LinkedIn Content Agent
Drafts in your voice, built from real material, with a self-critique attached before you read them. The posting system as a folder. The ghostwriter instruction goes into the Project; the voice and content files give it something to work from; and the rule that runs through all of it is that nothing gets invented — no statistic, no customer, no anecdote.
No email, no account, no cookie wall. Every file in it is also readable in full on this site.
The folder
linkedin-content-agent/
├── README.md # setup, in order
├── CLAUDE.md
├── BRAND-VOICE.md
├── CONTENT-ENGINE.md
├── COMPANY.md
├── PRODUCT.md
├── PERSONAS.md
└── PROMPTS/
├── founder-positioning.md
├── post-generator.md
├── content-repurposing.md
├── comment-strategy.md
└── ghostwriter-instructions.mdFounder Positioning Brief, worked
What this pack produces once the files above are filled in — the actual example from this prompt's own page.
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.
About twenty minutes, most of it writing down your ICP
- Download and unzip.
- Fill BRAND-VOICE.md with five real sentences.
- Paste the ghostwriter instruction into a Claude or ChatGPT Project.
- Attach the rest of the files as Project knowledge.
What you do with it once it is set up
- Position — One claim you can defend for twelve months. Plus the not-list.
- Capture — Material from calls, support threads and your own analysis — logged as it happens.
- Draft — Post built from material, in your voice, with the limitation stated.
- Critique — Three named weaknesses and the strongest objection, before you read it.
- Engage — Comments on the accounts whose audience is your audience.
Every file, in full, on this site
Nothing in the pack is hidden behind the download. If you would rather take three files than fifteen, take three.
- Context file
CLAUDE.md
An agent that reads the right files in the right order and knows what it is not allowed to do.
- 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.
- Context file
COMPANY.md
The assistant stops describing your company the way its training data describes companies in your category.
- Context file
PRODUCT.md
Messages stop describing features and start describing what changes for the person receiving them.
- Context file
PERSONAS.md
Messages that speak to what the reader is measured on rather than to a job title.
- Prompt
Founder Positioning Brief
A single defensible claim, three supporting themes, an explicit not-list, and a one-question test for whether any given post belongs.
- 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.
- Prompt
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.
- Prompt
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.
Use it for your work and your clients' work
Use every prompt, file and pack for your own company or for clients you are paid by, commercially, modified as much as you like. Put them in your Claude Project, your ChatGPT Project, your Cursor workspace or your agent repo. Share a filled-in copy with your team.
Keep the attribution line at the bottom of any file you redistribute unchanged, and credit Linkediz with a link wherever you republish a resource in full.
Repackage the library or a pack as your own product, paid or free, or scrape the section to rebuild it elsewhere. The downloads exist so you do not have to.
These are writing and research aids. They do not know your customers, they can be wrong, and an assistant will state a fabricated fact as confidently as a true one. Read what comes out before you send it to a person.
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.
The reference behind this pack
Every figure in a post here is sourced and dated. It is the standard the "never invent" rule is aiming at.