LinkedIn

Verified against ChatGPT · 2026-08-08

Turn one specific work moment into a LinkedIn post that doesn't read like everyone else's

Builds a single LinkedIn post from one concrete thing that actually happened this week, structured around a hook, one real detail, and a takeaway — instead of the generic 'lessons learned' template everyone's feed is drowning in.

ChatGPT (GPT-5.1)5 fillable variables

The prompt

Ready to copy — highlighted parts are example details you can swap.

You are drafting one LinkedIn post for me, built from a single real thing that happened in my work recently — not a generic industry take, not motivational filler.

WHAT HAPPENED
A client almost walked after we missed a deadline by 6 hours; I called them directly instead of emailing, and they stayed.

WHY IT MATTERED TO ME
It proved that a five-minute phone call undoes more damage than a perfectly worded apology email ever could.

WHO SHOULD READ THIS
Agency owners and account managers who've had a client relationship nearly break over a missed deadline.

MY VOICE
Direct, a little self-deprecating, no corporate buzzwords like 'synergy' or 'circle back.'

THE POINT I WANT LANDED
When you've messed up, the medium of the apology matters as much as the apology itself.

RULES FOR THE DRAFT
Open with the single most specific, concrete detail from what happened — a number, a quote someone said, a decision that felt wrong at the time — not an abstract opening line like "I learned something important this week." The first line has to work as a standalone sentence someone would stop scrolling for; assume nobody reads past line one unless it earns the second. Do not summarize the whole story in the first paragraph — let the specific moment sit, then unpack it. Write in short lines with white space between them the way LinkedIn's feed actually renders, not dense paragraphs — but do not turn every sentence into its own line out of habit; group related thoughts. Use exactly one concrete detail I gave you, not invented ones — if a number, name, or quote isn't in what I gave you, do not fabricate one to make the story sound more impressive. End on the takeaway I specified, stated as something the reader can actually use or reconsider, not a vague inspirational close like "keep pushing forward." Do not add a call to action asking people to comment or share unless I've asked for one.

WHAT NOT TO DO
Do not write this as a listicle ("3 lessons I learned") unless the moment I gave you actually breaks into three distinct things — forcing a real story into a numbered list format flattens it. Do not open with a rhetorical question ("Ever wonder why...") — it's the single most overused LinkedIn opener and readers now skip past it reflexively. Do not use the word "grateful" or "humbled" unless it's in my own words above.

OUTPUT FORMAT
1. The post itself, formatted with line breaks as it should appear on LinkedIn.
2. One alternate opening line, in case the first doesn't land, using a different specific detail from what I gave you.
3. A one-line note on what I should NOT post if this feels too exposed or specific for a public feed — a gut-check, not a rewrite.

Customize

Optional — swap in your own details for the highlighted parts above.

Why this works

The instruction to lead with one specific, ungeneralized detail rather than a topic sentence works against a well-documented failure mode of instruction-tuned models: when asked to write a 'LinkedIn post' with no other constraint, GPT-5.1 defaults to a summarizing opening line because that's the statistically safest, most generically applicable structure across the training distribution of business-advice content — which is exactly why so many LinkedIn posts already sound alike. Forcing the model to use only a detail explicitly supplied, and prohibiting invented specifics, closes off the model's tendency to manufacture a more 'impressive' number or quote when the real one feels underwhelming, which is a subtle failure mode particularly likely for high-stakes personal narrative content where the model is otherwise inclined to embellish for effect. Explicitly banning the rhetorical-question opener and the listicle-unless-earned structure matters because both are extremely high-frequency patterns in the model's exposure to LinkedIn-style content specifically, meaning they are the default the model reaches for absent a countervailing instruction, not because they're a genuinely strong choice for every story shape. The final gut-check step exists because a model has no actual stake in the professional consequences of oversharing a specific client name or internal number publicly — asking it to flag exposure risk surfaces that judgment call for the human rather than assuming the model made it silently, since the model cannot know your actual risk tolerance or client relationship without being told.

What you get back

6 hours late. That's how long we missed a client deadline by last month.

My first instinct was to send an apology email. Polished. Professional. Covering every base.

Instead I picked up the phone.

The client's first words weren't about the deadline — they were relief that someone actually called instead of hiding behind a template.

The apology wasn't what saved the relationship. The medium was.

Verified against

ChatGPT GPT-5.1 · 2026-08-08

Changelog

  • 2026-08-08 — Initial publish, verified against ChatGPT GPT-5.1.

Need this built into your business?

If a prompt isn't enough — Google Ads management, built and maintained for you — that's Scult's day job.

EXPLORE GOOGLE ADS MANAGEMENT
Write a first line that survives LinkedIn's "see more" cutoffGenerate six hook-line options for a LinkedIn post, each built on a different mechanism and tested against the actual character count where LinkedIn truncates a post, so every option reads as a complete thought before the cutoff rather than a fragment that only resolves after the tap.ChatGPTClaude2026-07-20Turn a work memory into a story-driven LinkedIn post with a real lessonStructure a raw, unpolished work anecdote into a hook-setup-turn-lesson post using LinkedIn's actual short-line, high-white-space format, while explicitly protecting the unflattering or uncertain detail that makes the story read as lived rather than as a templated failure-to-growth arc.ClaudeChatGPT2026-07-22Outline a swipeable LinkedIn carousel from a single ideaTurn one idea into a slide-by-slide outline for LinkedIn's native document-upload carousel format, built around exactly one point per slide and a design note per slide, so it reads as a designed sequence instead of a wall of bullet points split across pages.ClaudeChatGPT2026-07-23Rewrite your LinkedIn About section so it reads as a person, not a resumeTurn disjointed notes or a resume-voice draft into a first-person About section that opens strong before LinkedIn's preview cutoff and reads like it was written by the person, not extracted from a CV, with keywords worked into real sentences instead of bolted onto the end.ClaudeChatGPT2026-07-24
All LinkedIn prompts

Check your AI visibility

One URL in, a 0–100 score and the exact fixes out.

RUN THE CHECK

Browse all the tools

15 tools across six categories
13 of them never send your data anywhere

Free · No signup · No trial clock

SEE THE DIRECTORY