LinkedIn Post Visual skill
The prompt structure Moonrank's LinkedIn Agent uses to brief image models: one visual metaphor, exact text, and a house style that makes every post read as part of the same series.
Download the prompt structure, see how the agent picks the metaphor, or run it inside the LinkedIn Agent.
- Category
- Agent
- LinkedIn Agent
- Format
- linkedin-post-visual.md
- Price
- Free to download
The skill file
What is the LinkedIn Post Visual skill?
The LinkedIn Post Visual skill turns a finished post into a prompt an image model can follow: one visual metaphor, the exact words to render, and a consistent house style. It also tells you when a real screenshot beats a generated image.
It's written as a SKILL.md, a plain-language instruction format that people and AI agents can both follow. Use it with ChatGPT or Gemini, hand it to a designer, or let the LinkedIn Agent write the prompt with each draft.
Downloading the playbook is free with a Moonrank account. Pairing every draft with a visual prompt is what the LinkedIn Agent does for you.
See it in action
“My AI-generated images are cluttered and the text is always misspelled. How do I brief the model better?”
Your prompts describe a mood, not a layout. The rewrite gives the model a fixed structure (headline, one hero metaphor, one row of steps, footer), lists every word exactly, locks your background and accent color, and ends with an instruction to spell the text exactly as written.
From input to fix list
- 1
You bring the post
The final text, and your brand colors.
- 2
Moonrank decides what the image says
The payoff, the proof, or the offer. Never a copy of the hook.
- 3
It picks one metaphor
A single visual idea that makes the point at a glance.
- 4
It writes the prompt
Format, style, exact text, and a 16:9 variant for X.
Everything it checks
Real-proof check
Use a real screenshot when you have one. Generate only when you don't.
Payoff-first headline
The image says what the reader gets, not what the hook said.
One visual metaphor
A single concrete idea instead of a busy collage.
Locked house style
Same background, font, and accent every week.
Exact-text rendering
Every word listed so the model spells it right.
LinkedIn and X sizes
Portrait for LinkedIn, landscape for X.
When to reach for it
- Create the image for this week's posts in minutes.
- Make your visuals look like one brand, week after week.
- Stop getting misspelled text from image models.
- Brief a designer with a clear layout.
- Decide when a real screenshot is the better visual.