Scrolling Meta Ad Library is fun; turning what you see into a brief your creative team can act on is not. These 15 prompts force a structured teardown — hook, offer, visual, social proof, fatigue cycle, audience signal — so you walk away with a ranked list of angles to test, not a vague “we should do video too” gut feeling. Paste any model you already pay for (GPT-5.5, Claude Sonnet 4.6, or Gemini 3.1 Pro all handle these without a custom GPT) and feed it the ad copy plus a visual description.
TL;DR
- The teardown is only as good as the input: paste the actual ad copy and a written visual description, never a vague summary. Models cannot see the screenshot.
- Use Meta Ad Library’s new impression-range buckets and active/inactive toggle (both live for every ad since January 2026) to separate scaled winners from killed tests before you even open a prompt.
- Cluster across 50+ ads at a time; under 20 you cannot tell category saturation from a one-off outlier.
- Steal the angle, offer, and hook structure — never the exact creative. Copyright sits on the creative; the strategy is fair game.
- Prompts 1–14 do the analysis; prompt 15 synthesizes everything into a one-page sprint brief.
Who this is for
Paid-media buyers at DTC brands, performance creative leads, agency creative strategists, growth marketers running Meta / Google / TikTok stacks, and founders who want to understand a competitor’s ad strategy without paying for a $129/month spy tool.
Where to find the ads (June 2026)
Pull the ads first, then run the prompts. Each library exposes different signals:
| Source | Cost | Best signal it exposes | Hard limit |
|---|---|---|---|
Meta Ad Library (facebook.com/ads/library) | Free, public | Impression-range bucket (under 1K → 1M+) and active/inactive status on every ad since Jan 2026; rolling 12-month spend card on advertiser pages | No in-creative keyword search across the whole library; you start from a Page or keyword |
Google Ads Transparency Center (adstransparency.google.com) | Free, public | Verified advertiser’s ads across Search, Shopping, Display, YouTube, Maps, Play | No keyword-in-creative search — search by advertiser name or paste the landing-page domain |
| TikTok Creative Center → Top Ads | Free, advertiser login | Curated best-performing ads with engagement metrics, by industry and region | Curated, not comprehensive; it shows winners, not the full account |
TikTok Commercial Content Library (library.tiktok.com) | Free, public | Raw transparency: every paid ad, targeting params, reach, spend bands | EEA, UK, and Switzerland delivery only (as of April 2026) — no US data |
| Foreplay / Atria (third-party) | ~$49–$175 / ~$129 a month | Saved swipe files, cross-platform search, AI brief-building | Paid; subscription cost scales with team or tracked spend |
A “Low Impression Count” badge (under 100 impressions) now flags obvious tests inside Meta Ad Library, so skip those when hunting for proven creative.
When not to use these prompts
Skip them for brands not running paid ads — the library will be empty. Skip them too for legally sensitive verticals (CBD, supplements with claims, financial services) where competitor ads may themselves be non-compliant; copying a non-compliant claim makes it your problem, not your defense.
Prompt anatomy / structure formula
A competitor ad analysis prompt should always carry six elements:
- Role: who the AI plays (luxury copywriter / Amazon listing strategist / DTC brand voice / paid-ads hook writer).
- Context: product, brand voice, target buyer, platform, price tier, season — anything that shifts copy.
- Goal: one concrete deliverable — 5 bullets, a 150-word hero, 13 tags, 10 hook lines, a refund reply.
- Constraints: must / must-not (FTC claims, banned words, character limits, tone, no emoji, no superlatives).
- Output format: numbered list, table, JSON, or labeled blocks so you can paste straight into the seller backend.
- Examples / signal: 1-2 reference lines you like, or anti-examples (“not like this competitor”).
Best for
- Quarterly creative strategy review
- New-channel launch competitive scan
- Hook library building
- Creative-fatigue diagnosis
- Agency brief input
15 copy-ready prompt templates
1. Single-ad structural teardown
The default for any ad you screenshot from Meta Ad Library.
You are a paid-media creative strategist. Tear down the ad below into structural elements: hook (first 3 seconds / first sentence), problem framing, product reveal, demonstration, offer / CTA, social proof, end card. Mark which elements are strong, which are weak, what to steal and what to skip.
Ad description: {paste ad copy + visual description + caption}Variables to swap: ad copy, visual description, caption, runtime if video
Optimization: If teardown stays abstract, add: “For every element, quote the actual line or describe the exact visual frame. No generic descriptions like creative hook is strong.”
2. Hook-only extraction (10 ads at a time)
Below are the first 3 seconds / first sentences of 10 competitor ads. Extract just the hooks. Cluster them into types ({question, statistic, demo, contrarian, before-after, persona-callout}). Mark which clusters are over-saturated in the category and which are whitespace.
{paste 10 hooks}3. Offer-strategy map
For the 8 competitor ads below, extract just the offer mechanic ({% off, bundle, free shipping, free trial, money-back, gift with purchase, payment plan}). Tally which mechanics are most common, which are rare. Recommend an offer mechanic for {my brand} that stands out in the category.4. Visual-style audit
Below are visual descriptions of 6 competitor ads. Cluster the visual styles ({UGC-shaky, studio-clean, kitchen-lifestyle, animated-product-spin, founder-talking-head}). Recommend 2 visual styles {my brand} should test based on category whitespace.5. Creative-fatigue cycle detection
Competitor {brand} has run these ads over the last 90 days: {list of ad summaries + launch dates}. Identify their creative-fatigue cycle: when do they refresh, how aggressively do they iterate, do they kill or amplify winners. Output 1 hypothesis about their internal creative cadence.6. Audience-signal inference
For the ad below, what audience segments are they likely targeting? Read the visual, casting, language register, music or voiceover style, and offer for signals. Output 3 candidate audience hypotheses with the evidence for each.
{paste ad}7. Hook → angle library
From the 15 competitor hooks below, build a 5-angle library for my creative team: angle name, example hook from competitor, how to adapt for {my brand} without copying. Output as a 5-row table.
{paste hooks}8. Comparison-claim audit
Below is a competitor ad making a comparison claim. Audit: what they explicitly say, what they imply, what claims would require substantiation in {market}, whether {my brand} could make a similar (or counter) claim without legal risk.
{paste ad}9. TikTok vs Meta same-brand split
Below are the same competitor brand’s ads on Meta and TikTok. Map the differences: hook type, pacing, talent / casting, on-screen text density, offer placement. What does the split tell us about their platform strategy?
{paste both ads}10. Carousel / catalog ad structure
For the carousel / catalog ad below, analyze the slide sequence: card 1 hook, card 2-N pattern, last card CTA. What product-mix logic is at work ({hero + sister SKUs, price-tier ladder, occasion-grouped, persona-grouped})? Recommend a carousel structure for {my brand}.
{paste carousel}11. Influencer / UGC ad teardown
For the influencer / UGC ad below, separate what is "creator authenticity" from what is "scripted ad". Mark the seam: which line was likely written by the brand vs. by the creator. What can {my brand} learn about creator-brief structure from this?
{paste ad}12. Brand-vs-direct-response ratio
For competitor {brand} in {month}, score each of their ads as brand-building (no offer / soft CTA) or direct-response (explicit offer / hard CTA). What ratio are they running? What does that say about their funnel stage strategy? Recommend a ratio for {my brand}.13. Cross-market localization audit
Competitor {brand} runs different ads in {US, UK, DE, JP}. Below are 1 ad per market. Audit what localizes (tone, casting, offer mechanic, hook angle) vs. what stays consistent (visual style, product framing). What is the localization framework you would steal?
{paste 4 ads}14. Winning-ad signal hunt (long-running ads)
Below are 5 competitor ads that have been running for {N+} weeks (likely winners). Identify common DNA: hook type, offer, visual cue, length, audience signal. Output the shared DNA as a creative brief for {my brand}.
{paste 5 long-runners}15. Competitive teardown → creative brief
Synthesizes earlier analyses into a usable brief.
Combine the hook library, offer map, and visual-style audit above into a single 1-page creative brief for {my brand}'s next paid-ad sprint: 3 hooks to test, 2 visual styles, 1 offer mechanic, audience hypothesis, success metric. Voice: actionable, no fluff.Common mistakes
- Copying a competitor ad line-for-line — you inherit their problems and lose any brand voice differentiation.
- Analyzing ads without recording the date they ran — fresh ads and 12-week-old winners need different interpretation.
- Counting “we should do video too” as analysis — the angle / hook / offer is the lesson, not the format.
- Skipping legal review on comparison claims — competitor non-compliance is not your defense.
- Reading only top-spend competitors — sometimes the smartest creative comes from the upstart you have not heard of.
- Building a hook library without a “do not copy” column — same hook on similar brands fatigues the audience instantly.
- Letting AI describe ads it cannot actually see — paste the actual copy and visual description; do not let it imagine.
How to push results further
- Sort Meta Ad Library by the impression-range bucket and filter to active ads — a creative sitting in the 100K–500K or 1M+ band that is still running is the closest thing to a public “this is working” signal.
- Cross-check the advertiser’s rolling 12-month spend card (live on Meta advertiser pages since late 2025): a brand pouring budget into one angle is telling you that angle converts.
- For TikTok, pair Creative Center → Top Ads (curated winners, by industry) with the Commercial Content Library for raw EEA/UK/Switzerland transparency; outside Europe, fall back to organic discovery and a swipe tool.
- Keep a teardown doc with one tab per competitor; revisit quarterly. A swipe-file tool like Foreplay (from ~$49/month) automates the save step if manual screenshots stop scaling.
- Always write your own brand differentiator before tearing down a competitor — otherwise you absorb their positioning by osmosis.
- Build hook clusters across 50+ ads at a time; under 20 you cannot tell category saturation from a one-off outlier.
- Pair teardowns with your own ad-performance data. The lesson lives in the interaction between their creative and your results, not in absolute creative quality.
- Run a competitor scan within 48 hours of any major channel launch (new product, new market, new creator partnership).
FAQ
- Where can I see competitor ads for free?: Meta Ad Library (
facebook.com/ads/library, public, no login), Google Ads Transparency Center (adstransparency.google.com), and TikTok’s Commercial Content Library (library.tiktok.com, EEA/UK/Switzerland delivery only). Paid tools like Foreplay ($49–$175/month) or Atria ($129/month) add swipe files and cross-platform search. - Can I search Meta Ad Library by keyword inside the creative?: No. You search by advertiser Page name or a broad keyword that matches ad text; there is no full-text search across every ad’s copy. Google’s Transparency Center is stricter still — search by advertiser name or paste the landing-page domain.
- Is copying a competitor ad legal?: Copying the exact creative (image, video, script) carries copyright risk. Borrowing the angle, offer structure, or hook type is standard practice across the industry. Always rebuild it in your own brand voice.
- What metrics tell me a competitor ad is winning?: Runtime plus impression band is the cleanest public combination — an ad that has run 4+ weeks and sits in a high impression bucket (and is still active) is almost certainly performing. High creator engagement on a UGC piece is a secondary signal.
- Should AI write our final ads from the teardown?: Use it to draft 5–10 hook variations and a brief from the analysis (GPT-5.5, Claude Sonnet 4.6, and Gemini 3.1 Pro all work). Final creative selection and production stays with your team — the model has not seen the original screenshots and cannot judge production craft.
- How often should I run a teardown?: Lightly weekly (scroll the library), a full structured teardown quarterly, and an urgent scan within 48 hours whenever a competitor makes a major move.