Detalle del Skill

email-report

Generates performance reports from email-service-provider data.

CoincidenciaDirectaRevisado para marketing por correo electrónico
Fuentecognyai/claude-code-marketing-skillsFuente externa
Instalaciones reportadas32Solo señal de popularidad

Revisar antes de usar

La revisión automática comprueba relevancia, no seguridad ni respaldo. Lee las instrucciones de la fuente antes de usar este Skill.

Vista previa guardada

SKILL.md

Este extracto es una copia guardada durante la revisión. La fuente externa contiene la versión completa y actual.

---
name: email-report
description: Auto-generate the weekly or monthly email performance report in three formats — Slack update, CEO email, board-deck section — from real ESP data
version: "1.0.0"
author: Cogny AI
requires: cogny-mcp
platforms: [klaviyo, mailchimp, rule, get-a-newsletter]
user-invocable: true
argument-hint: "[weekly|monthly] [slack|ceo|deck|all]"
allowed-tools:
  # Cogny Cloud (aggregated) namespace
  - mcp__cogny__klaviyo__*
  - mcp__cogny__mailchimp__*
  - mcp__cogny__rule__*
  - mcp__cogny__get_a_newsletter__*
  - mcp__cogny__create_finding
  - mcp__cogny__write_context_node
  - mcp__cogny__read_context_node
  # Cogny Solo / Lite (per-ESP direct) namespace
  - mcp__klaviyo__*
  - mcp__mailchimp__*
  - mcp__rule__*
  - mcp__get_a_newsletter__*
  - Bash
  - Read
  - Write
---

# Email Report

The 3-hour tax every email marketer pays: pulling last period's numbers, charting the trend, explaining the variance, and writing commentary in the right voice for the audience. This skill does it in one command and outputs three versions — Slack ping, CEO email, board deck section — so you can ship the one your stakeholder needs.

**Requires:** Cogny MCP + a connected ESP. [Sign up](https://cogny.com)

## Usage

`/email-report` — monthly report, all three formats (default)
`/email-report weekly` — last 7 days
`/email-report monthly ceo` — monthly, only the CEO email
`/email-report weekly slack` — weekly, only the Slack update

## Prerequisites Check

Detect connected ESP. If none, stop and prompt.

## Steps

### 1. Define the period

| Mode | Current window | Comparison |
|------|----------------|------------|
| weekly | last 7 days | prior 7 days + 4-week rolling avg |
| monthly | last 30 days | prior 30 days + 12-week rolling avg |

State the exact date ranges up front.

### 2. Pull the data

**Per-ESP tool adapter.** The right tool depends on which ESP is connected:

| Data | Klaviyo | Mailchimp | Rule | Get a Newsletter |
|------|---------|-----------|------|------------------|
| Campaign list | `list_campaigns` | `tool_list_campaigns` | `tool_list_campaigns` | `tool_list_sent` |
| Campaign metrics | `get_campaign` + `list_events` (metric-filtered) | `tool_get_report` | `tool_get_campaign_statistics` | `tool_get_report` |
| Automation / flow list | `list_flows` | `tool_list_automations` | `tool_list_journeys` | **not available** |
| Flow metrics | `get_flow` | `tool_get_automation` | `tool_list_journeys` (limited) | **not available** |
| Subscriber list size | `list_profiles` (count) | `tool_get_audience` | `tool_list_subscribers` (count) | `tool_list_contacts` (count) |
| Revenue per send | ✓ via `list_events` with `metric="Placed Order"` | **not available** | **not available** | **not available** |

For the current window AND the comparison window, pull:

**Campaign broadcasts:**
- Each campaign's subject, send date, recipient count, opens, unique opens, clicks, unique clicks, unsubs, bounces.
- **Revenue attributed — Klaviyo only.** For Klaviyo, fetch "Placed Order" events scoped to the send window and attribute by campaign. For Mailchimp/Rule/Get a Newsletter, omit the revenue line entirely from the report and call it out.

**Flows / automations — varies by ESP:**
- Klaviyo: flow name, triggered volume, revenue per flow (via events).
- Mailchimp: automation name, sends, opens, clicks (no revenue).
- Rule: journey name + limited metrics.
- Get a Newsletter: **no flow object exists.** Skip this section; use a "recurring sends" proxy if the user has a newsletter cadence.

**List-level metrics:**
- List size at period start vs end
- New subscribers in period
- Unsubscribes in period
- Net change + growth rate

### 3. Compute the report metrics

For each window, compute:

| Metric | Calc | Why it matters |
|--------|------|----------------|
| Sends | total emails delivered | Volume sanity check |
| Open rate | unique opens / delivered | Subject/preheader effectiveness (MPP-distorted) |
| CTR | unique clicks / delive
Leer la fuente completa en GitHub (abre una página externa)
Contexto

Trabajo relacionado