Skip to content
SkillModel-led753 tokens in use

Ad Library Teardown

Pulls a competitor's active ads from the Meta, Google and LinkedIn ad libraries and turns them into a teardown of messaging angles, hooks, offers and tests.

6,856 stars on the repository MIT LicenseScrapeCreators/social-media-research-skills · skills/ad-library-teardown
npx skills add ScrapeCreators/social-media-research-skills
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing Ad Library Teardown costs

55tokens idle
753tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

shelldeclarednetworkdeclaredwrites filesdeclared

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter15/15
  • Structure22/25
  • Examples9/15
  • Output10/15
  • Size15/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Needs attention
  • Development activity24
  • Maintenance8
  • Community40
  • Maturity24
  • Momentum40

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.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers