THE STORYLINE CARD · the recommendation, argued top-down
WAKES WHEN a recommendation or a deck is being planned, or its slide titles are being tightened
THE LOOP
write the answer first, in one line
check · the pyramid and its faults
ghost · a slide for every support
fill each chart slot with its proof
titles · every one an action title
NEVER
Pass a label as a slide title
Stand an argument on one key line
Draw a chart before the storyline holds
IT MAKES check — the pyramid and its faults; ghost — the ghost deck, slide by slide, chart slots marked; titles — every ## slide title: ACTION or MEND, with why.
THE STANDARD the answer first; two to five key lines; every key line has support; titles say what the slide proves; a slot is not a chart; shape, not truth.
PROOF SELFTEST 8/8 · witnessed in Claude 2026-10-10 · 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 · 3CCB41247427ADECE15EFF15
CITE THIS CARDTHE STORYLINE CARD, Edition 1. Lund Studio LLC, Westminster, Colorado. https://lundr.tech/?view=storyline-card. Punch 3CCB41247427ADECE15EFF15. Retrieved 2026-10-10.
What it is.
Builds a recommendation top-down before a slide is drawn: check reads a storyline written as one governing thought (#), two to five key lines (##) and their support (-) and names a governing thought or key line that is a label, a question or over fifteen words, too few or too many key lines, and a key line with no support; ghost writes the ghost deck from it — the title, the summary, a divider per key line, a slide per support with the chart it needs left as a slot, and the ask; titles reads a deck's slide titles and names every one that is not an action title — a sentence that says what the slide proves.
It carries a machine that shows its working: check — the pyramid and its faults; ghost — the ghost deck, slide by slide, chart slots marked; titles — every ## slide title: ACTION or MEND, with why — 8 checks in its selftest, every command on the record. It will never pass a label as a slide title; never stand an argument on one key line; never draw a chart before the storyline holds.
Six laws, written into the card.
They are in the card itself, so the AI follows them.
THE ANSWER FIRSTThe governing thought is the recommendation in one sentence; everything below it holds it up.
TWO TO FIVE KEY LINESOne is not an argument; more than five is a list.
EVERY KEY LINE HAS SUPPORTA key line with nothing under it is an assertion, and is named.
TITLES SAY WHAT THE SLIDE PROVESFive to fifteen words, a sentence, not a label or a question.
A SLOT IS NOT A CHARTThe ghost deck marks the chart each slide needs; the team fills it with the proof and its source.
SHAPE, NOT TRUTHThe card reads the argument's shape; whether it is true is the evidence's to show.
What rides in the card.
In the card’s own voice, with a machine that shows its working.
THE GUIDEreferences/THE-CONSULTANCY.md
THE MACHINEstoryline.py · three commandscheck — the pyramid and its faults; ghost — the ghost deck, slide by slide, chart slots marked; titles — every ## slide title: ACTION or MEND, with why. Every command prints its working and refuses a bad input; 8 checks in its selftest, every command on the record.
What it does once your AI has it.
check The pyramid and its faults
ghost The ghost deck, slide by slide, chart slots marked
titles Every ## slide title: ACTION or MEND, with why
On the record A storyline read as a sound pyramid — one answer, three key lines, five supports; the ghost deck written at eleven slides with a chart slot for each support; an old deck's titles read, one action title kept and a label and a question named to mend.
What it will never do.
It will never pass a label as a slide title; never stand an argument on one key line; never draw a chart before the storyline holds.
An action title is read by form — a sentence of five to fifteen words, not a question; a well-formed title can still say nothing, and the card cannot tell. The pyramid is read from headings and bullets as written; an argument written as prose is not read. 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-CONSULTANCY.md — the guide in references/, in the card's own voice
scripts/storyline.py — the machine: check · ghost · titles, standard library only, selftest 8/8
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 8/8 · 3 COMMANDS ON THE RECORD · WITNESSED IN CLAUDE 2026-10-10 · EDITION 1 · PUNCH 3CCB41247427ADECE15EFF15
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 1105 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 2026-10-10
storyline.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.
check
the pyramid and its faults
ghost
the ghost deck, slide by slide, chart slots marked
titles
every ## slide title: ACTION or MEND, with why
selftest
8 checks that prove the machine; it must print 8/8
(the storyline written top-down)
$ (the storyline written top-down)
check · THE PYRAMID AND ITS FAULTS
$ python3 scripts/storyline.py check storyline.md
GOVERNING · Plan the bake from pre-orders and waste falls by a third within a quarter
KEY · Most waste comes from bread baked for customers who never come
- Monday and rainy days carry half the year's waste across all three bakeries
- Footfall swings by forty percent while the bake stays the same every day
KEY · Customers will pre-order when it is easy and early
- Two in five interviewed customers would order the night before
- The downtown trial took ninety orders a day within two weeks
KEY · The change pays back before the busy season
- Flour and butter saved cover the ordering page within four months
3 key lines · 5 supports · the pyramid stands
ghost · THE GHOST DECK, SLIDE BY SLIDE, CHART SLOTS MARKED
titles · EVERY ## SLIDE TITLE: ACTION OR MEND, WITH WHY
$ python3 scripts/storyline.py titles deck.md
MEND line 2 · Revenue — a label — say what it shows
ACTION line 3 · Revenue fell 12% because fewer customers came on Mondays
MEND line 4 · What next? — a question — say the answer
3 slide titles · 1 action title · 2 to mend
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?
Write the answer first, in one line. It asks first for the answer in one sentence, the key lines, and the support for each.
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 (8/8) 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. An action title is read by form — a sentence of five to fifteen words, not a question; a well-formed title can still say nothing, and the card cannot tell. The pyramid is read from headings and bullets as written; an argument written as prose is not read.
What will it never do?
It will never pass a label as a slide title; never stand an argument on one key line; never draw a chart before the storyline holds.
