ad-library-teardown
installsforks
How to install ad-library-teardown?
scrapecreators/social-media-research-skills/ad-library-teardown
$npx -y skills add ScrapeCreators/social-media-research-skills --skill ad-library-teardownUse 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.
SKILL.md
| 1 | # Ad Library Teardown |
| 2 | |
| 3 | ## Overview |
| 4 | |
| 5 | 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. |
| 6 | |
| 7 | ## When to Use |
| 8 | |
| 9 | Use this skill when the user asks to: |
| 10 | |
| 11 | - analyze a competitor's active ads |
| 12 | - search Meta/Facebook, Google, or LinkedIn ad libraries |
| 13 | - extract ad hooks, CTAs, claims, offers, and landing page angles |
| 14 | - compare ad messaging across competitors |
| 15 | - summarize video ad transcripts |
| 16 | - generate ad test ideas from competitor ads |
| 17 | |
| 18 | ## Data Sources |
| 19 | |
| 20 | | Ad library | Search/list endpoint | Detail endpoint | Transcript endpoint | |
| 21 | |---|---|---|---| |
| 22 | | 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` | |
| 23 | | Google | `/v1/google/adLibrary/advertisers/search`, `/v1/google/company/ads` | `/v1/google/ad` | n/a | |
| 24 | | LinkedIn | `/v1/linkedin/ads/search` | `/v1/linkedin/ad` | n/a | |
| 25 | |
| 26 | ## Workflow |
| 27 | |
| 28 | 1. **Find the advertiser** |
| 29 | - Use company search endpoints when the user provides only a brand name. |
| 30 | - Use domain/advertiser/page IDs when available. |
| 31 | |
| 32 | 2. **Fetch active ads** |
| 33 | - Prefer active ads unless the user asks for historical analysis. |
| 34 | - Capture platform, advertiser/page, ad ID, start date, creative type, text, headline, CTA, destination URL, and source URL. |
| 35 | |
| 36 | 3. **Fetch details for representative ads** |
| 37 | - Enrich the ads with detail endpoints. |
| 38 | - For video Meta ads, fetch transcripts when available. |
| 39 | |
| 40 | 4. **Cluster messaging** |
| 41 | Group ads by: |
| 42 | - pain point |
| 43 | - persona |
| 44 | - offer |
| 45 | - proof/social proof |
| 46 | - feature/benefit |
| 47 | - objection handled |
| 48 | - comparison/alternative angle |
| 49 | - urgency/discount |
| 50 | |
| 51 | 5. **Extract swipeable elements** |
| 52 | - hooks |
| 53 | - headlines |
| 54 | - primary text patterns |
| 55 | - CTAs |
| 56 | - claims |
| 57 | - offers |
| 58 | - visual/creative concepts |
| 59 | |
| 60 | 6. **Recommend tests** |
| 61 | Suggest tests based on repeated patterns and gaps, not random ideas. |
| 62 | |
| 63 | ## Output Format |
| 64 | |
| 65 | ```markdown |
| 66 | # Ad Library Teardown: {brand} |
| 67 | |
| 68 | ## Summary |
| 69 | - Ads analyzed: {count} |
| 70 | - Platforms: Meta / Google / LinkedIn |
| 71 | - Main positioning: |
| 72 | - Strongest repeated offer: |
| 73 | |
| 74 | ## Messaging Angles |
| 75 | | Angle | Evidence | Example ads | Notes | |
| 76 | |---|---|---|---| |
| 77 | |
| 78 | ## Hooks and Headlines Swipe File |
| 79 | - "..." |
| 80 | - "..." |
| 81 | |
| 82 | ## Offers and CTAs |
| 83 | | Offer | CTA | Platform | Example | |
| 84 | |---|---|---|---| |
| 85 | |
| 86 | ## Video Transcript Notes |
| 87 | - [Ad](url): summary, hook, best quote |
| 88 | |
| 89 | ## What They Appear to Be Testing |
| 90 | 1. ... |
| 91 | 2. ... |
| 92 | |
| 93 | ## Recommended Tests for Us |
| 94 | 1. ... |
| 95 | 2. ... |
| 96 | 3. ... |
| 97 | |
| 98 | ## Sources |
| 99 | - [Ad](url) |
| 100 | ``` |
| 101 | |
| 102 | ## Common Pitfalls |
| 103 | |
| 104 | - 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. |
| 105 | - Do not ignore repeated ads. Repetition is often a useful signal. |
| 106 | - Do not invent spend, conversion rate, or targeting unless public data includes it. |
| 107 | - Do not skip video transcripts when the user asks for hooks or messaging from video ads. |
People who liked this also viewed
6 picksType
- seo-auditWhen the user wants to audit, review, or diagnose SEO issues on their site. Also use when the user mentions "SEO audit," "technical SEO," "why am I not ranking," "SEO issues," "on-page SEO," "meta tagSkillsJul 2026
- copywritingWhen the user wants to write, rewrite, or improve marketing copy for any page — including homepage, landing pages, pricing pages, feature pages, about pages, or product pages. Also use when the user sSkillsJul 2026
- marketing-psychologyWhen the user wants to apply psychological principles, mental models, or behavioral science to marketing. Also use when the user mentions 'psychology,' 'mental models,' 'cognitive bias,' 'persuasion,'SkillsJul 2026
- content-strategyWhen the user wants to plan a content strategy, decide what content to create, or figure out what topics to cover. Also use when the user mentions "content strategy," "what should I write about," "conSkillsJul 2026
- programmatic-seoWhen the user wants to create SEO-driven pages at scale using templates and data. Also use when the user mentions "programmatic SEO," "template pages," "pages at scale," "directory pages," "location pSkillsJul 2026
- marketing-ideasWhen the user needs marketing ideas, inspiration, or strategies for their SaaS or software product. Also use when the user asks for 'marketing ideas,' 'growth ideas,' 'how to market,' 'marketing stratSkillsJul 2026
