Ad Library Teardown gives an agent a method for reading a competitor’s public ads. It finds the advertiser, fetches active ads, enriches representative ones with detail and video transcripts, and groups them by pain point, persona, offer, proof and objection.
The result is a marketer-ready report: a swipe file of hooks and headlines, a table of offers and CTAs, notes on video ads, what the advertiser appears to be testing, and test ideas for your own ads.
What You Get
- A messaging-angle table with evidence and example ads
- A swipe file of hooks, headlines and primary text patterns
- An offers and CTAs table by platform
- Notes on video ads built from Meta ad transcripts
- A list of what the advertiser appears to be testing and recommended tests for your own ads
Common Use Cases
- Reviewing a competitor’s active Meta ads before writing new creative
- Comparing ad messaging across several competitors
- Pulling hooks and claims from video ads through their transcripts
- Planning an ad test roadmap from repeated patterns and gaps
What Makes It Unique
Most ad research prompts stop at listing ads. This skill clusters them by angle, persona, offer and objection, then ties each recommended test to repeated patterns and gaps. It also states limits up front: an active ad is not proof of a winning ad, and spend, conversion and targeting are never invented.
Under The Hood
The skill is a single SKILL.md of instructions with no scripts. When used, the agent calls the ScrapeCreators REST API with curl or fetch, sending your API key from the SCRAPECREATORS_API_KEY environment variable, to search ad libraries, load ad details and fetch Meta video transcripts. Its frontmatter allows the shell, file reading and writing, and web fetches, so the agent can run commands, call the API over the network and save the report as a file.