) and as a plain .md for ChatGPT, Gemini & every LLM
Delivered to your email within 60 seconds · Secured by Stripe
Price includes UK VAT where applicable
Before you buy.
How is this different from just asking Claude directly?
Ask Claude to 'help me prep for a meeting' and you get a tidied-up version of the agenda. Meeting Pre-Read works out what each attendee actually wants underneath it, names the one question that costs you the meeting if you fumble it and makes you draft the answer now, maps where the conversation will pivot off-agenda, and defines what concretely has to be true when you walk out. It prepares you for the real meeting, not the stated one.
Will this work with ChatGPT, Gemini, and other LLMs?
Yes. You get a native Claude Skill (.zip) that auto-invokes in Claude, plus a plain .md you can paste into a ChatGPT Custom GPT, a Gemini system prompt, or any LLM. The procedure travels with the file.
Can I share this with my team?
It's licensed for your own personal and professional use. The output it produces is yours to circulate. To put the Tool itself in the hands of a whole team, email hello@authority.md about team licensing.
What if it doesn't work for me?
If the file hasn't been delivered, or arrives defective or empty, we refund in full: see our refund policy.