---
type: method
slug: social-media-graphics
title: "Design social media graphics"
category: "Design & Creative"
subcategory: "Images & graphics"
level: starter
source: https://deepstoryresearch.com/method/social-media-graphics
publisher: Deepstory Research
---

> **How to use this file:** attach it to ChatGPT, Claude, Gemini or Copilot (or paste the prompt section), replace every [PLACEHOLDER] with your details, and add any data or Deepstory evidence files the method needs.

## When to use this method
- Creating a consistent visual feed.

## Prompt

# Design social media graphics
Method by Deepstory Research: deepstoryresearch.com/method/social-media-graphics

You are a social designer. Follow the method below step by step. Goal: A set of on-brand post templates (carousel, quote, stat, announcement) with copy and layout specs.

## My inputs
- Brand kit: [BRAND_KIT]  (example: colours, fonts, logo)
- Platforms and sizes: [PLATFORMS_AND_SIZES]  (example: Instagram 1080×1350, LinkedIn 1200×1200)
- Content to design: [CONTENT_TO_DESIGN]  (example: 5 posts from calendar)

Before you start: if any input above is still in [BRACKETS] or missing, ask me for it in one short numbered list and wait. Do not guess. If I attached files (data, briefs, Deepstory evidence files), treat them as the primary source.

## Steps to follow
1. Define 4 reusable templates.
2. For each post: layout, copy per slide, visual prompt.
3. Specify safe zones and text limits.
4. Give export settings.

## Deliver the output in this structure
- Template specs
- Post-by-post designs
- Image prompts
- Export settings

## Quality rules
- Max ~20 words per slide; contrast checked.
- Label every number as FACT (with source and date), ESTIMATE (show the calculation) or ASSUMPTION.
- If a Deepstory evidence file is attached, use its figures as the reference values and cite its source references; tag claims that are not from it as [UNVERIFIED].
- End with: the 3 assumptions that matter most, what would change the answer, and the single best next step.

---
Deepstory methods are process guidance for AI tools. Review AI output before relying on it; legal, tax, medical and investment matters need a qualified professional.