# Refresh an old post for reposting

> Use when an old post performed well and you want to run it again without it reading as a lazy recycle.

## Fill in before running

- `{{ORIGINAL_DATE}}`
- `{{ORIGINAL_POST}}`
- `{{PLATFORM}}`
- `{{WHAT_CHANGED}}`

## Prompt

```
You are refreshing an old social post so it can run again.

Original post, published {{ORIGINAL_DATE}}:
"""
{{ORIGINAL_POST}}
"""
Platform: {{PLATFORM}}
What has changed since then: {{WHAT_CHANGED}}

Step 1. Audit the original. List: claims that may now be out of date, figures that need rechecking, references to tools, prices, or events that have moved on, and anything that reads as dated in tone. For each, say whether it is definitely stale, possibly stale, or still fine. Do not guess at current facts - mark anything you cannot verify from the input as [VERIFY].

Step 2. Write three refreshed versions:
A. Same argument, updated specifics, tightened by at least 20 percent.
B. The same argument told through a different opening and a different example.
C. The argument revisited: explicitly written as a follow-up that says what has changed since, and where the original was wrong or incomplete.

Rules:
- Version C must name at least one thing the original got wrong or oversimplified. If nothing was wrong, say so plainly rather than inventing a mea culpa.
- Do not add statistics not present in the original or in what I told you changed.
- No em dashes, no "I posted this a year ago and it still holds", no closing paragraph restating the opening.

Finish by recommending one of the three and giving the reason in one sentence.
```

## Getting a better result

- Version C almost always beats a straight repost because it gives the audience a reason to read again.
- Work through the [VERIFY] list before publishing; stale figures are the fastest way to lose credibility.
- Keep a note of which originals you have refreshed so you do not run the same argument three times a year.

---

From the QuQi prompt library - https://www.quqi.io/prompts/evergreen-repost-refresh
