Create and Assure a LinkedIn Contribution

Turn one valuable idea into a LinkedIn article that survives the stranger test. Do not fabricate proof or promise outcomes you do not own.

Use when. A valuable idea is ready to share and LinkedIn is the chosen channel.

Do not use when. The idea is not yet worth sharing, proof would have to be invented, or you want the model to publish.

Your input. Central idea; available evidence; evidence boundary; target reader; LinkedIn constraints; named publication owner.

Your quality check. A stranger can state the claim in one sentence. Encounter is not outcome. Unknowns stay visible. Publication stays blank.

Put this to work

Create an EXTERNAL_READY LinkedIn article draft

For the accountable publication owner

Copy this prompt. Paste it with the relevant source material into Claude, ChatGPT, or any AI assistant, then review the result before acting.

You are assisting an accountable publication owner to create one LinkedIn article. You may draft and refine only from the evidence and constraints I supply. You do not publish, fabricate proof, or approve the work yourself.

CONTRIBUTION CONTEXT

- Central idea or worthwhile change: [state it]
- Evidence available: [what you can cite]
- Evidence boundary: [where learning stops; what remains unknown]
- Target reader: [who should benefit]
- Surface and constraints: [LinkedIn article; professional tone; 1200-1800 words]
- Publication owner: [name or role]

PRODUCTION STAGES

Follow these stages in order:

**PLAN**
- State one useful idea or worthwhile change for the reader
- Distinguish encounter (what reader might experience) from outcome (beneficiary change you own)
- Name the evidence boundary: where does the learning stop? What remains unknown or untested?
- Identify falsifier: what would invalidate this idea or force a rewrite?

**PRODUCE**
- Write the article with a cold-reader test: can a stranger state the central claim in one sentence?
- Use supplied evidence only; mark assumptions as assumptions
- Keep encounter ≠ outcome visible (e.g., "readers might try X" not "readers will achieve Y")
- No fabricated testimonials, metrics without provenance, or invented validation

**ASSURE**
- Stranger test: would a cold reader understand the central claim, evidence boundary, and what's unknown?
- Surface match: does this fit LinkedIn's professional article format and norms?
- Evidence discipline: are all claims supported or marked as assumptions/unknowns?
- Falsifier check: is the condition that would invalidate this idea stated?

**EXTERNAL_READY**
Return the draft article, evidence used, unknowns acknowledged, falsifier statement, and this question: "Is this ready for you to publish, or what needs revision?"

FALSIFIER RULES

Generic language, unsupported engagement promises, surface mismatch, or self-approval means STOP. Recovery: preserve the draft, name the failed check, and return it for manual correction. Final acceptance check: verify every material claim against supplied evidence and leave publication to the human owner.

Human decision — cannot be delegated. Publish, revise, or stop. AI returns an EXTERNAL_READY draft only. The owner decides. No clinic CTA.

Outcome

One EXTERNAL_READY draft with a useful idea, evidence boundary, and falsifier. Publication remains a human act.

Use When

Use when a valuable idea deserves wider reach and LinkedIn is the chosen channel. The owner keeps the publish decision.

Inputs

Central idea, evidence, evidence boundary, target reader, surface constraints, and named publication owner.

Recipe

Copy the prompt. Follow PLAN → PRODUCE → ASSURE → EXTERNAL_READY. Leave publication to the owner.

Human and AI Control

The owner may permit drafting through EXTERNAL_READY only. Stop for fabricated proof, unsupported outcome claims, self-approval, surface mismatch, or an unclear publication gate.

Output and Handoff

Return the draft, evidence used, unknowns, falsifier, and a blank publish decision. The LinkedIn Article Form names the slots.

Evidence and Stop

Stop for generic language, unsupported engagement promises, surface mismatch, or self-approval. Reader metrics are interaction signals, not beneficiary proof.

Reliability

Skill and tool: biz-mkt-marketing with a private AI chat limited to approved sources. The article form is the pattern; claim traceability and owner approval are the protocol. Retain draft, corrections, and publication decision as evidence. Accept only a warranted, human-approved draft.

If the stranger test fails, revise the missed slot and retest with a different cold reader. When published, watch whether readers ask about the evidence boundary — that is honesty working.