/ Directorio / Playground / claude-ads
← Todos los servidores ↗ GitHub
● Comunidad AgriciDaniel ⚡ Instantáneo

claude-ads

por AgriciDaniel · AgriciDaniel/claude-ads

Runs 250+ paid-ads audit checks across Google, Meta, YouTube, LinkedIn, TikTok, Microsoft, and Apple — with scoring, creative review, and PDF reports.

A Claude Code skill for paid-advertising audits and optimization. Feed it campaign exports or screenshots and it produces a weighted 0-100 Ads Health Score, platform-specific findings, creative quality review, privacy-infra verification (Consent Mode V2, CAPI, Events API), and a client-ready PDF. Parallel subagents run per-platform analyses simultaneously.

▶ Ver demo 📦 Instalar 💡 Casos de uso

Por qué usarlo

Características clave

Demo en vivo

Cómo se ve en la práctica

claude-ads-skill.replay ▶ listo
0/0

Instalación

Repositorio del autor · Documentación oficial de Skills de Claude

Casos de uso

Usos del mundo real: claude-ads

Audit a Google Ads account before taking it over

👤 Agencies onboarding a new paid-search client ⏱ ~45 min intermediate

Cuándo usarlo: You're bidding for the account and need to show concrete gaps in week one.

Requisitos previos
  • Exported account data or screenshots — Google Ads Editor export or the standard 'all campaigns' CSV
Flujo
  1. Feed the skill the export
    Run the claude-ads skill on this Google Ads export. Focus on Search + PMax. Give me the health score and top 10 issues.✓ Copiado
    → Score with breakdown by category (structure, bidding, creative, tracking)
  2. Drill into PMax specifically
    Now deep-dive PMax — asset quality, audience signals, brand-exclusion list. What's the quick-win?✓ Copiado
    → Platform-specific findings with remediation priority
  3. Generate the PDF
    Export to a client PDF with the score dashboard on page 1 and the remediation roadmap at the end.✓ Copiado
    → Polished PDF ready to send

Resultado: A deliverable audit that wins the pitch.

Errores comunes
  • Audit based on incomplete data gives wrong conclusions — Include 90 days of performance plus settings export, not just a screenshot

Verify Meta Advantage+ privacy infrastructure before iOS 18

👤 In-house paid-social managers ⏱ ~30 min advanced

Cuándo usarlo: Attribution is drifting and you suspect CAPI or Events API isn't firing cleanly.

Flujo
  1. Run the privacy-infra check
    Use claude-ads to audit our Meta setup for CAPI completeness, event match quality, and Consent Mode V2.✓ Copiado
    → Per-event pass/fail with remediation
  2. Get the fix plan
    Prioritize fixes by attribution-loss impact.✓ Copiado
    → Ordered list tied to revenue impact

Resultado: A concrete privacy-infrastructure punch-list.

Errores comunes
  • Matching Match Quality fixes without GTM changes — The skill flags when GTM/server-side tag config is also required

Generate 10 new ad creative variants for a failing ad set

👤 Performance marketers in creative refresh ⏱ ~30 min intermediate

Cuándo usarlo: CPMs are climbing and your creatives are fatigued.

Flujo
  1. Provide the winning ad + brief
    Here's our best-performing Meta ad. Use claude-ads creative agents to generate 10 variants that test different hooks.✓ Copiado
    → 10 copy + visual-brief pairs, each with a stated hypothesis
  2. Score the variants
    Which 3 should we ship first based on policy safety and hypothesis strength?✓ Copiado
    → Short list with reasoning

Resultado: A creative batch with clear hypotheses to test.

Errores comunes
  • Generated copy violates platform policy — The skill's compliance check catches most issues — but have a human final-check on regulated verticals
Combinar con: nano-banana-pro-prompts-recommend-skill

Combinaciones

Combínalo con otros MCPs para multiplicar por 10

claude-ads-skill + nano-banana-pro-prompts-recommend-skill

After creative-agents propose variants, generate image prompts for each

For each of the 10 creative variants, use Nano Banana to propose an image prompt.✓ Copiado
claude-ads-skill + claude-seo-skill

Align paid landing pages with SEO best practices from /seo audit

Run /seo audit on the landing pages paid traffic is hitting, then cross-reference with claude-ads landing-page quality findings.✓ Copiado

Herramientas

Lo que expone este MCP

HerramientaEntradasCuándo llamarCoste
Platform audit exported campaign data Full or partial account review 0
Ads Health Score audit results At the end of each audit 0
Privacy infrastructure check tag config or screenshots Attribution or policy review 0
Creative generation agents winning ad + brief Creative refresh 0
Financial modeling conversion rate, AOV, margin Budget planning 0

Coste y límites

Lo que cuesta ejecutarlo

Cuota de API
None for the skill
Tokens por llamada
Full audit: 15-40k tokens; single-platform: 5-10k
Monetario
Free — skill is local; you still pay for the ad spend it's auditing
Consejo
Run platform-by-platform for ongoing clients; full-account audits are best for onboarding and quarterly reviews.

Seguridad

Permisos, secretos, alcance

Almacenamiento de credenciales: No credentials — skill reads exports you paste in. Campaign data stays on your machine.
Salida de datos: None from the skill itself

Resolución de problemas

Errores comunes y soluciones

Score seems too low/high for the account

Check the export completeness — missing conversion data skews the score.

Creative agents miss brand voice

Include a brand voice doc or 3 winning ads as style anchors in the prompt.

PDF export fails

The skill needs a markdown-to-PDF runtime; check the skill's setup section for the required dependency.

Alternativas

claude-ads vs otros

AlternativaCuándo usarlaContrapartida
Manual audits via platform UIsYou only manage one account and have timeThorough but slow; doesn't scale
claude-seo-skillYou need organic / technical SEO instead of paidDifferent side of the acquisition funnel

Más

Recursos

📖 Lee el README oficial en GitHub

🐙 Ver issues abiertas

🔍 Ver todos los 400+ servidores MCP y Skills