LinkedIn Founder Positioning Prompt
A single defensible claim, three supporting themes, an explicit not-list, and a one-question test for whether any given post belongs. Founder content fails at the strategy layer, not the writing layer: forty posts about five unrelated things build no position at all. This prompt produces the one claim worth being known for, the three themes that ladder into it, and the list of things to stop saying — which is the half that makes the rest work.
You are a positioning strategist working with a founder who posts on LinkedIn. Your standard is high: a position that could be held by any competent competitor is not a position.
## The founder
{{ROLE}} at {{COMPANY}}
What we sell: {{PRODUCT}}
ICP: {{ICP}}
Proof available: {{PROOF}}
Objective: {{OBJECTIVE}}
Tone: {{TONE}}
## What I currently talk about
[PASTE 5–10 RECENT POSTS, or a list of the topics you have covered]
## Method
1. Find the claim. It must be: specific to this company's experience, contestable by a reasonable person, and something this founder can defend for twelve months without running out of material. If the honest answer is that no such claim exists yet, say that and say what evidence would create one.
2. Test it: would a serious competitor happily make the same claim? If yes, it is a category truism. Sharpen it or discard it.
3. Derive three themes that each ladder into the claim from a different direction — typically one about the problem, one about the method, one about the evidence.
4. Write the not-list: the adjacent topics that dilute the position. Be specific, including the ones that get engagement. Engagement on an off-position topic is the most expensive kind.
5. Write the belonging test: one question that decides whether a draft post belongs, answerable in five seconds.
6. Map the claim to the profile: the headline and About opening that state it.
## Constraints
- One claim. Not a pillar framework, not a messaging house, not five "content pillars".
- Nothing that requires the founder to have opinions on general business topics, leadership, hiring or AI unless those are literally the product.
- No "thought leadership" as a goal. Name what the position is supposed to cause.
## Output format
### The claim
One sentence. Then: who would disagree with it, and why that is a good sign.
### Why this and not the obvious alternative
Two sentences.
### The three themes
| Theme | The angle it takes on the claim | Example post titles (3 each) |
|---|---|---|
### The not-list
Topics to stop posting about, each with the reason.
### The belonging test
One question.
### Profile alignment
The headline and the About opening that state the claim, with character counts.
### Twelve-month material check
Whether there is enough real experience behind the claim to sustain a year of posting, and where the next material comes from.- You post regularly and nobody can say what you are known for.
- You are about to start posting and want a spine before the first one.
- You are briefing a ghostwriter or a content agent and need the position in writing.
- Paste real posts, not a description of them. The gap between what you think you post about and what you actually post about is where the finding is.
- Take the not-list seriously, especially the entries that perform well. Off-position engagement is why founders with 40,000 followers sell nothing.
- Put the claim and the belonging test into BRAND-VOICE.md so every content prompt inherits them.
The output schema it demands
The single highest-leverage part of any prompt. Without a declared shape you get prose you then have to reformat; with one, you get sections you can act on — and you can tell at a glance when the model skipped something.
### The claim (+ who would disagree) ### Why this and not the obvious alternative ### The three themes (table) ### The not-list ### The belonging test ### Profile alignment ### Twelve-month material check
What it looks like filled in
Illustrative, not a promise — this is the shape of a good answer rather than a guarantee of one. The scenario is the same fictional company used across the whole toolkit.
10 recent posts pasted, mostly general finance-ops commentary. Product: Cadence, multi-entity payroll reconciliation.
The claim — multi-entity close time is an entity-count problem, not a headcount problem. A competitor selling generic "close automation" would disagree — they would call it a tooling problem.
The not-list — general AI-in-finance commentary (2 of the 10 pasted posts) and hiring advice (1 post). Neither ladders into the claim; both come off the calendar.
The belonging test — does this post make the entity-count claim more credible, or is it just a true statement about finance? "Just true" does not get published.
Twelve-month material check — thin. Only 3 of the 10 pasted posts have real material behind them. The capture habit in CONTENT-ENGINE.md needs to start now, not once the calendar runs dry.
Attach these once and stop retyping your business
This prompt works pasted into a blank chat. It works considerably better inside a Project with these attached, because then the ICP, the product and the limits are already in context and every answer inherits them.
The reference behind this prompt
A worked example of the same exercise: one claim — publish what LinkedIn costs with the date it was checked — and an explicit not-list.
Written to a fixed structure and run through Claude and ChatGPT to confirm each one returns the output format it declares. That is not the same as a measured reply-rate benchmark, and nothing here claims one — if you run these at volume and have numbers, we want them.
Take the whole folder instead
This prompt, the files it expects and the rest of the sequence, as a zip you can drop into a Claude Project, a Cursor workspace or an agent repo. Free, no account.