THE QUALIFY CARD · is this deal real? six facts, their words
WAKES WHEN someone asks whether a deal is real, what to ask next, or which deals to work first
THE LOOP
qualify.py new · the sheet, from notes
mark each fact 0 · 1 · 2, quote beside it
score · ranked, every gap named
questions · for the next call, per gap
re-mark after every call; hope stays out
NEVER
Mark a fact confirmed from hope
Call a deal qualified with no buyer met
Skip the pain because the demo went well
IT MAKES new — the sheet to fill in, one row a deal; score — every deal scored, ranked, with its gaps; questions — the discovery questions for that deal's gaps.
THE STANDARD six facts, from their words; no buyer, no deal; no pain, no urgency; the gaps are the plan; re-mark after every call; the score sorts; the quotes make it true.
PROOF SELFTEST 12/12 · witnessed in Claude 2026-10-09 · Edition 1.
THE SEAL 98 of 100 · LEGENDARY · WITNESSED · Trigger 5 · Machinery 5 · Law 5 · Portability 5 · Proof 5
IT CAN BE WRONG an AI reading a text file: it can be wrong and can invent a number, a rule, a name or a date; check what matters against your own records and the source; the risk is yours. THE-CLAUSES.md rides in the packet and is part of the licence.
THE PUNCH · SHA-256 OF SKILL.MD · 845545D143E049CB6FD6BD5B
CITE THIS CARDTHE QUALIFY CARD, Edition 1. Lund Studio LLC, Westminster, Colorado. https://lundr.tech/?view=qualify-card. Punch 845545D143E049CB6FD6BD5B. Retrieved 2026-10-10.
What it is.
Qualifies sales deals on the six facts a real deal has — the metric that improves, the buyer with the budget, the decision criteria, the buying process, the pain in the buyer's words and a champion inside — each marked unknown, partial or confirmed from what was actually said, scored and ranked with the gaps named, and with the discovery questions to ask for each gap; a deal with no buyer met or no pain stated is unqualified whatever its total.
It carries a machine that shows its working: new — the sheet to fill in, one row a deal; score — every deal scored, ranked, with its gaps; questions — the discovery questions for that deal's gaps — 12 checks in its selftest, every command on the record. It will never mark a fact confirmed from hope; never call a deal qualified with no buyer met; never skip the pain because the demo went well.
Six laws, written into the card.
They are in the card itself, so the AI follows them.
SIX FACTS, FROM THEIR WORDSEach is marked from what the buyer said on a call; the quote sits beside the mark.
NO BUYER, NO DEALUntil the person with the budget is named and met, the deal is unqualified whatever else it has.
NO PAIN, NO URGENCYA deal with no cost of the status quo in the buyer's words will not close on a date.
THE GAPS ARE THE PLANEvery partial or unknown fact has a question for the next call; the card writes them.
RE-MARK AFTER EVERY CALLA mark is a date-stamped fact, never a feeling about the deal.
THE SCORE SORTS; THE QUOTES MAKE IT TRUETwo deals a point apart are a tie, settled by reading the notes.
What rides in the card.
In the card’s own voice, with a machine that shows its working.
THE GUIDEreferences/THE-SIX-FACTS.md
THE MACHINEqualify.py · three commandsnew — the sheet to fill in, one row a deal; score — every deal scored, ranked, with its gaps; questions — the discovery questions for that deal's gaps. Every command prints its working and refuses a bad input; 12 checks in its selftest, every command on the record.
What it does once your AI has it.
new The sheet to fill in, one row a deal
score Every deal scored, ranked, with its gaps
questions The discovery questions for that deal's gaps
On the record Four example deals scored on the six facts and ranked — the renewal upsell qualified, the inbound pilot unqualified, the deal with no buyer met unqualified whatever else it had — and the discovery questions written for the deal with the most gaps.
What it will never do.
It will never mark a fact confirmed from hope; never call a deal qualified with no buyer met; never skip the pain because the demo went well.
The score sorts what the rep wrote; it cannot tell a confirmed fact from a hopeful one, so the sheet is filled from call notes with the quote beside each mark. Scores are coarse on purpose; two deals a point apart are a tie. It is an AI reading a text file: it can be wrong, so check what matters against your own records and the source.
What’s in the buy.
CARD.md — the whole card: who it is, its laws, when it says no, what it carries · SKILL.md — the door your AI reads first · START-HERE.md — the first five minutes, for you
THE-SIX-FACTS.md — the guide in references/, in the card's own voice
scripts/qualify.py — the machine: new · score · questions, standard library only, selftest 12/12
WITNESS.md + SELFTEST.md — every command on the record, as it printed · MANIFEST.md, every file hashed · AUDIT.md, the twelve checks
MY-LEDGER.md — the card's memory, on your own machine · TIN.md · LICENSE-NOTE.md · THE-CLAUSES.md · HOSTS.md
card.svg + card-machine.svg + card.json · card.html, the card as one offline file · the doors for ChatGPT, Gemini, Cursor, Claude Code and MCP hosts (rules/, system/, mcp/)
PROOF · SELFTEST 12/12 · 3 COMMANDS ON THE RECORD · WITNESSED IN CLAUDE 2026-10-09 · EDITION 1 · PUNCH 845545D143E049CB6FD6BD5B
ON EVERY DOOR · A CARD FOR YOUR AI, A FILE FOR YOUR COMPUTER
In Claude: turn on code execution under Settings › Capabilities, then Customize › Skills › + › Create skill, and upload the zip as it is — START-HERE.md in the box walks you through it, and tells you how to keep the ledger. In ChatGPT, Gemini and the rest: a Project, a GPT or a Gem with the card’s files attached and the short door in the box pasted as its instructions. The words run anywhere an AI reads Markdown; the machines run wherever the host runs Python. Witnessed in Claude only. The host marks →
Take it.
Nº 841 PROPOSED — LAUNCHING SOON
Sold as is under the term printed. A card instructs an AI you operate; results depend on your model, your files and your judgement. Not medical, legal, tax or financial advice, never the person’s boss, and not a licence to practise. The terms →
One payment. The file is yours to keep and keeps working at its edition; new editions issued in the year after you buy reach you by email as replacement files. Tax is added at checkout where it applies. Nothing auto-renews.
A TERM, NOT A SUBSCRIPTION: NOTHING RENEWS ITSELF AND NOBODY IS CHARGED AGAIN. WHEN A TERM ENDS THE FILES STAY ON YOUR COMPUTER AND STAY READABLE — FREEZE, NOT LOSS.
THE MACHINE · IN THE OPEN · FROM THE WITNESSED RUN OF 2026-10-09
qualify.py, every command showing its working.
A small Python program, standard library only. Your AI runs it; you can too. Every block below is pasted from the card’s own WITNESS.md, as printed.
new
the sheet to fill in, one row a deal
score
every deal scored, ranked, with its gaps
questions
the discovery questions for that deal's gaps
selftest
12 checks that prove the machine; it must print 12/12
new · THE SHEET TO FILL IN, ONE ROW A DEAL
$ python3 scripts/qualify.py new deals.csv
sheet written · deals.csv · 4 example deals (invented) · mark each fact 0 unknown, 1 partial, 2 confirmed, from the buyer's own words
score · EVERY DEAL SCORED, RANKED, WITH ITS GAPS
$ python3 scripts/qualify.py score deals.csv --report ranking.md
QUALIFY · 4 deals · 1 qualified · 1 working · 2 unqualified
QUALIFIED 11/12 · Summit renewal upsell · USD 90,000 · metr:2 buye:2 crit:2 proc:2 pain:1 cham:2
gaps: pain
WORKING 9/12 · Northwind support automation · USD 48,000 · metr:2 buye:2 crit:1 proc:1 pain:2 cham:1
gaps: criteria, process, champion
UNQUALIFIED 4/12 · Harbor onboarding · USD 12,000 · metr:1 buye:0 crit:0 proc:0 pain:2 cham:1
no buyer met · gaps: metric, buyer, criteria, process, champion · no timeline · competition unknown
UNQUALIFIED 1/12 · Pioneer pilot · no amount · metr:0 buye:1 crit:0 proc:0 pain:0 cham:0
no pain in their words · gaps: metric, buyer, criteria, process, pain, champion · no timeline · competition unknown
A deal with no buyer or no pain is UNQUALIFIED whatever its total; QUALIFIED needs every fact at least partial and 10 of 12.
report written · ranking.md
questions · THE DISCOVERY QUESTIONS FOR THAT DEAL'S GAPS
$ python3 scripts/qualify.py questions deals.csv "Harbor onboarding"
QUESTIONS · Harbor onboarding · UNQUALIFIED 4/12
METRIC (partial):
- What number would have to move for this to be worth it, and by how much?
- How do you measure that today, and what is it now?
BUYER (unknown):
- Whose budget does this come from?
- When could we meet them, and what will they want to see?
CRITERIA (unknown):
- When you compare options, what are the three things that decide it?
- Is that written down anywhere we could see?
PROCESS (unknown):
- From a yes on your side, what happens next — who signs, who reviews, how long does each step take?
- Has anything like this been bought here before? How did that go?
CHAMPION (partial):
- Who on your side wants this most, and why?
- Would they walk us through the building when we are not there?
TIMELINE:
- Is there a date this has to be live by, and what set it?
COMPETITION:
- Who else are you talking to, and what do you like about them?
Write the answers, with the quote, into the sheet; the mark follows the quote, never the hope.
THE NUMBERS, NAMES AND DATES IN THESE RUNS ARE THE STUDIO’S OWN EXAMPLES, INVENTED FOR THE RECORD; NO REAL COMPANY, PERSON OR PROPERTY IS NAMED.
QUESTIONS AT THE TABLE
Asked before the wire.
What does it need from me?
Qualify.py new · the sheet, from notes. It asks first for the deals in play and, for each, the call notes the marks come from — the quote goes beside the mark.
Does it send anything anywhere?
No. The machine is a standard-library Python program that runs on your own computer and sends nothing anywhere; the words run wherever an AI reads Markdown. No server, no account, no key.
What is on the record?
The self-test (12/12) and every command run on real example inputs, pasted into WITNESS.md as they printed; the punch on the face is the SHA-256 of SKILL.md, so a downloaded copy can be checked against this room.
Can it be wrong?
Yes — it is an AI reading a text file. The score sorts what the rep wrote; it cannot tell a confirmed fact from a hopeful one, so the sheet is filled from call notes with the quote beside each mark. Scores are coarse on purpose; two deals a point apart are a tie.
What will it never do?
It will never mark a fact confirmed from hope; never call a deal qualified with no buyer met; never skip the pain because the demo went well.
