Sales Discovery Call Toolkit: MEDDIC Scorecard, SPIN Question Prep and Mutual Action Plan, AI Skill for Claude & ChatGPT, B2B Sales

Discovery Call Co-Pilot is an AI skill for Claude and ChatGPT, made for sales professionals. Before the call: a brief sized to your slot, with SPIN-sequenced questions. After: paste messy notes, get a MEDDIC scorecard with evidence, every gap with the question that closes it, and a mutual action plan with dates.

Instant download. Works on the free tier. No coding. Walk in prepared. Walk out knowing if the deal is real.

WHAT IS AN AI SKILL?
Think of it as a trained assistant you add to Claude or ChatGPT. It is a small folder of files: the step-by-step method the AI must follow, the templates it fills in, the checks it runs on itself, and a worked example. You load it once (about a minute), then talk to the AI in plain English the way you would brief a colleague. Instead of a generic chat answer, you get the finished piece of work as a real file you can print, send or open in Excel. No coding, no software to install, nothing to configure. It runs inside your own Claude or ChatGPT account.

THE PROBLEM IT SOLVES
You came off the call energised. They loved the demo, they laughed at your joke, they said “this is exactly what we need.” You marked it qualified.

Then it died in procurement, or the real decision-maker appeared in week six and had never heard of you, or “we're just going to hold off until next quarter” arrived by email and never thawed.

ABOUT THE EXAMPLES BELOW
The figures and names come from the built-in demo: Sam Torres, an Austin B2B seller working a real pipeline and one live enterprise deal. Type "demo" after setup and you watch the same run happen in front of you before you type a single real number.

WHAT IT DOES (6 JOBS, ONE SKILL)
1. Prep the call
Tell it how long the call is and it sizes the brief: 15 minutes gets 4 questions, 30 gets 8, 45–60 gets the full 10–12. The opener changes with the motion too, so an inbound call asks “why now?” before anything else.

2. Brief the meeting with the signer
Meeting the CFO, the founder, the person who actually signs? That's a different call, not a shorter one: 60 seconds of context, three questions, the champion's number put up for correction, and a dated ask.

3. Score the deal
Paste your messy notes. Six MEDDIC letters out of ten, each with the evidence quoted back at you, blanks scored zero and flagged. Paste a transcript instead and it measures your talk time against the 60–70%-prospect target.

4. Build the mutual action plan
Four columns — step, date, owner, what it unblocks — worked backwards from the date the prospect named, with tasks on both sides and the two rows sellers always leave out: who signs on what date, and the kickoff.

5. Rescue an exposed deal
A verdict of At risk fires the 7-day recovery plan: three dated actions, ending with the checkpoint said out loud. No meeting with the buyer on the calendar by day 7 and the deal goes back to being a lead.

6. Track it across calls
Second call on the same account? Hand it the prior scorecard and it diffs the deal letter by letter, with a trajectory: improving, flat, or decaying. A flat second call is itself the finding.

WHAT YOU GET
• Brief sized to the call: 15 min → 4 questions, 30 → 8, 45–60 → 10–12
• MEDDIC scorecard — six letters, scored with evidence
• Mutual action plan: step, date, owner, and who signs

Everything leaves in a form you can forward, file, or bring to a pipeline review:
• The pre-call brief, and the one-page call sheet you keep open live
• The exec brief for the call with the person who signs
• The MEDDIC scorecard — six letters, scored with quoted evidence
• The gap list, and the question that closes each gap
• The Mutual Action Plan, dated, with owners on both sides
• A follow-up email in your voice, mirroring their words

YOUR FIRST FIVE MINUTES (copy-paste any of these)
› Prep me for a 30-minute call with [company] tomorrow.
› Just the call sheet — one page, questions only.
› Here are my notes from today's call. Score the deal.
› Build the mutual action plan and my follow-up email.
› demo — watch it score a call that felt great.

HOW TO SET IT UP (about a minute)
1. Download the zip and unzip it. Inside: a START-HERE file, INSTALL steps for Claude, and CHATGPT-SETUP for ChatGPT.
2. Claude app: Settings → Capabilities → Skills → Upload skill (or add the files to a Project). Claude Code: drop the folder into ~/.claude/skills/. ChatGPT: follow CHATGPT-SETUP (copy-paste, about two minutes).
3. Type "demo" to watch the skill run on a built-in example. Then give it your own details in plain English.

WHO MADE THIS
The Skill Mastery builds AI skills for working professionals: photographers, filmmakers, creators, marketers and sales teams. We don't start from what AI can do. We start from how the job is actually done, the methods the trade already trusts (here: MEDDIC qualification, SPIN questioning and pipeline math with age decay), the numbers that have to be right, and the mistakes that cost real money. Then we engineer the skill so the AI follows those rules every single time, and we test it the way a buyer would use it: on the built-in demo, on a cold scenario it has never seen, and in a currency other than our own. Every skill ships with a demo mode, a self-check, and a plain list of what it can't do.

WHY NOT JUST ASK THE CHATBOT?
• It scores from evidence, not vibes. Every letter's score quotes the words that earned it. If the prospect never mentioned how they decide, that letter is a zero — visibly, with the gap named. A general chatbot fills the silence with something plausible.

• Every gap arrives with its fix. Any letter scored 3 or below gets the exact question that closes it, plus a way to get the answer by email instead of another meeting: put your arithmetic in the follow-up and invite the correction.

• It builds the plan they correct. The mutual action plan is what the top Decision Process band actually asks for. It works backwards from their go-live date, asks whether legal or procurement is involved, and goes out as a draft to fix rather than approve.

WHAT IT WON'T DO (read this before buying)
• It scores the deal from what you heard. It can't attend the call, and it won't invent an answer to a question you never asked.
• MEDDIC is a qualification framework, not a crystal ball. A high score means a well-qualified deal, not a guaranteed one.
• Research is built from what you provide plus general knowledge. Anything it can't verify is marked [ASK ON CALL] rather than asserted.

FAQ
Q: How is this different from just asking Claude or ChatGPT?
A: A chatbot will summarise your notes and tell you it went well. This applies MEDDIC as a rubric: six letters, each scored out of ten with the evidence quoted, blanks scored zero and flagged, then a prescription for every weak letter. It is designed to disagree with your optimism, which is the entire value.

Q: What is a mutual action plan, and why does it matter?
A: It is the dated plan both sides own: step, date, owner, and what each step unblocks. Most sellers have never produced one, which is why deals stall between “they'll discuss internally” and silence. This one is built backwards from the date the prospect named, includes the legal and procurement steps nobody mentions, and ends with who signs and when the work starts.

Q: I don't sell enterprise. Is MEDDIC overkill?
A: No. The six questions — who feels the pain, who signs, how they decide, what it's worth, what the process is, who's on your side — matter as much on a $4,000 deal as a $400,000 one. Small transactional deals get a short path instead: four questions and an opener, not a trimmed-down ceremony.

Q: The founder agreed to a meeting. Do I just use the same brief?
A: No, and that is a mode of its own. An executive call gets 60 seconds of context in their organisation's own numbers, exactly three questions, the champion's cost figure offered up for correction, one dated ask, and two lines you send your champion beforehand so they aren't walking into their own boss's meeting unrehearsed.

Q: Is it a subscription?
A: No. A one-time purchase, yours to keep, updates included. It runs inside the Claude or ChatGPT account you already have — the free tiers work too.

Q: Do I need a paid Claude or ChatGPT plan?
A: No. The free tiers run it. Paid plans give you longer sessions and stronger models, which is nicer but not required.

Q: Claude or ChatGPT: which should I use?
A: Both are included and both work. Claude gives the fuller experience because skills upload directly; ChatGPT setup is a two-minute copy-paste from the included CHATGPT-SETUP file.

Q: Do I need to know how to code?
A: No. You type in plain English. Setup is upload-a-file, and every step is written out for non-technical people.

Q: Does it work outside the US, in my currency?
A: Yes. It works in your currency, your date format and your market. It never converts or invents exchange rates.

Q: Can I use it for client work?
A: Yes. One purchase is a perpetual single-user licence; everything it produces is yours to use, unrestricted, for your own business or your clients. You just can't resell or share the skill files themselves.

Q: Is my data private?
A: It runs entirely inside your own Claude or ChatGPT account. We never see your numbers, clients or files.

Q: Can I use it on my phone?
A: Set it up once on a computer; after that it works from the Claude and ChatGPT phone apps too.

Q: Do I get updates?
A: Yes, free updates to this version. If a new version ships, message us on Etsy for the update.

Q: What if it doesn't work for me?
A: Digital files can't be returned on Etsy, but message us and we'll make it right, whether that's a fix, a walkthrough or a refund. A real person replies.

PART OF THE CLOSER SUITE
Also in this shop: Cold Outreach Engine, Proposal & Quote Builder, Objection Battlecards, Pipeline Doctor, or the full Closer Suite bundle at a saving. They share one profile, so you describe your business once and every skill reads it.

INSTANT DIGITAL DOWNLOAD
One .zip file, delivered by Etsy the moment you buy. Nothing physical will be shipped. Free updates for the current version. Questions before or after buying: message us here on Etsy, a real person replies.
Version 2.0.0.

AI disclosure: this toolkit was designed and written by The Skill Mastery with the help of AI tools, then tested by hand (every calculation, template and demo checked). It runs inside Claude or ChatGPT; it is not a standalone app. Not affiliated with Anthropic or OpenAI. Claude and ChatGPT are trademarks of their respective owners.