Prompt library
Copy-paste prompts that tell Claude or ChatGPT what ads to make this week, and why. Each one is built on a real experiment Meta advertisers run every week.
11 prompts · Free to copy
Catch winning ads as they wear out and ship fresh versions before CPA climbs.
Look at the last 7 days of ad performance. Find our top-spending ads where frequency is going up and CTR is dropping. Make 5 new versions of each with a new image, model, or headline, but keep the persona, angle and format the same.
Mine reviews and comments for reasons to buy you aren't using in ads yet.
Look at the last 30 days of reviews and ad comments from our top persona. What reasons for buying, or results, do they talk about that we're not using in our ads yet? Make 5 ads for each new angle, keeping the persona and format the same.
Put your best persona and angle into formats you haven't tried yet.
Look at the last 7 days of ad performance and find our best persona-angle combo. Then find 3 formats in our swipe file we haven't tried with it yet, and build it in each one, keeping the persona and angle the same.
Turn this week's best 5-star reviews into testimonial ads.
Look at the last 7 days of 5-star reviews. Pick the ones where the customer talks about a specific result or a doubt they got over. Turn each one into a testimonial ad, keeping the persona and angle the same.
Find the hesitations that stop people buying and answer them head on.
Look at the last 30 days of ad comments, support tickets and return reasons. What hesitations keep coming up, like fit, sizing or fabric? Make 3 ads per objection that tackle it head on, keeping the persona the same.
Take a winning ad and run it for every color and matching product.
Look at the last 7 days of ad performance and our product catalog. Find winning ads with a product that comes in other colors or has a matching product. Make the same ad for each one, keeping the persona, angle and format the same.
Spot a customer group you aren't targeting and build a full funnel for them.
Look at the last 30 days of customer reviews and post-purchase surveys. Is anyone describing themselves as part of a group we're not already targeting or testing? Pick the most promising one and make 10 TOF, 10 MOF and 10 BOF ads for them, keeping the product the same.
See who competitors' long-running ads call out, and test that persona yourself.
Look at competitor ads in the Meta Ad Library that have been running for 30+ days. Who are they calling out that we aren't? Pick the most promising persona and make 10 TOF, 10 MOF and 10 BOF ads for them, keeping the product the same.
Get ads ready for the next season change or holiday before it arrives.
Look at the calendar and weather for the next 4-6 weeks. Is a season change or holiday coming up that changes how our customers use our products? If so, make 5 ads per persona for our best product for that season, keeping the angle and format the same and adding the seasonal hook.
Tie your product to what your customers care about this week, or skip it.
Look at what's happening this week in the news and trends, plus any upcoming events. Is there anything one of our personas actually cares about? If so, make 5 ads tying it to our product, keeping the persona the same. If not, skip it this week.
Announce every new product and restock with your winning persona and angle.
Look at the product catalog for anything new or restocked in the last 7 days. Make 5 ads for each one using our current winning persona and angle.
A prompt is only as good as the data behind it. These prompts ask for ad performance, reviews, comments and your catalog, so the setup that matters is getting that data in front of the model.
Create a project (both Claude and ChatGPT have them) and add your brand basics: what you sell, who buys it, your voice, your best ads. Every prompt you run in that project starts from that context instead of from zero.
Both tools can connect to outside apps. Connect the ones your prompt needs: Shopify for your catalog, Meta Ads for performance, and your reviews or helpdesk app for reviews and tickets. If a connector isn't available, export the data as a CSV and attach it.
Ask it to show the ads, reviews or products it picked before it writes anything. A wrong pick early on means a whole batch of wrong ads.
You'll get angles, headlines and creative direction. Build them in your design tool, or have an image model render them in 1:1, 4:5 or 9:16 for Meta placements.
Most AI ads look random because the prompt asks for "some ads". A good prompt names what changes, what stays the same, and what data it should decide from.
Product, persona, angle and format. Each prompt changes one and keeps the rest the same, so when an ad wins you know why.
Exploit wins more of the market you're in. Explore finds new markets, and a new market is really just a new persona. Seasonal captures moment-in-time spikes.
Performance data tells you what's working, and it feeds exploit. Customer data (reviews, surveys, comments) tells you what to try next, and it feeds explore.
You probably launch ads in weekly batches anyway. Each prompt looks at a different slice of data on batch day, which is why they all run on Mondays by default.
A set of instructions you paste into an AI tool like Claude or ChatGPT so it decides what ads to make and writes them. A good one names the data to look at, the one thing to change, and what to keep the same.
Yes, with the right data. Both can pick angles, write headlines and draft creative direction from your reviews, comments and performance. Connect your store and ad account, or attach exports, so they work from your numbers instead of guesses.
Most brands launch in weekly batches. Refresh an ad when its frequency rises and CTR drops, which the fatigue refresh prompt checks for every week.
Exploit ads win more of the market you already sell to: new versions, new angles and new formats for your current personas. Explore ads test a new persona, which is how you find a new market.
They work best with them. Without connectors the model will ask you to paste the data, so have your ad performance, reviews and catalog exports ready.
Yes. All 11 prompts are free to copy, change and share.
Yes. In StaticAds.ai any prompt here can become an Automation that runs on your schedule, Mondays at 5:00 AM by default, and builds the ads for you.
StaticAds.ai runs any of these prompts on a schedule with your catalog, swipe file and brand, and sends the new ads to Slack when they're ready.