Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add vladimirlucantis/meta-ads-framework-es --skill skillgit clone --depth 1 https://github.com/vladimirlucantis/meta-ads-framework-esWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/vladimirlucantis/meta-ads-framework-es/skill)<a href="https://agentmods.dev/skills/vladimirlucantis/meta-ads-framework-es/skill"><img src="https://agentmods.dev/badge/skills/vladimirlucantis/meta-ads-framework-es/skill.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00099 | $0.02709 |
| Opus 5 | $0.00049 | $0.01354 |
| Sonnet 5 | $0.00020 | $0.00542 |
| Haiku 4.5 | $0.00010 | $0.00271 |
Grade A, and why
meta-ads-framework-es scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meta Ads Framework (ES)
Autor: Vladimir Lucantis · Versión: 0.2.1 · Idioma: español (voseo) · Categoría: marketing
Framework profesional para análisis de campañas de Meta Ads en español. Agnóstico de estrategia: se adapta a cómo estructura campañas cada consultor o negocio. Aplica umbrales de decisión calibrados, patrones de creativos probados y estructura de respuesta consistente.
Cuándo activarse
Activar automáticamente cuando el usuario:
- Comparta métricas, informes o capturas del Administrador de Anuncios
- Pregunte sobre pixel, dataset, API de Conversiones o eventos
- Consulte sobre audiencias (personalizadas, lookalike, Advantage+)
- Pida guiones de Reels, hooks o copy para anuncios
- Necesite decidir si pausar, escalar o mantener un ad set
- Mencione problemas de frecuencia, fatiga creativa o deterioro de CTR
- Hable de estrategias de campaña (Advantage+, ABO, CBO, FRIA/CALIENTE, creative testing)
- Tenga una cuenta que convierte principalmente por WhatsApp o mensajes
Archivos de referencia
Cargar on-demand según lo que pida el usuario (no cargar todos al inicio):
references/estrategias-campania.md- Las 5 estrategias más comunes y cómo diagnosticar cada unareferences/metricas-umbrales.md- Umbrales de decisión por métrica, con variantes por estrategiareferences/estructura-reels.md- Formato de Reels publicitarios (gancho/cuerpo/cierre, duración, tono)references/creativos-por-estrategia.md- Adaptación de creativos según estrategia y tipo de audienciareferences/pixel-setup.md- Checklist de configuración de pixel, API de Conversiones y eventos
Paso 0: Detectar la estrategia ANTES de diagnosticar
Este es el paso más importante y el que muchos skills obvian. No se puede dar un buen diagnóstico sin saber qué estrategia está ejecutando el usuario.
Cómo detectar
- Mirar los nombres de los ad sets (ver tabla en
references/estrategias-campania.md) - Si los nombres son ambiguos, preguntar antes de sacar conclusiones
- Inferir del contexto: objetivo de campaña, cantidad de ad sets, tipo de segmentación
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 237 lines · 99 tokens per session scan A 656311df3a98
meta-ads-framework-es is a skill published in the GitHub repository vladimirlucantis/meta-ads-framework-es (3 stars, last pushed 4mo ago), licensed MIT. It adds 99 tokens to every session and 2,709 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
tmr-seo-analytics-report
Use this skill when the user asks to generate an SEO report, run an SEO + analytics performance report, check search console and GA4 performance, create a client SEO report, or analyze organic search visibility combined with website analytics. Covers Google Search Console metrics (impressions, clicks, CTR, average…
tmr-gsc-rank-tracker
Use this skill when the user wants to track how they rank for their target keywords over time in Google Search Console — e.g. "track my rankings", "rank tracker", "keyword position history", "how am I ranking", "show my ranking trend", "am I climbing or slipping on Google". It ASKS the user which keywords to check…
tmr-content-decay-detector
Use this skill when the user asks to detect content decay, find declining pages, audit SEO performance drops, identify pages losing organic traffic, run a content decay audit, check which blog posts or landing pages are losing clicks or sessions, or surface pages with falling rankings and engagement. Requires Google…
tmr-facebook-insights-report
Runs a comprehensive Facebook Page (organic) performance report using live data from Two Minute Reports (TMR) MCP. Trigger this skill whenever the user says anything like: "audit my Facebook Page", "Facebook Page performance report", "how is my Facebook Page growing", "review my Facebook engagement", "analyze my FB…
tmr-google-ads-audit
Runs a comprehensive Google Ads account audit using live data from Two Minute Reports (TMR) MCP. Trigger this skill whenever the user says anything like: "audit my Google Ads", "review my Google Ads account", "analyze my Google campaigns", "why is my Google Ads performance dropping", "Google Ads health check", "check…
tmr-linkedin-ads-audit
Runs a comprehensive LinkedIn Ads account audit using live data from Two Minute Reports (TMR) MCP. Trigger this skill whenever the user says anything like: "audit my LinkedIn Ads", "review my LinkedIn campaigns", "analyze my LinkedIn ad account", "why is my LinkedIn CPL high", "LinkedIn Ads health check", "check my…