AI for LinkedIn content
The most crowded category on the web and the one filled with the most slop, for one structural reason: prompts that take a topic and produce confident text will invent the evidence. Everything here works from material you supply instead, and the content prompt page carries all of them with their full text.
Position, then capture, then write. A content calendar with no material pipeline behind it dies in week three, reliably.
Giving a model a topic. That is the exact mode in which it fabricates a statistic, and LinkedIn is already full of numbers nobody can source.
4 for this work
- Prompt
LinkedIn Post Writer
A post built from material you supplied, with three alternative openings and an honest verdict when there is not enough there to publish.
- Project instruction
LinkedIn Ghostwriter — Project Instruction
A standing instruction you paste once into a Claude Project or ChatGPT Project, after which every post you ask for arrives in your voice and with a critique already applied.
- Prompt chain
Repurposing Chain
A set of independent posts extracted from one source, each standing on its own claim, with an honest count rather than a forced ten.
- Prompt
Comment Strategy
Three comments at different levels of directness, plus a verdict on whether this post is worth commenting on at all.
Attach these once instead of retyping
A prompt is consumed once; a context file is read on every turn for months. These are the ones this work depends on.
- Context file
BRAND-VOICE.md
Drafts arrive in your voice on the first attempt instead of after four rounds of "less corporate".
- Context file
CONTENT-ENGINE.md
A posting system with a material pipeline, rather than a calendar that dies in week three.
These are steps in a longer job
From raw material to a posting habit runs 6 steps end to end, and several of them are on this page. Each step names what it hands the next one, which is the part a list of prompts cannot show.
LinkedIn withdrew its own AI post writer, then shipped a button for reporting posts as AI slop
Both of those are on the table below and both were read from LinkedIn’s own help centre. The help article for the writing tool now says, in full, that it is not available at this time. What replaced it is an editor that shortens a draft you wrote, and a feedback option that tells LinkedIn a post reads as generated. That is the clearest signal the platform has given about generated content, and it is not in any listicle.
| What LinkedIn calls it | What it does | Availability | What unlocks it | What that costs |
|---|---|---|---|---|
| Create posts with our AI-powered writing tool | It generated a post draft from a short prompt. LinkedIn has withdrawn it. Its help article now reads, in full: "LinkedIn's AI-powered writing tool is not available at this time. We'll be introducing new tooling to help improve post writing in the near future." | Withdrawn | Nothing — LinkedIn removed it | Nothing, because it is gone |
| Post Proofreader | It reviews a post draft before you publish — shortening it, clarifying it — and proposes changes you accept or reject. | Gradual rollout | Premium Career or Premium Business | $39.99 a month, read from LinkedIn on 10 September 2026 |
| Seems like AI slop | A feedback option on a post that tells LinkedIn the post reads as AI slop. | Available | Every account, free or paid | No charge on any plan |
| AI-powered post writing for Premium Company Page | LinkedIn's introduction to Premium lists AI-powered post writing as something a Premium Company Page can use. | Gradual rollout | Premium Company Page | $99.99 a month, read from LinkedIn on 10 September 2026 |
Feature names are LinkedIn's own, read from its help centre and product pages on 20 September 2026; the prices come from this site's plan records and carry their own read dates per product family. Availability is LinkedIn's word, not a measurement — a gradual rollout means some accounts have it and LinkedIn does not publish which. The full records, with the ceilings and what LinkedIn declines to disclose, are on the LinkedIn AI features page.
6 tools act on LinkedIn posts. None of them writes yours
What they do is the engagement half: comment automatically, like on a schedule, or export the people who reacted to a post so they can be sequenced. Two of those three are actions LinkedIn’s User Agreement names directly. Read the second column before the feature list.
No account of yours can be restricted, because no account of yours is used. What it sells is a copy, as current as its last refresh — and nothing behind your login: not your network, not your inbox, not your saved lists.
The same reach as the extension class and the same clause against it, with one real difference: the session stays on your machine rather than in a vendor’s datacentre. The computer has to be awake for anything to run, and moving it to a rented server to fix that puts the traffic back on a datacentre IP.
The widest reach of any class and the highest exposure. It runs without you, the credential sits with somebody else, and every action is attributable to your account — which is also the thing LinkedIn can restrict.
| Tool | How it reaches LinkedIn | What it does with your account | Account exposure |
|---|---|---|---|
| Trigify | Data vendor | No account used | None |
| Linked Helper 2 | Desktop app | Sends under your name | High |
| Closely | Vendor cloud | Sends under your name | High |
One tool per route, alphabetically first within each, so nothing here reads as a pick — and exposure is derived from the route and whether the tool sends, not typed next to the vendor it flatters. All 6 in this group, filterable, are in the LinkedIn Content AI directory; every record was read from the vendor's own pages on 20 September 2026.
LinkedIn Personal Branding AI was researched separately and is empty. The forty-five tools researched are outbound and data products. Several act on other people’s posts — a comment, a like, an export of who engaged — and those are filed under LinkedIn Content AI. None of them writes your posts, holds a calendar or works on your own profile, so this heading carries no tools rather than a stretched reading of six.
5 MCP servers reach LinkedIn posts, and posting is the one thing LinkedIn’s own API permits
Posting is the one thing LinkedIn’s self-serve API actually permits: a permission exists for posting on your own behalf. That makes content the only area in this section where a sanctioned route is available at all — and it still does not cover commenting on other people’s posts or reading the feed.
A hosted service whose meta-tools expose more than 160 LinkedIn actions, discovered at runtime, including Sales Navigator and Recruiter messaging. The ones that write reach a real account, behind a server-side preview-then-confirm gate.
A paid cloud-browser service whose tools cover messaging, connections, search, fetching, posting, engagement and Sales Navigator, plus admin tools that let an agent manage seats and rate limits. The MIT repository alone does nothing without the vendor.
A self-hostable four-container outbound application whose MCP server is a route on your own instance. Its read tools touch nothing on LinkedIn; its write tools start real invitations, messages and scheduled posts under your name.
Profile data, the feed, messaging, connections and engagement, on a session taken from your own browser. No rate limiting, no throttle, no dry run and no confirmation step, and the maintainer forbids running it on a server.
4 of the 5 servers filed under posting and engagement, ordered by account exposure, lowest first. That is an ordering, not a recommendation: LinkedIn publishes no MCP server of its own and its User Agreement prohibits automated access by any means, so the directory puts that clause beside each record rather than ranking them. Read 20 September 2026.
What a content prompt will not do for you
Stated here rather than left for a reader to discover, because the gap between what a prompt does and what people expect it to do is where the time goes.
Every prompt here takes something you have — a call transcript, a support thread, a number from your own data, an argument you have had twice this month — and works it into a post. Handed a topic instead, a model writes a plausible statistic and attributes it to nobody. That failure is the reason this category exists.
LinkedIn publishes no reach figures for an unpublished post and no model has access to your audience. What a prompt can do is make the first two lines carry the argument, because those are the only ones shown before the fold.
Not from a chat window. The routes that do publish are an MCP server on LinkedIn’s posting permission, or a tool that drives your session — two very different arrangements, described where they belong. The servers that post, and what each one authenticates with.
The questions people arrive with, answered directly
Does LinkedIn have an AI post writer?
It had one and withdrew it. The help article for the AI-powered writing tool now says it is not available at this time and that new tooling will be introduced. What is live instead is Post Proofreader, an editor that shortens and clarifies a draft you wrote, in limited rollout on Premium — plus AI-powered post writing for a Premium Company Page, which is a separate product at a separate price.
Will LinkedIn penalise AI-generated posts?
LinkedIn has not published a ranking penalty. It has shipped a feedback option on a post labelled "Seems like AI slop", which tells LinkedIn the post reads as generated. Treat that as the platform saying the tone is the problem rather than the tool: a post built from material you actually have does not read that way, and one built from a topic does.
What is the best prompt for writing LinkedIn posts?
One that is forbidden from inventing evidence and is given some. The structural difference between a good LinkedIn post prompt and a bad one is not the format instructions — it is whether the input is a topic or a piece of material. Paste the transcript, the thread or the number, and require every claim in the output to trace back to it.
Can AI automate my LinkedIn comments and engagement?
Tools exist that do it and it is the exact behaviour Section 8.2 of the User Agreement names — creating, commenting on, liking, sharing or re-sharing posts by automated means. 6 tools in the directory act on LinkedIn posts, and the entries say what each one does to the account it runs on. This site describes that route; it does not suggest taking it.
Everything for content, in one folder
The Starter Pack bundles the twelve context files and the twelve most-used prompts as a zip — including the ones on this page. Free, and the ungated link sits under the form.