Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Microsoft/Bing Ads deep analysis covering search, Performance Max, Audience Network, and Copilot integration. Evaluates 20 checks with focus on Google import validation, unique Microsoft features, and cost advantage assessment. Triggers on: "Microsoft Ads", "Bing Ads", "Bing PPC", "Copilot ads", "Microsoft campaign", "Bing audit"
.claude/skills/miosa-osa-ads-microsoft/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-06 | ✗→✓ | ▲ Improved | 17% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 39% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -5% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 72% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 28% | 0% |
> 20-check audit of Microsoft (Bing) Ads with Google import validation and Copilot assessment.
bash/ads microsoft
| Feature | Description | Priority | |---------|-------------|----------| | Multimedia Ads | Image-rich search ads | Medium | | Action Extension | CTA button in search ad | Medium | | Filter Link Extension | Filterable category links | Low | | LinkedIn Profile Targeting | Target by company, industry, job function | High (B2B) | | Copilot Chat Placement | Ads within Copilot conversations | High |
| Metric | Pass | Warning | Fail | |--------|------|---------|------| | CTR (Search) | >=2.83% | 1.5-2.83% | <1.5% | | CPC (Search) | <=$1.55 | $1.55-2.50 | >$2.50 | | CPC vs Google | 20-40% lower | 10-20% lower | Same or higher | | CVR vs Google | Within 20% | 20-50% lower | >50% lower | | Impression share (brand) | >=80% | 60-80% | <60% |
MICROSOFT-ADS-REPORT.md — Full 20-check findings with pass/warning/fail| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 36,248 | 46,799 | +29% | 1 | 1 | 0% | 5,488 | 9,285 | +69% | 0 | 0 | — |
case-02 | fail→fail | 50,352 | 34,741 | -31% | 1 | 1 | 0% | 8,274 | 7,145 | -14% | 0 | 0 | — |
case-03 | fail→fail | 36,278 | 44,295 | +22% | 1 | 1 | 0% | 5,588 | 6,562 | +17% | 0 | 0 | — |
case-04 | pass→pass | 19,815 | 13,260 | -33% | 1 | 1 | 0% | 2,682 | 3,466 | +29% | 0 | 0 | — |
case-05 | fail→fail | 18,092 | 29,793 | +65% | 1 | 1 | 0% | 2,761 | 5,479 | +98% | 0 | 0 | — |
case-06 | fail→pass | 11,742 | 7,010 | -40% | 1 | 1 | 0% | 1,745 | 2,049 | +17% | 0 | 0 | — |
case-07 | fail→pass | 12,984 | 11,959 | -8% | 1 | 1 | 0% | 2,097 | 2,916 | +39% | 0 | 0 | — |
case-08 | pass→pass | 13,479 | 16,357 | +21% | 1 | 1 | 0% | 2,238 | 3,676 | +64% | 0 | 0 | — |
case-22 | pass→pass | 26,222 | 21,061 | -20% | 1 | 1 | 0% | 3,049 | 4,609 | +51% | 0 | 0 | — |
case-09 | pass→pass | 5,683 | 9,792 | +72% | 1 | 1 | 0% | 937 | 2,484 | +165% | 0 | 0 | — |
case-10 | fail→pass | 13,818 | 5,725 | -59% | 1 | 1 | 0% | 1,880 | 1,791 | -5% | 0 | 0 | — |
case-11 | fail→pass | 12,085 | 13,813 | +14% | 1 | 1 | 0% | 1,771 | 3,046 | +72% | 0 | 0 | — |
case-12 | pass→pass | 12,026 | 9,887 | -18% | 1 | 1 | 0% | 1,868 | 2,466 | +32% | 0 | 0 | — |
case-13 | fail→pass | 17,381 | 12,446 | -28% | 1 | 1 | 0% | 2,205 | 2,812 | +28% | 0 | 0 | — |
case-14 | pass→pass | 16,506 | 18,792 | +14% | 1 | 1 | 0% | 2,236 | 3,668 | +64% | 0 | 0 | — |
case-15 | fail→fail | 20,030 | 19,108 | -5% | 1 | 1 | 0% | 3,280 | 4,086 | +25% | 0 | 0 | — |
case-16 | fail→pass | 13,529 | 5,810 | -57% | 1 | 1 | 0% | 1,742 | 1,997 | +15% | 0 | 0 | — |
case-17 | pass→pass | 12,813 | 2,734 | -79% | 1 | 1 | 0% | 1,205 | 1,348 | +12% | 0 | 0 | — |
case-18 | fail→pass | 7,102 | 2,357 | -67% | 1 | 1 | 0% | 1,070 | 1,384 | +29% | 0 | 0 | — |
case-19 | fail→pass | 12,681 | 4,665 | -63% | 1 | 1 | 0% | 1,694 | 1,601 | -5% | 0 | 0 | — |
case-20 | pass→fail | 17,971 | 25,262 | +41% | 1 | 1 | 0% | 3,046 | 5,166 | +70% | 0 | 0 | — |
case-21 | pass→pass | 28,271 | 19,551 | -31% | 1 | 1 | 0% | 4,207 | 4,701 | +12% | 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. 22 cases were attempted. The headline lift of +32 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
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.