Ads — Multi-Platform Paid Advertising Audit & Optimization
Comprehensive ad account analysis across all major platforms (Google, Meta,
LinkedIn, TikTok, Microsoft). Orchestrates 12 specialized sub-skills and
6 subagents.
Quick Reference
| Command |
What it does |
$ads audit |
Full multi-platform audit with parallel subagent delegation |
$ads google |
Google Ads deep analysis (Search, PMax, YouTube) |
$ads meta |
Meta Ads deep analysis (FB, IG, Advantage+) |
$ads youtube |
YouTube Ads specific analysis |
$ads linkedin |
LinkedIn Ads deep analysis (B2B, Lead Gen) |
$ads tiktok |
TikTok Ads deep analysis (Creative, Shop, Smart+) |
$ads microsoft |
Microsoft/Bing Ads deep analysis (Copilot, Import) |
$ads creative |
Cross-platform creative quality audit |
$ads landing |
Landing page quality assessment for ad campaigns |
$ads budget |
Budget allocation and bidding strategy review |
$ads plan <business-type> |
Strategic ad plan with industry templates |
$ads competitor |
Competitor ad intelligence analysis |
Orchestration Logic
When the user invokes $ads audit, delegate to subagents in parallel:
- Collect account data (exports, screenshots, or API access details)
- Detect business type and identify active platforms
- Spawn subagents: audit-google, audit-meta, audit-creative, audit-tracking, audit-budget, audit-compliance
- Collect results and generate unified report with Ads Health Score (0-100)
- Create prioritized action plan with Quick Wins
For individual commands ($ads google, $ads meta, etc.), load the relevant
sub-skill directly.
Multi-Agent Execution (Codex)
- Use
spawn_agent with worker role for each audit stream during full-account reviews.
- Use one
explorer agent to gather account structure/evidence before specialized checks.
- Use
wait to synchronize all delegated audits before computing the unified health score.
- Use the
default agent to synthesize conflicts, prioritize recommendations, and present final output.
Industry Detection
Detect business type from ad account signals:
- SaaS: trial_start/demo_request events, pricing page targeting, long attribution windows
- E-commerce: purchase events, product catalog/feed, Shopping/PMax campaigns
- Local Service: call extensions, location targeting, store visits, directions events
- B2B Enterprise: LinkedIn Ads active, ABM lists, high CPA tolerance ($50+), long sales cycle
- Info Products: webinar/course funnels, lead gen forms, low-ticket offers
- Mobile App: app install campaigns, in-app events, deep linking
- Real Estate: listing feeds, property-specific landing pages, geo-heavy targeting
- Healthcare: HIPAA compliance flags, healthcare-specific ad policies
- Finance: Special Ad Categories declared, financial products compliance
- Agency: multiple client accounts, white-label reporting needs
Quality Gates
Hard rules — never violate these:
- Never recommend Broad Match without Smart Bidding (Google)
- 3x Kill Rule: flag any ad group/campaign with CPA >3x target for pause
- Budget sufficiency: Meta ≥5x CPA per ad set, TikTok ≥50x CPA per ad group
- Learning phase: never recommend edits during active learning phase
- Compliance: always check Special Ad Categories for housing/employment/credit/finance
- Creative: never run silent video ads on TikTok (sound-on platform)
- Attribution: default to 7-day click / 1-day view (Meta), data-driven (Google)
Reference Files
Load these on-demand as needed — do NOT load all at startup.
Path resolution: All references are installed at ads/references/.
When sub-skills or agents reference ads/references/*.md, resolve to
ads/references/*.md.
references/scoring-system.md — Weighted scoring algorithm and grading thresholds
references/benchmarks.md — Industry benchmarks by platform (CPC, CTR, CVR, ROAS)
references/bidding-strategies.md — Bidding decision trees per platform
references/budget-allocation.md — Platform selection matrix, scaling rules, MER
references/platform-specs.md — Creative specifications across all platforms
references/conversion-tracking.md — Pixel, CAPI, EMQ, ttclid implementation
references/compliance.md — Regulatory requirements, ad policies, privacy
references/google-audit.md — 74-check Google Ads audit checklist
references/meta-audit.md — 46-check Meta Ads audit checklist
references/linkedin-audit.md — 25-check LinkedIn Ads audit checklist
references/tiktok-audit.md — 25-check TikTok Ads audit checklist
references/microsoft-audit.md — 20-check Microsoft Ads audit checklist
Scoring Methodology
Ads Health Score (0-100)
Per-platform score using weighted algorithm from references/scoring-system.md.
Cross-platform aggregate weighted by budget share:
Aggregate = Sum(Platform_Score x Platform_Budget_Share)
Grading
| Grade |
Score |
Action Required |
| A |
90-100 |
Minor optimizations only |
| B |
75-89 |
Some improvement opportunities |
| C |
60-74 |
Notable issues need attention |
| D |
40-59 |
Significant problems present |
| F |
<40 |
Urgent intervention required |
Priority Levels
- Critical: Revenue/data loss risk (fix immediately)
- High: Significant performance drag (fix within 7 days)
- Medium: Optimization opportunity (fix within 30 days)
- Low: Best practice, minor impact (backlog)
Sub-Skills
This skill orchestrates 12 specialized sub-skills:
- ads-audit — Full multi-platform audit with parallel delegation
- ads-google — Google Ads deep analysis (Search, PMax, YouTube)
- ads-meta — Meta Ads deep analysis (FB, IG, Advantage+)
- ads-youtube — YouTube Ads specific analysis
- ads-linkedin — LinkedIn Ads deep analysis
- ads-tiktok — TikTok Ads deep analysis
- ads-microsoft — Microsoft/Bing Ads deep analysis
- ads-creative — Cross-platform creative quality audit
- ads-landing — Landing page quality for ad campaigns
- ads-budget — Budget allocation and bidding strategy
- ads-plan — Strategic ad planning with industry templates
- ads-competitor — Competitor ad intelligence
Subagents
For parallel analysis during full audits:
audit-google — Google Ads checks (G01-G74)
audit-meta — Meta Ads checks (M01-M46)
audit-creative — Creative quality for LinkedIn, TikTok, Microsoft
audit-tracking — Conversion tracking health across all platforms
audit-budget — Budget, bidding, structure for LinkedIn, TikTok, Microsoft
audit-compliance — Compliance, settings, performance across all platforms
1---2name: ads3description: >4 Comprehensive paid advertising audit and optimization for any business type.5 Performs full multi-platform audits (Google Ads, Meta Ads, LinkedIn Ads, TikTok6 Ads, Microsoft Ads), single-platform deep analysis, conversion tracking health7 checks, creative quality assessment, budget allocation optimization, bidding8 strategy evaluation, and compliance verification. Industry detection for SaaS,9 e-commerce, local service, B2B enterprise, info products, mobile app, real10 estate, healthcare, finance, and agency. Triggers on: "ads", "PPC", "paid11 advertising", "Google Ads", "Meta Ads", "Facebook Ads", "LinkedIn Ads",12 "TikTok Ads", "Microsoft Ads", "Bing Ads", "ad audit", "campaign audit",13 "ROAS", "conversion tracking", "creative fatigue", "bid strategy".14metadata:15 source: https://skillmd.com/skills/megastep/ads16---1718# Ads — Multi-Platform Paid Advertising Audit & Optimization1920Comprehensive ad account analysis across all major platforms (Google, Meta,21LinkedIn, TikTok, Microsoft). Orchestrates 12 specialized sub-skills and226 subagents.2324## Quick Reference2526| Command | What it does |27|---------|-------------|28| `$ads audit` | Full multi-platform audit with parallel subagent delegation |29| `$ads google` | Google Ads deep analysis (Search, PMax, YouTube) |30| `$ads meta` | Meta Ads deep analysis (FB, IG, Advantage+) |31| `$ads youtube` | YouTube Ads specific analysis |32| `$ads linkedin` | LinkedIn Ads deep analysis (B2B, Lead Gen) |33| `$ads tiktok` | TikTok Ads deep analysis (Creative, Shop, Smart+) |34| `$ads microsoft` | Microsoft/Bing Ads deep analysis (Copilot, Import) |35| `$ads creative` | Cross-platform creative quality audit |36| `$ads landing` | Landing page quality assessment for ad campaigns |37| `$ads budget` | Budget allocation and bidding strategy review |38| `$ads plan <business-type>` | Strategic ad plan with industry templates |39| `$ads competitor` | Competitor ad intelligence analysis |4041## Orchestration Logic4243When the user invokes `$ads audit`, delegate to subagents in parallel:441. Collect account data (exports, screenshots, or API access details)452. Detect business type and identify active platforms463. Spawn subagents: audit-google, audit-meta, audit-creative, audit-tracking, audit-budget, audit-compliance474. Collect results and generate unified report with Ads Health Score (0-100)485. Create prioritized action plan with Quick Wins4950For individual commands (`$ads google`, `$ads meta`, etc.), load the relevant51sub-skill directly.5253### Multi-Agent Execution (Codex)5455- Use `spawn_agent` with `worker` role for each audit stream during full-account reviews.56- Use one `explorer` agent to gather account structure/evidence before specialized checks.57- Use `wait` to synchronize all delegated audits before computing the unified health score.58- Use the `default` agent to synthesize conflicts, prioritize recommendations, and present final output.5960## Industry Detection6162Detect business type from ad account signals:63- **SaaS**: trial_start/demo_request events, pricing page targeting, long attribution windows64- **E-commerce**: purchase events, product catalog/feed, Shopping/PMax campaigns65- **Local Service**: call extensions, location targeting, store visits, directions events66- **B2B Enterprise**: LinkedIn Ads active, ABM lists, high CPA tolerance ($50+), long sales cycle67- **Info Products**: webinar/course funnels, lead gen forms, low-ticket offers68- **Mobile App**: app install campaigns, in-app events, deep linking69- **Real Estate**: listing feeds, property-specific landing pages, geo-heavy targeting70- **Healthcare**: HIPAA compliance flags, healthcare-specific ad policies71- **Finance**: Special Ad Categories declared, financial products compliance72- **Agency**: multiple client accounts, white-label reporting needs7374## Quality Gates7576Hard rules — never violate these:77- Never recommend Broad Match without Smart Bidding (Google)78- 3x Kill Rule: flag any ad group/campaign with CPA >3x target for pause79- Budget sufficiency: Meta ≥5x CPA per ad set, TikTok ≥50x CPA per ad group80- Learning phase: never recommend edits during active learning phase81- Compliance: always check Special Ad Categories for housing/employment/credit/finance82- Creative: never run silent video ads on TikTok (sound-on platform)83- Attribution: default to 7-day click / 1-day view (Meta), data-driven (Google)8485## Reference Files8687Load these on-demand as needed — do NOT load all at startup.8889**Path resolution:** All references are installed at `ads/references/`.90When sub-skills or agents reference `ads/references/*.md`, resolve to91`ads/references/*.md`.9293- `references/scoring-system.md` — Weighted scoring algorithm and grading thresholds94- `references/benchmarks.md` — Industry benchmarks by platform (CPC, CTR, CVR, ROAS)95- `references/bidding-strategies.md` — Bidding decision trees per platform96- `references/budget-allocation.md` — Platform selection matrix, scaling rules, MER97- `references/platform-specs.md` — Creative specifications across all platforms98- `references/conversion-tracking.md` — Pixel, CAPI, EMQ, ttclid implementation99- `references/compliance.md` — Regulatory requirements, ad policies, privacy100- `references/google-audit.md` — 74-check Google Ads audit checklist101- `references/meta-audit.md` — 46-check Meta Ads audit checklist102- `references/linkedin-audit.md` — 25-check LinkedIn Ads audit checklist103- `references/tiktok-audit.md` — 25-check TikTok Ads audit checklist104- `references/microsoft-audit.md` — 20-check Microsoft Ads audit checklist105106## Scoring Methodology107108### Ads Health Score (0-100)109110Per-platform score using weighted algorithm from `references/scoring-system.md`.111Cross-platform aggregate weighted by budget share:112113```114Aggregate = Sum(Platform_Score x Platform_Budget_Share)115```116117### Grading118119| Grade | Score | Action Required |120|-------|-------|-----------------|121| A | 90-100 | Minor optimizations only |122| B | 75-89 | Some improvement opportunities |123| C | 60-74 | Notable issues need attention |124| D | 40-59 | Significant problems present |125| F | <40 | Urgent intervention required |126127### Priority Levels128129- **Critical**: Revenue/data loss risk (fix immediately)130- **High**: Significant performance drag (fix within 7 days)131- **Medium**: Optimization opportunity (fix within 30 days)132- **Low**: Best practice, minor impact (backlog)133134## Sub-Skills135136This skill orchestrates 12 specialized sub-skills:1371381. **ads-audit** — Full multi-platform audit with parallel delegation1392. **ads-google** — Google Ads deep analysis (Search, PMax, YouTube)1403. **ads-meta** — Meta Ads deep analysis (FB, IG, Advantage+)1414. **ads-youtube** — YouTube Ads specific analysis1425. **ads-linkedin** — LinkedIn Ads deep analysis1436. **ads-tiktok** — TikTok Ads deep analysis1447. **ads-microsoft** — Microsoft/Bing Ads deep analysis1458. **ads-creative** — Cross-platform creative quality audit1469. **ads-landing** — Landing page quality for ad campaigns14710. **ads-budget** — Budget allocation and bidding strategy14811. **ads-plan** — Strategic ad planning with industry templates14912. **ads-competitor** — Competitor ad intelligence150151## Subagents152153For parallel analysis during full audits:154- `audit-google` — Google Ads checks (G01-G74)155- `audit-meta` — Meta Ads checks (M01-M46)156- `audit-creative` — Creative quality for LinkedIn, TikTok, Microsoft157- `audit-tracking` — Conversion tracking health across all platforms158- `audit-budget` — Budget, bidding, structure for LinkedIn, TikTok, Microsoft159- `audit-compliance` — Compliance, settings, performance across all platforms