THE DESK · THE QUANT · Nº 1322 · EDITION 1 ·Liquid error (snippets/rm-screen-card line 27): comparison of String with 0 failed
LUND CARDS · THE DESKNº 1322
THE CARD AS TEXT · FOR EYES AND FOR MACHINES
THE SCREEN CARD · the screener seat — filters and ranks a universe against your stated rules
WAKES WHEN an investor needs to narrow a list of companies by explicit criteria · a person asks 'screen these', 'which pass my filters', 'rank this universe' · a watchlist needs a disciplined, reproducible cut
THE LOOP
set · the filters (max/min on each metric) and the weights for the fit score
apply · every company against every filter, pass or fail, with the reason named
rank · by weighted fit, deterministically, so the same data gives the same order
flag · a blank metric is a gap, flagged by name, never treated as a pass or a zero
NEVER
Fills a missing metric with a guess to let a company pass — a blank is flagged
Gives investment advice or tells anyone to buy, sell, short, or trade
Presents a backtest, model, or projection as a promise of future return — unknown inputs are marked [FILL]
Front-runs, times a trade, or substitutes for a licensed professional's judgment
IT MAKES run — applies your filters, ranks by weighted fit, shows the reason for each verdict; selftest — 9 checks that prove the machine.
THE LAW A card builds and checks the analysis — the model, the screen, the thesis. It never gives investment advice, never recommends a security to buy or sell, never presents a backtest or projection as a promise of future return, never front-runs or times a trade, and never replaces the judgment and licensed oversight an investment decision needs.
PROOF SELFTEST 9/9 · witnessed in Claude 2026-10-20 on the studio’s own example inputs · the dated run in the box (RUN.md) · 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. LICENSE-NOTE.md rides in the packet and is the licence.
THE PUNCH · SHA-256 OF SKILL.MD · 43DEEF4D0B2DE279286C640D
CITE THIS CARDTHE SCREEN CARD, Edition 1. Lund Studio LLC, Westminster, Colorado. https://lundr.tech/?view=screen-card. Punch 43DEEF4D0B2DE279286C640D. Retrieved 2026-10-20.
What it is.
Filters and ranks a universe against your stated rules. Use when an investor needs to narrow a list of companies by explicit criteria. Not for buy or sell calls. For a candidate's full write-up → THE EQUITY RESEARCH CARD.
It carries a machine that shows its working: run — applies your filters, ranks by weighted fit, shows the reason for each verdict; selftest — 9 checks that prove the machine — 9 checks in its selftest, run in the open below. It never fills a missing metric with a guess to let a company pass — a blank is flagged; never gives investment advice or tells anyone to buy, sell, short, or trade; never presents a backtest, model, or projection as a promise of future return — unknown inputs are marked [FILL]; never front-runs, times a trade, or substitutes for a licensed professional's judgment.
The house law, written into the card.
It is in the card itself, so the AI follows it.
THE HOUSE LAW · THE DESKA card builds and checks the analysis — the model, the screen, the thesis. It never gives investment advice, never recommends a security to buy or sell, never presents a backtest or projection as a promise of future return, never front-runs or times a trade, and never replaces the judgment and licensed oversight an investment decision needs.
THE LIMIT, ON THE TINIt applies the rules you choose to the data you supply; a screen surfaces candidates, it does not pick investments. The filters and the data are yours to get right.
The method.
Set. The filters (max/min on each metric) and the weights for the fit score.
Apply. Every company against every filter, pass or fail, with the reason named.
Rank. By weighted fit, deterministically, so the same data gives the same order.
Flag. A blank metric is a gap, flagged by name, never treated as a pass or a zero.
What it does once your AI has it.
run Applies your filters, ranks by weighted fit, shows the reason for each verdict
selftest 9 checks on the studio’s own example inputs; it must print selftest 9/9
What it will never do.
It never fills a missing metric with a guess to let a company pass — a blank is flagged; never gives investment advice or tells anyone to buy, sell, short, or trade; never presents a backtest, model, or projection as a promise of future return — unknown inputs are marked [FILL]; never front-runs, times a trade, or substitutes for a licensed professional's judgment.
Where it hands off: A candidate's full write-up → THE EQUITY RESEARCH CARD. Its factor tilts → THE FACTOR CARD. Its valuation → THE DCF CARD.
It is an AI reading a text file: it can be wrong, so check what matters against your own records and the source. The holder brings their own AI; no endorsement by Anthropic or any other AI company is claimed. Names of other companies and standards are used only to say what the card works with.
What’s in the buy.
SKILL.md — the door your AI reads first: when it wakes, when it does not, the loop, the never-lines, the house law
CARD.md — the whole card in ten sections, §0 to §9 · TIN.md — what is on the tin, in nine lines
scripts/screen.py — the machine, Python standard library only, offline; selftest 9/9
RUN.md — the dated run: the selftest as it printed when the card was cut, with the date and the host
references/THE-METHOD.md — the method in plain words, in the card’s own voice
START-HERE.md and system/short-prompt.md — the doors, for any AI with or without skills
MY-LEDGER.md — the card’s memory, on your own machine · LICENSE-NOTE.md — the licence
PROOF · SELFTEST 9/9 · AUDIT 12/12 · WITNESSED IN CLAUDE 2026-10-20 ON THE STUDIO’S OWN EXAMPLE INPUTS · THE TEST PROMPTS IN FRESH CHATS OWED · EDITION 1 · PUNCH 43DEEF4D0B2DE279286C640D
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 1322 —Liquid error (snippets/rm-screen-card line 116): comparison of String with 0 failed
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. Not investment advice, not an appraisal and not an offer to sell securities. 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.
AFTER YOU PAY · SIGN IN WITH THE EMAIL YOU PAID WITH · THE CARD OPENS ON MY CARDS → · CHECKED AGAINST ITS FINGERPRINT · NOTHING TO WAIT FOR
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 STUDIO’S RUN OF 2026-10-20
screen.py, showing its working.
A small Python program, standard library only. Your AI runs it; you can too. The block below is the machine’s selftest as it printed when the studio ran it from inside the packet, in Claude, on 2026-10-20.
run
applies your filters, ranks by weighted fit, shows the reason for each verdict · run COMPANIES.csv CRITERIA.txt
selftest
9 checks that prove the machine; it must print selftest 9/9
selftest · AS PRINTED
$ python3 scripts/screen.py selftest
wrote SCREEN.md — 2/4 passed
REFUSED: no companies to screen
wrote SCREEN.md — 2/4 passed
wrote SCREEN.md — 2/4 passed
selftest 9/9
THE SELFTEST RUNS ON THE STUDIO’S OWN EXAMPLE INPUTS, INVENTED FOR THE TEST; NO REAL COMPANY, PERSON OR ACCOUNT IS NAMED.
QUESTIONS AT THE TABLE
Asked before the wire.
What does it need from me?
Your own files and figures, on your own disk. It starts by asking for them: the filters (max/min on each metric) and the weights for the fit score. If something it needs is missing, it marks it and says so — it never fills a gap with a guess.
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 machine's selftest (9/9), run from inside the packet in Claude on 2026-10-20 on the studio's own example inputs and printed below as it ran; the twelve-check audit (AUDIT.md, 12/12); MANIFEST.md with every file hashed. RUN.md in the box is that run, dated. Still to come, as the next receipt: the card's test prompts asked in fresh chats with the card installed. 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: 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. It applies the rules you choose to the data you supply; a screen surfaces candidates, it does not pick investments. The filters and the data are yours to get right.
What will it never do?
It never fills a missing metric with a guess to let a company pass — a blank is flagged; never gives investment advice or tells anyone to buy, sell, short, or trade; never presents a backtest, model, or projection as a promise of future return — unknown inputs are marked [FILL]; never front-runs, times a trade, or substitutes for a licensed professional's judgment.
