Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Full multi-platform paid advertising audit with parallel subagent delegation. Analyzes Google Ads, Meta Ads, LinkedIn Ads, TikTok Ads, and Microsoft Ads accounts. Generates health score per platform and aggregate score. Triggers on: "audit", "full ad check", "analyze my ads", "account health check", "PPC audit", "ad account audit"
.claude/skills/miosa-osa-ads-audit/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | 7% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 223% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 60% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 5% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 46% | 0% |
> Comprehensive paid media audit across all active advertising platforms.
bash/ads audit /ads audit --platforms google meta
audit-google — Conversion tracking, wasted spend, structure, keywords, ads, settings (G01-G74)audit-meta — Pixel/CAPI health, creative fatigue, structure, audience (M01-M46)audit-creative — LinkedIn, TikTok, Microsoft creative checks + cross-platform synthesisaudit-tracking — LinkedIn, TikTok, Microsoft tracking + cross-platform tracking healthaudit-budget — LinkedIn, TikTok, Microsoft budget/bidding + cross-platform allocationaudit-compliance — All-platform compliance, settings, performance benchmarksAsk the user for available data. Accept any combination:
If no exports available, audit from screenshots or manual data entry.
| Platform | Category Weights | |----------|-----------------| | Google | Conversion 25%, Waste 20%, Structure 15%, Keywords 15%, Ads 15%, Settings 10% | | Meta | Pixel/CAPI 30%, Creative 30%, Structure 20%, Audience 20% | | LinkedIn | Tech 25%, Audience 25%, Creative 20%, Lead Gen 15%, Budget 15% | | TikTok | Creative 30%, Tech 25%, Bidding 20%, Structure 15%, Performance 10% | | Microsoft | Tech 25%, Syndication 20%, Structure 20%, Creative 20%, Settings 15% |
Aggregate = Sum(Platform_Score x Platform_Budget_Share)
Grade: A (90-100), B (75-89), C (60-74), D (40-59), F (<40)ADS-AUDIT-REPORT.md — Comprehensive multi-platform findingsADS-ACTION-PLAN.md — Prioritized recommendations (Critical > High > Medium > Low)ADS-QUICK-WINS.md — Items fixable in <15 minutes with high impactEach platform section includes:
IF severity == "Critical" OR severity == "High"
AND estimated_fix_time < 15 minutes
THEN flag as Quick Win
SORT BY (severity_multiplier x estimated_impact) DESC| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 11,781 | 5,512 | -53% | 1 | 1 | 0% | 1,821 | 1,331 | -27% | 0 | 0 | — |
case-02 | fail→fail | 39,278 | 17,548 | -55% | 1 | 1 | 0% | 7,683 | 3,905 | -49% | 0 | 0 | — |
case-03 | fail→pass | 49,895 | 45,159 | -9% | 1 | 1 | 0% | 8,257 | 8,798 | +7% | 0 | 0 | — |
case-04 | fail→pass | 9,073 | 19,119 | +111% | 1 | 1 | 0% | 1,252 | 4,044 | +223% | 0 | 0 | — |
case-05 | pass→pass | 13,963 | 20,061 | +44% | 1 | 1 | 0% | 2,334 | 4,948 | +112% | 0 | 0 | — |
case-06 | pass→pass | 10,310 | 13,566 | +32% | 1 | 1 | 0% | 1,780 | 3,430 | +93% | 0 | 0 | — |
case-07 | fail→pass | 15,027 | 18,898 | +26% | 1 | 1 | 0% | 2,480 | 3,964 | +60% | 0 | 0 | — |
case-08 | fail→pass | 14,164 | 9,650 | -32% | 1 | 1 | 0% | 2,136 | 2,239 | +5% | 0 | 0 | — |
case-09 | fail→pass | 11,806 | 9,495 | -20% | 1 | 1 | 0% | 1,909 | 2,788 | +46% | 0 | 0 | — |
case-10 | fail→pass | 12,841 | 22,213 | +73% | 1 | 1 | 0% | 2,115 | 1,897 | -10% | 0 | 0 | — |
case-11 | fail→pass | 14,322 | 3,734 | -74% | 1 | 1 | 0% | 2,077 | 1,621 | -22% | 0 | 0 | — |
case-12 | fail→pass | 5,698 | 2,669 | -53% | 1 | 1 | 0% | 1,026 | 1,502 | +46% | 0 | 0 | — |
case-13 | pass→pass | 5,314 | 2,708 | -49% | 1 | 1 | 0% | 745 | 1,431 | +92% | 0 | 0 | — |
case-14 | pass→pass | 7,345 | 2,469 | -66% | 1 | 1 | 0% | 848 | 1,373 | +62% | 0 | 0 | — |
case-15 | pass→pass | 6,566 | 3,665 | -44% | 1 | 1 | 0% | 872 | 1,658 | +90% | 0 | 0 | — |
case-16 | fail→pass | 11,734 | 4,742 | -60% | 1 | 1 | 0% | 1,553 | 1,813 | +17% | 0 | 0 | — |
case-17 | fail→pass | 8,387 | 2,275 | -73% | 1 | 1 | 0% | 1,235 | 1,343 | +9% | 0 | 0 | — |
case-18 | fail→pass | 10,957 | 2,726 | -75% | 1 | 1 | 0% | 1,735 | 1,454 | -16% | 0 | 0 | — |
case-19 | fail→fail | 13,158 | 6,671 | -49% | 1 | 1 | 0% | 1,609 | 1,909 | +19% | 0 | 0 | — |
case-20 | pass→pass | 10,909 | 4,274 | -61% | 1 | 1 | 0% | 1,574 | 1,687 | +7% | 0 | 0 | — |
case-21 | pass→pass | 3,625 | 4,726 | +30% | 1 | 1 | 0% | 679 | 1,527 | +125% | 0 | 0 | — |
case-22 | pass→pass | 14,681 | 14,070 | -4% | 1 | 1 | 0% | 2,361 | 3,531 | +50% | 0 | 0 | — |
case-23 | pass→pass | 18,214 | 23,217 | +27% | 1 | 1 | 0% | 2,684 | 3,350 | +25% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted, and 22 counted toward the lift figure. The other 1 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +48 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.