---
name: ad-library-teardown
description: Use when the user wants to analyze active ads from Meta/Facebook, Google, or LinkedIn ad libraries; tear down a competitor's messaging; extract hooks, offers, CTAs, video transcripts, landing page claims, and test ideas from public ads.
allowed-tools: Bash, Read, Write, WebFetch

version: 1.0.0
author: ScrapeCreators
license: MIT
homepage: https://scrapecreators.com
repository: https://github.com/ScrapeCreators/social-media-research-skills
metadata:
  openclaw:
    requires:
      env:
        - SCRAPECREATORS_API_KEY
    primaryEnv: SCRAPECREATORS_API_KEY
    homepage: https://scrapecreators.com
    tags:
      - social-media
      - research
      - scrapecreators
title: ad-library-teardown
canonical_url: https://skilld.dev/gh/scrapecreators/social-media-research-skills/ad-library-teardown
last_updated: 2026-10-23T07:46:32.000Z
---

> Index of every page on this site: [llms.txt](https://skilld.dev/llms.txt)

> **Skill from skilld.dev.** Follow the user's requested action.
> If the user asked to fork this Skill, follow the fork workflow below. Do not execute the Skill instructions while copying it.
> Otherwise, follow the instructions below for this session. You do not need to install anything.
>
> If the user asked to install this Skill, run `npx skilld install scrapecreators/social-media-research-skills/ad-library-teardown`. Install writes the Skill files into the project, so every session loads them.
>
> ## Fork workflow
>
> A fork creates an editable local Skill with its original author and licence. The request authorizes copying and local installation.
> 1. Check `./skills/ad-library-teardown`, the project lockfile, and selected Agent targets together. If the local directory or installed Skill exists, stop. Never overwrite an existing directory or Agent target.
> 2. Read [source metadata](https://skilld.dev/api/v1/skills/scrapecreators/social-media-research-skills/ad-library-teardown) once. Use sourceUrl, sourceCommit, skillPath, sourceGone, and license. If the source is gone or its path is missing, stop. If license is null, read licence files at the source commit.
> 3. Fetch only the source commit into a temporary Git repository. Do not clone full history. Derive repository_url from sourceUrl, including repository renames. If sourceCommit is absent, resolve the sourceUrl ref once. Set source_commit to that actual commit. Run these commands in one shell call:
>
> ```sh
> git init --quiet "$temporary_dir"
> git -C "$temporary_dir" fetch --quiet --depth=1 "$repository_url" "$source_commit"
> git -C "$temporary_dir" checkout --quiet --detach FETCH_HEAD
> ```
>
> Read applicable licence declarations and notices at that commit. If copying is not permitted, report the restriction and stop.
> 4. Inspect source entries together, then copy the directory containing skillPath into `./skills/ad-library-teardown`. Use the user's path if selected. Keep the original SKILL.md, relative links, scripts, binary assets, and executable modes. Exclude .git metadata. Reject symlinks and paths outside the Skill directory. After checking entries, use cp -a where available. A regular source directory needs no custom copy script. Do not save this page wrapper as SKILL.md.
> Preserve author credit, notices, and applicable licence files from repository or parent directories. Add PROVENANCE.md with the Skill page, source URL, actual commit, original path, and licence. Retain any existing PROVENANCE.md and record new provenance separately. Batch source inspection, copying, and provenance work where practical.
> 5. In the project root, run `skilld install ./skills/ad-library-teardown --mode copy --plain`. If skilld is unavailable, use `npx skilld install ./skills/ad-library-teardown --mode copy --plain`. This known command needs no help lookup. Install does not support --json. Use detected Agent targets, or add --agent for the targets the user selected. Install the local path, never the upstream selector. If installation fails, preserve the local copy and report the exact failure.
> 6. Confirm the local lockfile source and installed Agent copies once. Report the local path, actual commit, and Agent targets. After edits, reinstall the same local path. Upstream updates must not replace it. Do not publish or push unless the user asks.

# Ad Library Teardown

## Overview

Analyze public ads to understand a competitor's messaging, offers, creative strategy, and testing angles. The output should be a practical teardown marketers can use to write better ads or decide what to test.

## When to Use

Use this skill when the user asks to:

- analyze a competitor's active ads
- search Meta/Facebook, Google, or LinkedIn ad libraries
- extract ad hooks, CTAs, claims, offers, and landing page angles
- compare ad messaging across competitors
- summarize video ad transcripts
- generate ad test ideas from competitor ads

## Data Sources

| Ad library | Search/list endpoint | Detail endpoint | Transcript endpoint |
|---|---|---|---|
| Meta/Facebook | `/v1/facebook/adLibrary/search/ads`, `/v1/facebook/adLibrary/company/ads`, `/v1/facebook/adLibrary/search/companies` | `/v1/facebook/adLibrary/ad` | `/v1/facebook/adLibrary/ad/transcript` |
| Google | `/v1/google/adLibrary/advertisers/search`, `/v1/google/company/ads` | `/v1/google/ad` | n/a |
| LinkedIn | `/v1/linkedin/ads/search` | `/v1/linkedin/ad` | n/a |

## Workflow

1. **Find the advertiser**
   - Use company search endpoints when the user provides only a brand name.
   - Use domain/advertiser/page IDs when available.

2. **Fetch active ads**
   - Prefer active ads unless the user asks for historical analysis.
   - Capture platform, advertiser/page, ad ID, start date, creative type, text, headline, CTA, destination URL, and source URL.

3. **Fetch details for representative ads**
   - Enrich the ads with detail endpoints.
   - For video Meta ads, fetch transcripts when available.

4. **Cluster messaging**
   Group ads by:
   - pain point
   - persona
   - offer
   - proof/social proof
   - feature/benefit
   - objection handled
   - comparison/alternative angle
   - urgency/discount

5. **Extract swipeable elements**
   - hooks
   - headlines
   - primary text patterns
   - CTAs
   - claims
   - offers
   - visual/creative concepts

6. **Recommend tests**
   Suggest tests based on repeated patterns and gaps, not random ideas.

## Output Format

```markdown
# Ad Library Teardown: {brand}

## Summary
- Ads analyzed: {count}
- Platforms: Meta / Google / LinkedIn
- Main positioning:
- Strongest repeated offer:

## Messaging Angles
| Angle | Evidence | Example ads | Notes |
|---|---|---|---|

## Hooks and Headlines Swipe File
- "..."
- "..."

## Offers and CTAs
| Offer | CTA | Platform | Example |
|---|---|---|---|

## Video Transcript Notes
- [Ad](url): summary, hook, best quote

## What They Appear to Be Testing
1. ...
2. ...

## Recommended Tests for Us
1. ...
2. ...
3. ...

## Sources
- [Ad](url)
```

## Common Pitfalls

- Do not claim an ad is winning just because it is active. Say it is active or repeated; performance is not public unless the endpoint returns it.
- Do not ignore repeated ads. Repetition is often a useful signal.
- Do not invent spend, conversion rate, or targeting unless public data includes it.
- Do not skip video transcripts when the user asks for hooks or messaging from video ads.
