vantage-ads — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited vantage-ads (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Public ad libraries are the single highest-signal competitive source — they reveal a competitor's actual offers, hooks, audiences, and (via ad longevity) what's working. This skill turns them into messaging and offer intelligence.
Web-only, all public. Sourcing in ../vantage/references/data-sources.md; score with scoring-framework.md §4.
| Channel | Source | What you get |
|---|---|---|
| Meta/Instagram | Meta Ad Library facebook.com/ads/library | Active creatives, full copy, "started running" date, variants, # active |
| Google/YouTube/Display | Google Ads Transparency Center adstransparency.google.com | Formats, creative, regions, date ranges |
| Company Page → Posts → Ads tab | B2B ad creative & copy | |
| TikTok | TikTok Creative Center Top Ads | Format/hook trends (region-limited) |
Blind spots (always disclose): Google Search text ads and several networks aren't fully visible. "No ads found" = not visible here, not "not advertising."
(footprint, not exact spend). Heavy + multi-platform = serious paid motion.
engine. A handful of stale ads = low investment.
profitable. Catalog these — they're the competitor's proven messages.
comparison, fear/FOMO, curiosity, offer-led). Which angle dominates?
the conversion mechanism — note strength and friction.
to homepage. Mismatch = a beatable weakness.
crowded; an under-served, resonant angle is an opening for the subject brand.
pre-validated swipe file of what converts this buyer. Highest-value output.
magnet)? Match or beat, or differentiate on something other than offer.
# Paid-Media Teardown — [set]
*Captured [date] · Sources: Meta Ad Library, Google ATC, [others]*
## Spend posture (footprint)
| Competitor | Meta active | Google formats | LinkedIn | Est. investment | Notes |
|-----------|------------:|---------------|---------|-----------------|-------|
## Proven messages (long-running ads = likely winners)
| Competitor | Hook | Angle | Offer | Running since | LP |
|-----------|------|-------|-------|---------------|----|
## Angle distribution across the set
[which angles are saturated vs open]
## Offer comparison
[trial/demo/discount/magnet strength per competitor]
## So what
- **Swipe-worthy proven angles** to test: …
- **Under-served angle / offer** the subject brand should own: …
- **Beatable weaknesses** (LP mismatch, stale creative): …
- **Blind spots:** [channels not publicly visible].~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.