Monthly Content Report logo

Monthly Content Report

Community
antoniolg
monthly-content-report

Genera el informe mensual de correlación entre contenido publicado en X, visitas a /cursos/expert/ai en Umami y ventas de AI Expert. Cruza métricas para identificar qué contenido impulsa conversiones. Úsalo cuando Antonio pida el informe mensual, el análisis de ventas del mes, o quiera saber qué posts funcionan mejor para vender.

Overview

Publisherantoniolg
Repositoryagent-kit
Skill namemonthly-content-report
Stars
97
Forks
16
Bundled files
3
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by antoniolg on GitHub. Read the source before you install it.

Installation

Install the Monthly Content Report AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/antoniolg/agent-kit.git /tmp/agent-kit
mkdir -p .claude/skills
cp -r /tmp/agent-kit/skills/monthly-content-report .claude/skills/monthly-content-report
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Monthly Content Report in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Monthly Content Report on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Monthly Content Report is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Monthly Content Report — Correlación contenido → tráfico → ventas

Genera un informe mensual que cruza:

  1. Posts de X publicados en el período (via bird CLI)
  2. Tráfico a /cursos/expert/ai en Umami (pageviews diarios)
  3. Ventas de AI Expert registradas en Google Sheets

El objetivo es entender qué contenido genera tráfico y conversiones reales.

Configuración requerida

Fichero ~/.config/skills/config.json bajo clave monthly_content_report:

json
{
  "monthly_content_report": {
    "umami_url": "<your-umami-url>",
    "umami_user": "<umami-username>",
    "umami_pass": "<umami-password>",
    "umami_website_id": "<umami-website-id>",
    "umami_path": "<path-to-track>",
    "thrivecart_api_key": "<api_key>",
    "thrivecart_product_id": 0
  }
}

Fuentes de datos

1. Posts de X (bird CLI)

bash
bird timeline --count 200 --since YYYY-MM-DD --until YYYY-MM-DD

Filtrar solo posts propios (no RTs), obtener: fecha, texto, likes, RTs, replies, impresiones.

2. Tráfico Umami

Script: scripts/umami-pageviews.js

bash
node scripts/umami-pageviews.js --start YYYY-MM-DD --end YYYY-MM-DD

Autenticación: POST /api/auth/login → JWT Pageviews: GET /api/websites/{id}/pageviews?startAt=&endAt=&unit=day&timezone=Europe/Madrid&path=eq.%2Fcursos%2Fexpert%2Fai

Salida: array [{date, pageviews, sessions}]

3. Ventas (ThriveCart API)

Script: scripts/thrivecart-sales.js

bash
node scripts/thrivecart-sales.js --start YYYY-MM-DD --end YYYY-MM-DD --json
  • Producto AI Expert: ID 9
  • Filtrar transaction_type == "charge" → primera compra (único o primer plazo)
  • Ignorar rebill (plazos posteriores) y failed
  • Campo related_to_recur: true indica pago a plazos
  • Campos útiles: date, customer.email, customer.name, amount_str, item_pricing_option_name

Workflow del agente

  1. Determinar período: por defecto el mes anterior completo. Preguntar si quiere otro rango.

  2. Obtener datos en paralelo:

    • Posts de X del período
    • Pageviews diarios de Umami
    • Ventas del período del Sheet
  3. Correlacionar:

    • Para cada día con ventas: ¿qué posts se publicaron ese día o los 2-3 días anteriores?
    • Para cada post: ¿cuánto subió el tráfico el día de publicación y los siguientes?
    • Calcular correlación entre engagement de posts y picos de tráfico
    • Identificar posts publicados dentro de los 7 días previos a cada venta
  4. Generar informe con estructura:

    ## Resumen mes [MES YYYY]
    - Total ventas: X (€ total)
    - Total visitas /cursos/expert/ai: X
    - Posts publicados: X
    - Conversión estimada: X%
    
    ## Posts con mayor impacto en tráfico
    [tabla: fecha | texto (100 chars) | likes | RTs | pico tráfico siguiente día | variación %]
    
    ## Días de venta y contenido previo
    [para cada venta: fecha venta, posts publicados en los 7 días anteriores]
    
    ## Top posts del mes (por engagement)
    [top 5 por likes+RTs]
    
    ## Insights y recomendaciones
    [qué temáticas/formatos correlacionan mejor con ventas]
  5. Guardar en ~/Documents/aipal/reports/monthly-content-report/YYYY-MM.md

  6. Enviar resumen compacto por Telegram

Registro en el vault (paso final obligatorio)

Después de guardar el informe completo en ~/Documents/aipal/reports/monthly-content-report/YYYY-MM.md, añadir una entrada al fichero ~/Documents/aipal/10-areas/contenido/learnings.md. Si el fichero no existe, crearlo.

Formato del bloque a añadir (append, nunca truncar):

markdown
## YYYY-MM — Informe mensual

- **Ventas**: X unidades / €X.XXX
- **Visitas /cursos/expert/ai**: X pageviews
- **Posts publicados**: X
- **Top posts por correlación con ventas**: [títulos o fragmentos]
- **Patrón detectado**: [breve descripción del patrón contenido→ventas más claro del mes]
- **Temáticas con mejor rendimiento**: [lista]
- **Temáticas con peor rendimiento**: [lista]
- **Informe completo**: `reports/monthly-content-report/YYYY-MM.md`

Este registro permite que futuras sesiones (y otras skills como weekly-newsletter) conozcan qué contenido convierte sin necesidad de releer el informe completo.

Notas importantes

  • Umami auth con path=eq.%2Fcursos%2Fexpert%2Fai (formato URL de Umami v2+, NO url= ni filters=)
  • Solo contar primera compra en ventas a plazos
  • Los posts de X via bird son solo los propios, no RTs ni respuestas
  • Correlación no es causalidad: señalar posibles relaciones, no afirmarlas

Scripts auxiliares

  • scripts/umami-pageviews.js — Obtiene pageviews de Umami por día
  • scripts/correlate.js — Cruza datos y genera tabla de correlación

Ejecución manual

bash
# Informe del mes anterior
node scripts/monthly-report.js

# Informe de un mes específico
node scripts/monthly-report.js --month 2026-01

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Monthly Content Report AI skill do?

Genera el informe mensual de correlación entre contenido publicado en X, visitas a /cursos/expert/ai en Umami y ventas de AI Expert. Cruza métricas para identificar qué contenido impulsa conversiones. Úsalo cuando Antonio pida el informe mensual, el análisis de ventas del mes, o quiera saber qué posts funcionan mejor para vender.

Why use Monthly Content Report on TypingMind?

Because you install it once and use it with any model. Monthly Content Report is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Monthly Content Report in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/antoniolg/agent-kit/tree/main/skills/monthly-content-report. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Monthly Content Report?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Monthly Content Report?

As many as you like. As long as a model supports skills, you can use Monthly Content Report with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Monthly Content Report AI skill free?

It is published on GitHub by antoniolg. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇