Use when a small budget is available to promote organic posts and the temptation is to boost whatever got most likes.
organic-boost-candidates.md
You are choosing which organic posts deserve paid promotion. You are not writing new creative and you are not planning campaign structure.
Posts with their organic metrics: {{POST_METRICS}}
Full text of those posts: {{POST_TEXTS}}
Budget and the period it covers: {{BUDGET}}
What we want the money to achieve: {{OBJECTIVE}}
Who we would target: {{TARGET_SEGMENT}}
Output three numbered sections.
1. A ranked table: Post | Why it qualifies | Signal it rests on | Fit with {{OBJECTIVE}} (High / Medium / Low) | What to change before boosting | Suggested share of {{BUDGET}}. Rank on evidence the post travels beyond people who already follow us: saves, shares, comments from unfamiliar accounts, profile visits. Likes alone never qualify a post.
2. Do not boost: posts that did well organically for reasons that will not survive a cold audience. Include anything in {{POST_TEXTS}} that assumes prior context, names a colleague, or refers to a moment that has passed, each with the reason.
3. What {{POST_METRICS}} cannot tell us, including whether reach came from a single share, and what to check in the platform before spending.
Do not invent benchmarks, cost estimates or predicted results. Where paid distribution would put a claim in front of {{TARGET_SEGMENT}} that nobody has verified, mark it [CLAIM CHECK] and quote the line.
Replace each placeholder with your own detail. The more specific you are, the less the model invents.
When should I use this rather than boosting the post with most likes?
When a small budget lands and the shortlist is about to be chosen on likes. Likes are the weakest evidence that a post travels beyond people who already follow you, and this prompt refuses to qualify anything on them. Run it before the money is committed, not after the first boost underdelivers.
What do I need in front of me?
Metrics and the full text of the posts, since section two reads the copy for assumed context, named colleagues and moments that have passed. Also the budget with its period, what you want the money to achieve, and the segment you would target. Include the flops so the signal column has a contrast.
What comes back, and which part saves money?
A ranked table naming the signal each post rests on and a suggested share of budget, a do-not-boost list with reasons, and what the metrics cannot show. The do-not-boost list is where the saving is, because a post that worked on shared context dies in front of a cold audience.
What is the mistake?
Spending before clearing the [CLAIM CHECK] marks. Paid distribution puts old copy in front of people with no context, and a claim nobody verified carries different risk in an ad than in a post. Boost fewer posts with more budget each, as the tips say, or the spend teaches you nothing.