Competitor Ad Analyzer
Ad library teardown

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.
---
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: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.
Manual install (npx, ZIP)
npx skills add ScrapeCreators/social-media-research-skills --skill ad-library-teardown -g -a claude-codemkdir -p ~/.claude/skills && curl -sL https://codeload.github.com/ScrapeCreators/social-media-research-skills/tar.gz/64ba7b4dea71 \
| tar -xz -C ~/.claude/skills --strip-components=2 social-media-research-skills-64ba7b4dea71/skills/ad-library-teardownNew-Item -ItemType Directory -Force "$HOME\.claude\skills" | Out-Null; Invoke-WebRequest "https://m.agentalley.io/zip/46c9b7409b9c9bc8b3a1/ad-library-teardown.zip" -OutFile "$env:TEMP\ad-library-teardown.zip"; Expand-Archive "$env:TEMP\ad-library-teardown.zip" -DestinationPath "$HOME\.claude\skills" -ForceConnects with Agent Alley MCP · agentalley.io/mcp
Files included
SKILL.md3.7 KB
Read the files here
ScrapeCreators/
Show the full text130 lines
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 |
/v1/google/adLibrary/advertisers/search, /v1/google/company/ads |
/v1/google/ad |
n/a | |
/v1/linkedin/ads/search |
/v1/linkedin/ad |
n/a |
Workflow
Find the advertiser
- Use company search endpoints when the user provides only a brand name.
- Use domain/advertiser/page IDs when available.
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.
Fetch details for representative ads
- Enrich the ads with detail endpoints.
- For video Meta ads, fetch transcripts when available.
Cluster messaging Group ads by:
- pain point
- persona
- offer
- proof/social proof
- feature/benefit
- objection handled
- comparison/alternative angle
- urgency/discount
Extract swipeable elements
- hooks
- headlines
- primary text patterns
- CTAs
- claims
- offers
- visual/creative concepts
Recommend tests Suggest tests based on repeated patterns and gaps, not random ideas.
Output Format
# 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.
| 1 | |
| 2 | name ad-library-teardown |
| 3 | 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. |
| 4 | allowed-tools Bash, Read, Write, WebFetch |
| 5 | |
| 6 | version 1.0.0 |
| 7 | author ScrapeCreators |
| 8 | license MIT |
| 9 | homepage https://scrapecreators.com |
| 10 | repository https://github.com/ScrapeCreators/social-media-research-skills |
| 11 | metadata |
| 12 | openclaw |
| 13 | requires |
| 14 | env |
| 15 | - SCRAPECREATORS_API_KEY |
| 16 | primaryEnv SCRAPECREATORS_API_KEY |
| 17 | homepage https://scrapecreators.com |
| 18 | tags |
| 19 | - social-media |
| 20 | - research |
| 21 | - scrapecreators |
| 22 | |
| 23 | |
| 24 | # Ad Library Teardown |
| 25 | |
| 26 | ## Overview |
| 27 | |
| 28 | 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. |
| 29 | |
| 30 | ## When to Use |
| 31 | |
| 32 | Use this skill when the user asks to: |
| 33 | |
| 34 | analyze a competitor's active ads |
| 35 | search Meta/Facebook, Google, or LinkedIn ad libraries |
| 36 | extract ad hooks, CTAs, claims, offers, and landing page angles |
| 37 | compare ad messaging across competitors |
| 38 | summarize video ad transcripts |
| 39 | generate ad test ideas from competitor ads |
| 40 | |
| 41 | ## Data Sources |
| 42 | |
| 43 | | Ad library | Search/list endpoint | Detail endpoint | Transcript endpoint | |
| 44 | |---|---|---|---| |
| 45 | | 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` | |
| 46 | | Google | `/v1/google/adLibrary/advertisers/search`, `/v1/google/company/ads` | `/v1/google/ad` | n/a | |
| 47 | | LinkedIn | `/v1/linkedin/ads/search` | `/v1/linkedin/ad` | n/a | |
| 48 | |
| 49 | ## Workflow |
| 50 | |
| 51 | **Find the advertiser** |
| 52 | Use company search endpoints when the user provides only a brand name. |
| 53 | Use domain/advertiser/page IDs when available. |
| 54 | |
| 55 | **Fetch active ads** |
| 56 | Prefer active ads unless the user asks for historical analysis. |
| 57 | Capture platform, advertiser/page, ad ID, start date, creative type, text, headline, CTA, destination URL, and source URL. |
| 58 | |
| 59 | **Fetch details for representative ads** |
| 60 | Enrich the ads with detail endpoints. |
| 61 | For video Meta ads, fetch transcripts when available. |
| 62 | |
| 63 | **Cluster messaging** |
| 64 | Group ads by: |
| 65 | pain point |
| 66 | persona |
| 67 | offer |
| 68 | proof/social proof |
| 69 | feature/benefit |
| 70 | objection handled |
| 71 | comparison/alternative angle |
| 72 | urgency/discount |
| 73 | |
| 74 | **Extract swipeable elements** |
| 75 | hooks |
| 76 | headlines |
| 77 | primary text patterns |
| 78 | CTAs |
| 79 | claims |
| 80 | offers |
| 81 | visual/creative concepts |
| 82 | |
| 83 | **Recommend tests** |
| 84 | Suggest tests based on repeated patterns and gaps, not random ideas. |
| 85 | |
| 86 | ## Output Format |
| 87 | |
| 88 | |
| 89 | # Ad Library Teardown: {brand} |
| 90 | |
| 91 | ## Summary |
| 92 | - Ads analyzed: {count} |
| 93 | - Platforms: Meta / Google / LinkedIn |
| 94 | - Main positioning: |
| 95 | - Strongest repeated offer: |
| 96 | |
| 97 | ## Messaging Angles |
| 98 | | Angle | Evidence | Example ads | Notes | |
| 99 | |---|---|---|---| |
| 100 | |
| 101 | ## Hooks and Headlines Swipe File |
| 102 | - "..." |
| 103 | - "..." |
| 104 | |
| 105 | ## Offers and CTAs |
| 106 | | Offer | CTA | Platform | Example | |
| 107 | |---|---|---|---| |
| 108 | |
| 109 | ## Video Transcript Notes |
| 110 | - [Ad](url): summary, hook, best quote |
| 111 | |
| 112 | ## What They Appear to Be Testing |
| 113 | 1. ... |
| 114 | 2. ... |
| 115 | |
| 116 | ## Recommended Tests for Us |
| 117 | 1. ... |
| 118 | 2. ... |
| 119 | 3. ... |
| 120 | |
| 121 | ## Sources |
| 122 | - [Ad](url) |
| 123 | |
| 124 | |
| 125 | ## Common Pitfalls |
| 126 | |
| 127 | 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. |
| 128 | Do not ignore repeated ads. Repetition is often a useful signal. |
| 129 | Do not invent spend, conversion rate, or targeting unless public data includes it. |
| 130 | Do not skip video transcripts when the user asks for hooks or messaging from video ads. |
Details
- Version
- 1.0.0
- Updated
- Aug 26, 2026
- License
- MIT
- Stars on the repo
- ★ 2,619
- Checked
- Source
- ScrapeCreators/social-media-research-skills ↗
- Creator
- ScrapeCreators · 13 listings
Similar skills
See all →
SkillProduct Listing Visual Creator
SkillPricing Page Builder
SkillArticle Opening Hooks
SkillEcommerce Landing Page Designer
SkillDirect Response Copywriter
SkillConverting Headline WriterMore from ScrapeCreators
SkillCreator Audience Analyzer
SkillAudience Comment Mining
SkillCompetitor Social Media Research
SkillSocial Content Repurposer
SkillCreator Account Analyzer
SkillInfluencer Prospect Finder