THE EVERYWHERE CARD · Says whether a skill is ready for each place it can run, and why not where it isn't.
WAKES WHEN Before a skill is uploaded or published · A skill works in one place but not another · Someone asks which Claude surfaces a skill supports
THE LOOP
Take the skill.
Run `check`.
Read spec FAILs first.
Give the matrix with reasons.
Hand over the run matrix and ask for real runs.
NEVER
Calls READY 'tested'
Dodges a platform rule
Quotes a limit without its date
IT MAKES check — check skills; write EVERYWHERE.md, RUN-MATRIX.md and.
THE STANDARD rEADY means nothing in the files blocks it; every BLOCKED carries its reason and its fix; surface rules are quoted as published…; no workaround that dodges a platform rule; verify by execution; say the limit out loud in the work; nothing hidden; the person decides.
PROOF SELFTEST 16/16 · witnessed 2026-10-13 on material and live on Claude · 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 · 5E1BB8611E75E2EEE86AA566
CITE THIS CARDTHE EVERYWHERE CARD, Edition 1. Lund Studio LLC, Westminster, Colorado. https://lundr.tech/?view=everywhere-card. Punch 5E1BB8611E75E2EEE86AA566. Retrieved 2026-10-13.
What it is.
Checks a skill against the open Agent Skills specification and says, surface by surface (Claude Code, the Agent SDK, claude.ai, the Claude API, other Agent Skills hosts), whether it is ready, needs a check, or is blocked, and why: name rules, reserved words, packages it needs, network it calls, zip shape.
Use before publishing or uploading a skill anywhere. Do not use to test what the skill does once running (THE LIFT CARD) or to scan for hidden instructions (THE PACKET SCAN CARD).
It carries a machine that shows its working: check — check skills; write EVERYWHERE.md, RUN-MATRIX.md and — 16 checks in its selftest. It will never calls READY 'tested'; never dodges a platform rule; never quotes a limit without its date.
Eight laws, written into the card.
They are in the card itself, so the AI follows them.
READY MEANS NOTHING IN THE FILES BLOCKS ITREADY means nothing in the files blocks it, never that it was run.
EVERY BLOCKED CARRIES ITS REASON AND ITS FIXEvery BLOCKED carries its reason and its fix.
SURFACE RULES ARE QUOTED AS PUBLISHED…Surface rules are quoted as published at the edition date.
NO WORKAROUND THAT DODGES A PLATFORM RULENo workaround that dodges a platform rule.
VERIFY BY EXECUTIONVerify by execution, not by reasoning: run the machine and read what it prints before saying a thing is done.
SAY THE LIMIT OUT LOUD IN THE WORKSay the limit out loud in the work: every result names what it did not check.
NOTHING HIDDENNothing hidden: two readers, the person and the AI, see the same words.
THE PERSON DECIDESThe person decides.
What rides in the card.
In the card’s own voice, with a machine that shows its working.
THE GUIDEreferences/THE-SURFACES.md
THE MACHINEeverywhere.py · one commandcheck — check skills; write EVERYWHERE.md, RUN-MATRIX.md and. Every command prints its working and refuses a bad input; 16 checks in its selftest.
What it does once your AI has it.
check Check skills; write EVERYWHERE.md, RUN-MATRIX.md and
On the record this cut's own 18 `.skill.zip` files — real material (not made up for the test). All 18: READY on Claude Code, the Agent SDK, claude.ai, the Claude API and other Agent Skills hosts, from a static read. READY is not a run: RUN-MATRIX.md is left blank for real runs on each surface. Live on Claude Sonnet, 2026-10-13: 7 of 7 passed; the card fired on 3 of 3 trigger cases and on none of its hand-off cases.
What it will never do.
It will never calls READY 'tested'; never dodges a platform rule; never quotes a limit without its date.
A static read against published rules. Hosts change their rules and limits; a real run on each surface is the only proof it runs there. 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: its boot, laws, loop, when it says no, its seals, ledger, term and score · SKILL.md — the door your AI reads first · START-HERE.md — the first five minutes, for you
THE-SURFACES.md — the guide in references/, in the card's own voice
scripts/everywhere.py — the machine: check, standard library only, no network, selftest 16/16
WITNESS.md — the runs on real material and live on Claude, with what was not run · SELFTEST.md — the machine's own test, as run at the cut · MANIFEST.md, every file hashed · CHANGELOG.md
tests/evals.json + EVALS.md — the cases it must take, hand off and refuse
MY-LEDGER.md — the card's memory, on your own machine · TIN.md, the nine lines on the tin · LICENSE-NOTE.md
card.svg + card-machine.svg + card.json · card.html, the card as one offline file · doors/ — the rules files for Cursor, Codex, Gemini, Copilot and Claude Code, the system text for any other AI, a local-model file and an MCP door
PROOF · SELFTEST 16/16 · WITNESSED ON MATERIAL · LIVE ON CLAUDE SONNET 2026-10-13 · 7 OF 7 PASSED · EDITION 1 · PUNCH 5E1BB8611E75E2EEE86AA566
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 1196 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 CARD’S OWN WITNESS.MD
everywhere.py, every command showing its working.
A small Python program, standard library only. Your AI runs it; you can too. The blocks below are pasted from the card’s own WITNESS.md, as printed.
check
check skills; write EVERYWHERE.md, RUN-MATRIX.md and
selftest
16 checks that prove the machine; it must print 16/16
THE COMMANDS, IN ORDER, ON THIS CUT'S OWN 18 `.SKILL.ZIP` FILES
$ python3 scripts/everywhere.py check ZIPS --out out --date 2026-10-12
THE VERDICTS, AS PRINTED
VERDICT: PASS · 0 FAIL · 0 WARN · 18 skill(s) checked
VERDICT: BLANK · fill this in after real runs on each surface
THE RUNS ARE PASTED FROM THE CARD’S OWN WITNESS.MD AS PRINTED. FIXTURES MARKED FICTIONAL ARE THE STUDIO’S OWN EXAMPLES, INVENTED FOR THE RECORD; NO PRIVATE PERSON IS NAMED.
QUESTIONS AT THE TABLE
Asked before the wire.
What does it need from me?
The skill folders or zips. Take the skill, and it goes from there.
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 (16/16), a run on real or invented material with every command and verdict pasted into WITNESS.md as printed, and live runs on Claude Sonnet: 7 of 7 passed; the card fired on 3 of 3 trigger cases and on none of its hand-off cases.; 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. A static read against published rules. Hosts change their rules and limits; a real run on each surface is the only proof it runs there.
What will it never do?
It will never calls READY 'tested'; never dodges a platform rule; never quotes a limit without its date.
