Respuesta rápida
- Qué es
- marketing-loops es una skill de Corey Haines (licencia MIT) que le enseña a Claude a armar rutinas de marketing que un agente corre con una frecuencia fija o ante un evento, cada una con un control antes de actuar, memoria y una condición para frenar.
- Qué le das
- Qué resultado quieres cuidar (posiciones en Google, anuncios, retención, prospección), qué herramientas y datos tienes y qué puede hacer el agente sin pedir permiso
- Qué te devuelve
- La ficha completa de cada rutina (frecuencia, cuándo actúa, pasos, control, memoria, frenos y adónde va el resultado) y cómo programarla en tu agente
- Autor
- Corey Haines
- Licencia
- MIT
- Repositorio
- coreyhaines31/marketingskills
- En GitHub
- 60,6 mil estrellas · actualizada el
- Revisada por Claura
Instálala en una línea para todos tus proyectos, en Claude Code, Cursor, Codex y más:
npx skills add coreyhaines31/marketingskills --skill marketing-loops -g
Funciona en
~/.claude/skills/~/.agents/skills/~/.agents/skills/~/.agents/skills/Pedidos para probarla
Con la skill instalada, copia uno y pégaselo a tu agente tal cual, o cambia los datos por los tuyos.
Convierte el reporte semanal de redes que hago a mano en una rutina que corra un agente, con su parada y el momento en que yo reviso.
Dame tres rutinas de marketing para una agencia chica que un agente pueda correr solo, con qué guarda en memoria cada una.
Arma un bucle que revise cada lunes las páginas de mi web que perdieron visitas y me proponga qué actualizar.
#Qué hace
marketing-loops es una skill de Corey Haines (licencia MIT) para armar rutinas de marketing que un agente de IA corre con una frecuencia fija o cuando pasa algo. La diferencia con una idea suelta es que la rutina se repite: la skill la llama el pariente operativo de las ideas de marketing. El proceso tiene cinco pasos: aclarar qué resultado cuida la rutina, elegir la más cercana del catálogo, ajustar la frecuencia, decidir qué hace sola y qué deja para tu aprobación, y programarla.
Cada rutina se define con nueve partes: cada cuánto mira, cuándo actúa, para qué existe, qué skills usa, los pasos de cada corrida, el control previo (que no sea ruido ni un error de medición), qué recuerda entre corridas para no repetir avisos, cuándo se frena o pasa el caso a una persona, y adónde va el resultado. Una tabla ata la frecuencia a la velocidad de la señal: posiciones en Google y competidores por semana, cansancio de anuncios cada dos o tres días, señales de baja de clientes a diario, contenido que pierde tráfico por mes. Las reglas de seguridad separan lo que puede correr solo (leer, analizar, puntuar, preparar borradores) de lo que necesita aprobación (gastar, mover presupuesto, enviar, publicar, borrar o cambiar configuraciones), con topes de gasto, listas de cuentas permitidas, cumplimiento de CAN-SPAM, GDPR y las reglas de cada plataforma, y un interruptor para apagar.
El catálogo trae 60 rutinas en nueve áreas: SEO y contenido, anuncios pagos, prensa, redes y alianzas, prospección en frío, activación, retención, ingresos, referidos y operación. Un ejemplo es la revisión semanal de anuncios, que termina con una sola decisión por cuenta: mantener, arreglar, probar o investigar. Suma dos operadores completos, uno de SEO con memoria propia en .agents/seo/ y otro de prospección con memoria en .agents/outbound/, una plantilla para crear rutinas nuevas, una guía para combinarlas y otra sobre dónde guardar la memoria.
#Cómo aplicarla a tu negocio
Caso de ejemplo: una tienda online de muebles en Chile que invierte en Meta y Google y revisa las campañas «cuando puede». Quiere una revisión fija sin que nadie toque presupuestos sin permiso.
- Elige la rutina. Del catálogo sale la revisión semanal de anuncios: cada lunes, gasto y ritmo, tráfico, conversiones, cansancio de creatividades, página de destino y medición, en ese orden.
- Carga los objetivos. En
.agents/product-marketing.mdanotas el costo por venta aceptable y qué cuenta como conversión, por ejemplo una compra o un pedido de presupuesto. - Fija los frenos. La rutina nunca cambia presupuestos, pujas ni anuncios activos: deja los cambios como propuesta. Si el gasto pasa el tope, se detiene y avisa.
- Prográmala. En Claude Code la dejas con horario fijo para los lunes a las 9; en otro agente, con un cron equivalente.
- Lee la decisión. Cada lunes recibes una línea por cuenta, por ejemplo «Google: arreglar, la medición no coincide con las ventas del sitio», con los datos, las hipótesis y lo que falta saber. Si nadie actúa con esa salida, la skill misma dice que conviene borrar la rutina.
#Cómo instalarla
Es una skill que no depende de un agente en particular: el cuerpo de cada rutina corre en cualquiera, y solo la forma de programarla cambia según la herramienta.
- Con una línea, para cualquier agente:
npx skills add coreyhaines31/marketingskills --skill marketing-loops -gla deja instalada en todos tus proyectos. Como las rutinas usan otras skills del autor (anuncios, analítica, SEO, emails en frío), conviene instalar el repo completo connpx skills add coreyhaines31/marketingskills -g. - A mano: copia la carpeta
skills/marketing-loops/completa (conreferences/, donde viven el catálogo y las reglas de seguridad) a~/.claude/skills/para Claude Code, o a~/.agents/skills/para Cursor, Codex y Gemini CLI. - App de Claude: comprime la carpeta en un ZIP y súbela desde Customize, Skills, «Upload a skill».
- Qué más necesitas: acceso a los datos que lee cada rutina (Analytics, Search Console, el administrador de anuncios o el CRM) y algo que la programe: las tareas programadas de Claude Code, un cron o tu propio calendario.
El SKILL.md completo (con la licencia y la fuente) está más abajo.
El SKILL.md completo
Skill original de Corey Haines (MIT). Fuente: github.com/coreyhaines31/marketingskills/tree/main/skills/marketing-loops.
El archivo original está en inglés y va tal cual, sin traducir. Lo de arriba de esta ficha es el resumen en español: qué hace, cómo aplicarla y cómo instalarla.
Leer el archivo (123 líneas)
Marketing Loops
You help set up marketing loops — repeatable marketing workflows an AI agent runs on a cadence, each with a defined trigger, a bounded set of steps, a self-check, and an explicit stopping condition. A loop turns a marketing task you'd otherwise do manually (and forget) into an always-on system: the weekly SEO opportunity scan, the ad-fatigue refresh, the churn-signal watch.
This is the operational cousin of marketing-ideas. Ideas tell you what to try once. Loops tell you what to keep doing on a schedule — and wire the other marketing skills together to do it.
How to Use This Skill
Check for product marketing context first: if .agents/product-marketing.md exists (or .claude/product-marketing.md, or the legacy product-marketing-context.md), read it before asking questions. Use that context and only ask for what's missing.
Then:
- Clarify the job. What outcome should this loop protect or grow? (rankings, ad efficiency, activation, retention, revenue, referrals)
- Pick a loop from the catalog in
references/loop-catalog.md— or adapt the closest one. - Tune the cadence to how fast the underlying signal actually changes (see the cadence rule below).
- Confirm the human checkpoint. Decide what the loop does autonomously vs. what it stages for human approval before publishing or spending — see
references/loop-guardrails.md. - Schedule it (see "Scheduling a loop" below).
Building more than one loop, or a whole marketing operating system? See references/loop-orchestration.md for how loops compose and the order to adopt them (start with tracking + a weekly review; don't build them all at once).
Anatomy of a Marketing Loop
Every loop in the catalog has these nine parts. When you author or adapt one, fill all of them — a loop missing a stop condition, a self-check, or its state handling is a liability, not an asset.
| Part | What it defines |
|---|---|
| Check cadence | How often the loop looks (weekly / daily / on-trigger). Match it to signal speed. |
| Acts when | The action condition — what must be true to actually do something, vs. just check and skip. Most runs of a good loop are "checked, nothing to do." |
| Purpose | The one outcome this loop exists to move. |
| Skills used | Which marketing skills the loop orchestrates each iteration. |
| Loop body | The ordered steps run each iteration. |
| Self-check | The verification done before acting — so the loop doesn't act on noise, seasonality, or a tracking bug. |
| State / idempotency | What the loop remembers between runs: last-run marker, dedupe key, cooldown window, "already handled" set. Without this, loops double-act, re-nag the same people, or re-alert the same thing. Non-negotiable for anything scheduled — see references/loop-state.md for where state lives and the idempotency patterns. |
| Stop / bail-out | When the loop skips, halts, escalates to a human, or disables itself — plus what it does on error. Every loop needs one, including heartbeat loops (their stop is "manual disable + error-halt," never "n/a"). |
| Output | Where results go: a file, a PR, a staged draft, a notification, a report. |
The Check cadence / Acts when split matters: a churn-signal loop might check daily but only act when an account crosses a risk threshold it hasn't been contacted about inside the cooldown window. Conflating the two produces loops that either miss the window or spam.
The cadence rule
Match cadence to how fast the signal actually changes — not to how often you'd like an update.
| Signal | Realistic cadence | Why |
|---|---|---|
| Rankings, backlinks, domain authority | Weekly | Move slowly; daily checks are noise |
| Ad creative fatigue, CPA drift | Every 2–3 days | Meta/Google feedback loops are days, not hours |
| Activation / onboarding funnel | Weekly | Needs enough signups to be significant |
| Churn signals | Daily or on-trigger | Early intervention window is short |
| Content / copy decay | Monthly | Traffic erosion is gradual |
| Competitor changes | Weekly | Pricing/positioning shifts are infrequent but matter |
| Social listening / mentions | Daily | Engagement windows close fast |
Over-frequent loops are the most common failure mode: they generate busywork, burn budget, and train you to ignore the output.
When NOT to loop
Not everything should be automated on a cadence. Skip a loop — or add a mandatory human checkpoint — when:
- Strategy or creative direction is the real work. Loops maintain and optimize; they don't set positioning, invent campaigns, or make brand calls.
- The action publishes or spends without review. Auto-drafting an ad, email, or post is fine. Auto-publishing or auto-shifting budget needs a human checkpoint unless the user has explicitly authorized autonomous action and set guardrails (caps, allowlists).
- The signal is too sparse to be significant. A weekly conversion-rate loop on 40 visitors/week is measuring noise.
- It's a vanity loop. If nobody acts on the output, delete the loop. A loop that emails a dashboard nobody reads is worse than nothing.
For any loop that sends, spends, publishes, or touches personal data, apply references/loop-guardrails.md — the two-tier action model (autonomous-safe vs. gated), spend/send caps, CAN-SPAM/GDPR/FTC/ToS rules, the always-escalate list, and a required kill switch.
Scheduling a loop
These loops are agent-agnostic — the body works in any agent. The scheduling depends on your environment:
- Claude Code — native options:
/loop(self-paced, until a condition),ScheduleWakeup(dynamic pacing that reacts to state), andCronCreate(fixed cron schedule). If you have a loop-mechanics skill such asloopifyinstalled, use it to choose between them and tune delays; otherwise the guidance below is enough. - Any agent + cron — wrap the loop body as a scheduled prompt/script (
0 9 * * 1for Mondays 9am, etc.). - Manual cadence — for high-judgment loops, "run this skill every Monday" is a perfectly good loop. The value is the repeatable body, not the automation.
Default to time-of-day cron for review-style loops (weekly review, ranking watch) and dynamic pacing for monitor-until-threshold loops (churn watch, launch-day tracking).
The Catalog
references/loop-catalog.md holds the full library — 60 marketing loops with thorough funnel coverage: SEO & Content, Paid, Earned/Social/Partnerships, Outbound, Activation, Retention, Revenue, Referral & Advocacy, and Ongoing Ops. Each is a complete, adaptable spec. Start there, pick the closest match, and tune it to the user's product, stage, and tooling.
Running a whole channel: the SEO operator
When the user wants an agent to own SEO for a site rather than run one loop, use references/seo-operator.md. It bundles the SEO loops (site health, claim drift, striking-distance push, AI-answer check, keyword gap, content decay, competitor watch, and more) into one schedule with shared memory in .agents/seo/, a first-run checklist, operating rules, a writing gate, and a one-screen weekly report.
Running outbound: the outbound operator
For an agent running day-to-day outbound (signal sweeps, staged outreach, reply triage, sending-domain health, weekly sequence retros), use references/outbound-operator.md. It sets the brief, approved claims, approval rules by tier, shared memory in .agents/outbound/, and a weekly report.
Authoring a new loop
When nothing in the catalog fits, author a new loop from references/loop-template.md — a copy-paste template with fill-in prompts, a worked before/after example, and a ship checklist. Fill all nine anatomy parts; if you can't answer the self-check, state/idempotency, and stop/bail-out concretely, the loop isn't ready to run.
Anti-patterns
- Looping without a stop condition → runaway spend or infinite churn.
- Same cadence for every loop → most run too often and get ignored.
- No self-check → the loop acts on noise, seasonality, or a tracking bug.
- No human checkpoint on spend/publish actions.
- Building 10 loops at once → start with one, prove it earns its keep, then add the next.
Banned vocabulary
Avoid: "set it and forget it," "fully autonomous marketing," "AI does everything," "10x on autopilot," "growth hacking machine." Loops are disciplined systems with checkpoints, not magic. Describe them honestly.
Related Skills
- marketing-ideas — one-off tactics and inspiration (what to try). Loops operationalize the ones worth repeating.
- ab-testing — the experimentation loop specifically (hypothesis → test → promote winner → repeat).
- analytics — most loops read from analytics to decide whether to act.
- reverse-engineer-marketing — the growth-move watch loop keeps a competitor teardown current, and teardown plays name the loop that sustains each one.
- Individual channel skills (
ads,seo-audit,emails,social,churn-prevention,pricing,referrals) — the loop bodies orchestrate these.
Copiar el archivo tal cual
--- name: marketing-loops description: "When the user wants a recurring marketing job an AI agent runs on a cadence or trigger, or asks what a weekly or daily automated check should do, remember, and when it should stop: SEO and ads checks, churn watches, outbound triage. For one-off ideas, see marketing-ideas. For the test loop, see ab-testing." metadata: version: 1.8.4 --- <!-- Skill original: marketing-loops, de Corey Haines (https://github.com/coreyhaines31/marketingskills/tree/main/skills/marketing-loops) Licencia: MIT. Reproducida con atribución según los términos de la licencia. Copia publicada en claura-ai.com/skills. --> # Marketing Loops You help set up **marketing loops** — repeatable marketing workflows an AI agent runs on a cadence, each with a defined trigger, a bounded set of steps, a self-check, and an explicit stopping condition. A loop turns a marketing task you'd otherwise do manually (and forget) into an always-on system: the weekly SEO opportunity scan, the ad-fatigue refresh, the churn-signal watch. This is the operational cousin of `marketing-ideas`. Ideas tell you *what to try once*. Loops tell you *what to keep doing on a schedule* — and wire the other marketing skills together to do it. ## How to Use This Skill **Check for product marketing context first:** if `.agents/product-marketing.md` exists (or `.claude/product-marketing.md`, or the legacy `product-marketing-context.md`), read it before asking questions. Use that context and only ask for what's missing. Then: 1. **Clarify the job.** What outcome should this loop protect or grow? (rankings, ad efficiency, activation, retention, revenue, referrals) 2. **Pick a loop** from the catalog in `references/loop-catalog.md` — or adapt the closest one. 3. **Tune the cadence** to how fast the underlying signal actually changes (see the cadence rule below). 4. **Confirm the human checkpoint.** Decide what the loop does autonomously vs. what it stages for human approval before publishing or spending — see `references/loop-guardrails.md`. 5. **Schedule it** (see "Scheduling a loop" below). Building more than one loop, or a whole marketing operating system? See `references/loop-orchestration.md` for how loops compose and the order to adopt them (start with tracking + a weekly review; don't build them all at once). ## Anatomy of a Marketing Loop Every loop in the catalog has these nine parts. When you author or adapt one, fill all of them — a loop missing a stop condition, a self-check, or its state handling is a liability, not an asset. | Part | What it defines | |------|-----------------| | **Check cadence** | How often the loop *looks* (weekly / daily / on-trigger). Match it to signal speed. | | **Acts when** | The action condition — what must be true to actually *do* something, vs. just check and skip. Most runs of a good loop are "checked, nothing to do." | | **Purpose** | The one outcome this loop exists to move. | | **Skills used** | Which marketing skills the loop orchestrates each iteration. | | **Loop body** | The ordered steps run each iteration. | | **Self-check** | The verification done *before* acting — so the loop doesn't act on noise, seasonality, or a tracking bug. | | **State / idempotency** | What the loop remembers between runs: last-run marker, dedupe key, cooldown window, "already handled" set. Without this, loops double-act, re-nag the same people, or re-alert the same thing. Non-negotiable for anything scheduled — see `references/loop-state.md` for where state lives and the idempotency patterns. | | **Stop / bail-out** | When the loop skips, halts, escalates to a human, or disables itself — plus what it does on error. Every loop needs one, including heartbeat loops (their stop is "manual disable + error-halt," never "n/a"). | | **Output** | Where results go: a file, a PR, a staged draft, a notification, a report. | The **Check cadence / Acts when** split matters: a churn-signal loop might *check* daily but only *act* when an account crosses a risk threshold it hasn't been contacted about inside the cooldown window. Conflating the two produces loops that either miss the window or spam. ## The cadence rule Match cadence to how fast the signal actually changes — not to how often you'd *like* an update. | Signal | Realistic cadence | Why | |--------|-------------------|-----| | Rankings, backlinks, domain authority | Weekly | Move slowly; daily checks are noise | | Ad creative fatigue, CPA drift | Every 2–3 days | Meta/Google feedback loops are days, not hours | | Activation / onboarding funnel | Weekly | Needs enough signups to be significant | | Churn signals | Daily or on-trigger | Early intervention window is short | | Content / copy decay | Monthly | Traffic erosion is gradual | | Competitor changes | Weekly | Pricing/positioning shifts are infrequent but matter | | Social listening / mentions | Daily | Engagement windows close fast | Over-frequent loops are the most common failure mode: they generate busywork, burn budget, and train you to ignore the output. ## When NOT to loop Not everything should be automated on a cadence. Skip a loop — or add a mandatory human checkpoint — when: - **Strategy or creative direction is the real work.** Loops maintain and optimize; they don't set positioning, invent campaigns, or make brand calls. - **The action publishes or spends without review.** Auto-*drafting* an ad, email, or post is fine. Auto-*publishing* or auto-*shifting budget* needs a human checkpoint unless the user has explicitly authorized autonomous action and set guardrails (caps, allowlists). - **The signal is too sparse to be significant.** A weekly conversion-rate loop on 40 visitors/week is measuring noise. - **It's a vanity loop.** If nobody acts on the output, delete the loop. A loop that emails a dashboard nobody reads is worse than nothing. For any loop that sends, spends, publishes, or touches personal data, apply `references/loop-guardrails.md` — the two-tier action model (autonomous-safe vs. gated), spend/send caps, CAN-SPAM/GDPR/FTC/ToS rules, the always-escalate list, and a required kill switch. ## Scheduling a loop These loops are agent-agnostic — the *body* works in any agent. The *scheduling* depends on your environment: - **Claude Code** — native options: `/loop` (self-paced, until a condition), `ScheduleWakeup` (dynamic pacing that reacts to state), and `CronCreate` (fixed cron schedule). If you have a loop-mechanics skill such as `loopify` installed, use it to choose between them and tune delays; otherwise the guidance below is enough. - **Any agent + cron** — wrap the loop body as a scheduled prompt/script (`0 9 * * 1` for Mondays 9am, etc.). - **Manual cadence** — for high-judgment loops, "run this skill every Monday" is a perfectly good loop. The value is the repeatable *body*, not the automation. Default to time-of-day cron for review-style loops (weekly review, ranking watch) and dynamic pacing for monitor-until-threshold loops (churn watch, launch-day tracking). ## The Catalog `references/loop-catalog.md` holds the full library — 60 marketing loops with thorough funnel coverage: SEO & Content, Paid, Earned/Social/Partnerships, Outbound, Activation, Retention, Revenue, Referral & Advocacy, and Ongoing Ops. Each is a complete, adaptable spec. Start there, pick the closest match, and tune it to the user's product, stage, and tooling. ## Running a whole channel: the SEO operator When the user wants an agent to own SEO for a site rather than run one loop, use `references/seo-operator.md`. It bundles the SEO loops (site health, claim drift, striking-distance push, AI-answer check, keyword gap, content decay, competitor watch, and more) into one schedule with shared memory in `.agents/seo/`, a first-run checklist, operating rules, a writing gate, and a one-screen weekly report. ## Running outbound: the outbound operator For an agent running day-to-day outbound (signal sweeps, staged outreach, reply triage, sending-domain health, weekly sequence retros), use `references/outbound-operator.md`. It sets the brief, approved claims, approval rules by tier, shared memory in `.agents/outbound/`, and a weekly report. ## Authoring a new loop When nothing in the catalog fits, author a new loop from `references/loop-template.md` — a copy-paste template with fill-in prompts, a worked before/after example, and a ship checklist. Fill all nine anatomy parts; if you can't answer the self-check, state/idempotency, and stop/bail-out concretely, the loop isn't ready to run. ## Anti-patterns - Looping without a stop condition → runaway spend or infinite churn. - Same cadence for every loop → most run too often and get ignored. - No self-check → the loop acts on noise, seasonality, or a tracking bug. - No human checkpoint on spend/publish actions. - Building 10 loops at once → start with one, prove it earns its keep, then add the next. ## Banned vocabulary Avoid: "set it and forget it," "fully autonomous marketing," "AI does everything," "10x on autopilot," "growth hacking machine." Loops are disciplined systems with checkpoints, not magic. Describe them honestly. ## Related Skills - **marketing-ideas** — one-off tactics and inspiration (what to try). Loops operationalize the ones worth repeating. - **ab-testing** — the experimentation loop specifically (hypothesis → test → promote winner → repeat). - **analytics** — most loops read from analytics to decide whether to act. - **reverse-engineer-marketing** — the growth-move watch loop keeps a competitor teardown current, and teardown plays name the loop that sustains each one. - Individual channel skills (`ads`, `seo-audit`, `emails`, `social`, `churn-prevention`, `pricing`, `referrals`) — the loop bodies orchestrate these.
Preguntas frecuentes sobre la skill marketing-loops
¿Qué es la skill marketing-loops y para qué sirve?
marketing-loops es una skill de Corey Haines (github.com/coreyhaines31/marketingskills, licencia MIT) para diseñar rutinas de marketing que un agente de IA repite: la revisión semanal de oportunidades de SEO, el recambio de anuncios cansados, la vigilancia de clientes que se pueden ir o la clasificación de respuestas de prospección. Cada rutina tiene nueve partes obligatorias, entre ellas un control antes de actuar, memoria entre corridas y una condición de freno. Trae un catálogo de 60 rutinas listas para adaptar, una plantilla para crear las tuyas y reglas de seguridad para todo lo que gasta, envía o publica.
¿Cómo la aplico sin que el agente haga lío?
Empieza por una sola rutina, como recomienda la skill: medición más una revisión semanal, y suma otra recién cuando la primera demostró que sirve. Elige la del catálogo que más se parezca a tu necesidad y ajusta la frecuencia a la velocidad real de la señal: las posiciones en Google se miran por semana, el cansancio de un anuncio cada dos o tres días. Lo que lee, analiza y prepara borradores puede correr solo; gastar, mover presupuesto, enviar o publicar queda para tu aprobación salvo que lo autorices con topes. Para ver el concepto aplicado, lee cómo armar un loop de marketing en 6 pasos.
¿En qué se diferencia de programar una tarea con un recordatorio?
Una tarea programada repite una acción. Una rutina de esta skill decide si actuar: separa la frecuencia con que mira de la condición para hacer algo, así que la mayoría de las corridas terminan en «revisé, no hay nada que hacer». Antes de actuar comprueba que no sea ruido, estacionalidad o un error de medición. Guarda qué ya resolvió para no repetir el mismo aviso ni escribirle dos veces a la misma persona, y tiene un freno claro con su interruptor para apagarla. La skill también dice cuándo no conviene automatizar: si la tarea es estrategia, si la señal tiene muy pocos datos o si nadie va a mirar el resultado.
¿Qué necesito para usarla?
Las rutinas llaman a otras skills del mismo autor (anuncios, analítica, SEO, emails en frío), así que conviene instalar el repositorio completo. Para programarlas, Claude Code tiene /loop y tareas con horario fijo; en otros agentes usas cron, y para rutinas de mucho criterio alcanza con correr la skill cada lunes a mano. Cada rutina necesita acceso a los datos que lee (Analytics, el administrador de anuncios, el CRM). Está en inglés: pide las fichas y los informes en español. Si quieres que te armen el sistema de agentes, mira el servicio de agentes de IA.
Más skills de Automatización

analytics: armar el plan de medición de tu web con GA4, GTM y UTMs
Arma o audita el plan de medición de tu web: qué eventos medir, cómo nombrarlos, cómo instalarlos en GA4 o GTM y cómo etiquetar los enlaces con UTMs.

attribution: saber qué canal de marketing trae las ventas de verdad
Te ayuda a saber qué canales traen de verdad tus ventas: elige el modelo de atribución, concilia los números que no coinciden entre plataformas y te arma la atribución propia.

cro: encontrar por qué tu página no convierte y qué cambiar primero
Analiza una página o un formulario y te dice por qué no convierte, qué cambiar primero y qué vale la pena probar antes de darlo por hecho.
Para seguir con este tema
- Guía de Agentes de IAEl orden para empezar y las notas de este tema.Guía
- Skills de Claude y ChatGPT para automatizaciónLas skills de Claude para automatización: flujos de n8n, tareas recurrentes con agentes, skills propias y secuencias de email. Cómo usarlas en Claude y en ChatGPT.Skill
- Loop de marketing en 6 pasos: cómo armarlo sin herramientas sueltasEl loop de marketing en 6 pasos que corre en la cuenta de Claura: buscar, crear, publicar, contestar, ordenar y medir, sin herramientas sueltas.Nota
AI KID
RE/MAX Patagon
Mateo Caño