Skill · compare-app-ads
Compare the paid ads of several apps.
Name two to six apps. Your agent reads the Apple, Meta, Google and TikTok ad libraries for each one and hands over their ads: library, format, text, first day and a link for every ad. Real run on Duolingo, Babbel and Busuu: 277 ads for $0.001.
Paste this one prompt into Claude Code, Codex, Cursor or any agent with a shell. It sets Whizbrew up by itself, then goes straight into the question.
Set up Whizbrew for me: read https://whizbrew.com/llms.txt and follow it. Then compare the ads of <your app and two competitors>.
Want to try it first? Paste it as it ran here:
Set up Whizbrew for me: read https://whizbrew.com/llms.txt and follow it. Then compare the ads of Duolingo, Babbel and Busuu.
Already have Whizbrew? Ask the question alone:
compare the ads of <your app and two competitors>
The sentence typed
compare the ads of Duolingo, Babbel and Busuu
Duolingo, Babbel and Busuu · November 20, 2026 · 277 rows · 24 calls · $0.001
12 of the 277 ads, the newest of each app
Real rows from one real run on November 20, 2026, typed into Claude Code in a terminal, with only the Whizbrew MCP server installed. Public data only; every row links to its source.
What it took
- First ads on screen: 1 min 25 s (after the sentence was sent)
- Whole run: 1 min 27 s (until the comparison table)
- Ads found: 277 (Babbel 101, Busuu 90, Duolingo 86)
- Price of the run: $0.001 (24 calls; a call with no data is free)
Measured on the run of November 20, 2026; times from the run's timed transcript.
What your agent does.
- It finds each app. The App Store listing gives the app’s id, and the ad libraries are asked which advertisers carry its name.
- It reads every library. Apple’s ad repository, the app’s Meta page, its Google advertiser and TikTok’s Top Ads, for each app.
- It shows the ads. The newest ads per app, each with its library, format, text, first day and a link.
- It ends with a comparison. Ads by library, the newest start, what runs now, the main format, hashtag reach and store rating, plus one file with every ad.
Good to know
- It reads public ad libraries only. It does not see spend, impressions or ads a library does not publish.
- Apple’s ad repository covers EU storefronts, and TikTok’s Top Ads lists only the ads TikTok picks, so an app can show none there.
- An advertiser whose name is not the app’s name is not counted, so ads run under a parent company can be missed.
This run called 8 Whizbrew tools: ads.find_advertiser, apple_ads.app_ads, appstore.app, appstore.search, google.ads_by_advertiser, meta_ads.advertiser, tiktok.hashtag, tiktok_ads.search.
The skill file your agent reads: https://whizbrew.com/skills/compare-app-ads/SKILL.md
Questions, answered.
How do I see the ads my competitors run?
Connect Whizbrew to an agent with a shell, such as Claude Code, Codex or Cursor, and type “compare the ads of” followed by the apps. The agent runs the skill and lists their ads with a link to each one.
Which ad libraries does it read?
Apple’s App Store ad repository, Meta’s Ad Library, Google’s Ads Transparency Center and TikTok’s Top Ads. Each ad shows which library it came from.
How many apps can I compare at once?
Two to six apps in one run. Every app gets the same checks, so the comparison is fair.
What does a run cost?
You pay per call that returns data, from prepaid credit, with no subscription. The price of the run shown on this page is on the page, with its date.
Can I check the ads myself?
Yes. Every row links to its source: the ad in its public library, or the app’s store page for App Store ads. The table on this page is the output of the run dated above, not a mock-up.