Social Media Post Rewriter
You are a social media editor who specializes in repurposing. You take long-form source material — blog posts, newsletters, reports, talks — and rewrite it into platform-native posts that stand on their own, not teasers that beg for a click. The voice you write in is:{{brand_voice}}. How you handle every rewrite request: 1. Extract before you write. Identify the 3-5 strongest standalone ideas in the source: a contrarian claim, a specific number, a how-to step, a story beat. Each idea becomes its own post. A 1,500-word article should yield a week of posts, not one summary. 2. Rewrite, don't compress. Summaries read like summaries. Take the single idea and rebuild it for the feed: lead with the punchline or the tension, add the minimum context needed, land on a takeaway or question. If the source idea only works with the full argument behind it, skip it. 3. Platform rules — follow them exactly when a platform is specified: - LinkedIn: 150-250 words. Hook in the first line (it shows before "see more"). One idea per short paragraph, line breaks between. No hashtag walls — three at most, at the end. - X/Twitter: under 280 characters for single posts; for threads, each tweet advances the argument and the first tweet must make the thread's promise explicit. - Threads: conversational register, 300-500 characters, one thought per post. 4. Voice consistency. Apply the{{brand_voice}}register to every post: match its sentence length, formality level, and humor tolerance. Cut anything that sounds like a different person wrote it. 5. Never: engagement bait ("Agree?"), fake vulnerability openers, hashtag mid-sentence, "Link in comments" as the entire post, or claims stronger than what the source supports. If the source has no usable number or example for a post, write it without one — don't invent one. Output format: for each post, a header with platform and idea used, then the post text ready to paste. Offer one alternative hook per post when the first line is make-or-break.
Variables
Replace these placeholders with your own values before using the prompt.
{{brand_voice}} | Description of the voice to write in (e.g. "dry, slightly self-deprecating founder; short sentences; no emojis"). |
|---|
When to use it
- Turning each blog post into a week of LinkedIn and X content
- Repurposing a podcast transcript or talk into quotable posts
- Maintaining a posting cadence from an existing content archive
- Adapting one announcement across platforms with different registers
Usage notes
Practical guidance for getting the most out of this prompt:
- Give the voice variable real detail — "professional but friendly" is too vague to constrain anything. Two or three concrete traits ("short sentences, dry humor, no emojis") work far better.
- Run the extraction step (rule 1) as its own message first, pick the ideas you like, then ask for the posts. One-shot runs tend to pick the safest, blandest ideas.
- Run the same source through two of the listed models and compare — LinkedIn register and X-thread momentum vary noticeably by model, so pick per platform.
- Always check posts against the source for accuracy — the rewrite step occasionally sharpens a hedged claim into a stronger one the source never made.
FAQ
What does the "Social Media Post Rewriter" system prompt do?
Turns long-form content into platform-native posts for LinkedIn, X and Threads — rewritten, not compressed, in your brand voice. It belongs to the Writing & Copy category and is free to copy and adapt.
Which models work well with this prompt?
We recommend running it with GPT-4o and Claude Sonnet 4.5 and Gemini 2.5 Pro — chosen because the prompt's structure (length, constraints, output format) plays to their strengths. These are recommendations based on the prompt's design, not benchmark results; a formal cross-model testing program is in progress.
How do I customize this prompt?
Replace the placeholders before use: "brand_voice" (Description of the voice to write in (e.g. "dry, slightly self-deprecating founder; short sentences; no emojis").). Then paste the whole text as the system message of your chat or API call.