$18,240 from 3 email campaigns last week
Campaign revenue rose 18% on the week before ($15,410). The VIP early access email earned $0.80 per recipient, five times the full-list restock email.
Every Monday: last week's Klaviyo email campaigns with open and click rates and placed-order revenue, against the week before.
Reads
You get
The card on the right is a sample. Yours shows your own numbers and updates in place every run.
What lands on your board
Campaign revenue rose 18% on the week before ($15,410). The VIP early access email earned $0.80 per recipient, five times the full-list restock email.
For an online store, the Klaviyo question on Monday is simple: how much did last week's emails sell, and which one did it? Answering it means opening each campaign, checking the attribution metric and adding up revenue by hand, then doing the same for the week before to know whether it was good.
The agent asks Klaviyo's reporting API for all of it in two calls, one per week, using Placed Order as the conversion metric. You get revenue per campaign, rates that match what Klaviyo shows, and a one-line answer to "was it a good week".
List metrics with GET /api/metrics and take the ID of "Placed Order" (from your Shopify or other store integration). Save it in the skill so later runs skip this step.
POST /api/campaign-values-reports with timeframe: { start, end } for last Monday to Sunday, conversion_metric_id, filter: equals(send_channel,"email") and statistics: ["recipients", "open_rate", "click_rate", "unsubscribe_rate", "conversions", "conversion_value", "revenue_per_recipient"].
Same call with the previous week. The reporting endpoints have tight rate limits, so make one call per week rather than one per campaign, and wait out a 429 with its Retry-After.
Look up each campaign_id with GET /api/campaigns/{id} for its name and send time.
Total revenue, recipients and campaigns for both weeks, then one row per campaign with rates and revenue, sorted by revenue. Flag a campaign whose unsubscribe rate is over twice the week's average.
With BRIEFKIN_TOKEN set, the agent sends the result as one card that updates in place every run. Without it, you get the report in the chat.
Pick your agent, where the data comes from and how to schedule it; the commands below follow.
One command. It puts the SKILL.md in ~/.claude/skills and in ~/.agents/skills, which Codex, Cursor, Gemini CLI, Copilot CLI and OpenCode read too.
shellcurl -fsSL https://briefkin.dev/skills/klaviyo-weekly-campaign-report/install | shAsk Claude Code:
promptRun the klaviyo-weekly-campaign-report skillOr paste the prompt instead of installing:
promptUsing Klaviyo's Reporting API, find the ID of the Placed Order metric, then call campaign-values-reports twice: last week (Monday to Sunday) and the week before, filtered to email, with recipients, open_rate, click_rate, unsubscribe_rate, conversions, conversion_value and revenue_per_recipient. Look up each campaign's name. Give me total campaign revenue for both weeks with the change, a table of last week's campaigns sorted by revenue, and flag any unsubscribe rate over twice the week's average. End with one line on which campaign earned its place and why.Mondays at 8:00, from cron on any machine where Claude Code is signed in:
crontab0 8 * * 1 claude -p "Run the klaviyo-weekly-campaign-report skill"Add it with crontab -e. A laptop asleep at that time runs it when it wakes if you use launchd or Task Scheduler instead; GitHub Actions works for the API route.
Connect Briefkin once with curl -fsSL https://briefkin.dev/install | sh and every run lands on your board as a report card. How setup works
SKILL.md---
name: klaviyo-weekly-campaign-report
description: "Every Monday: last week's Klaviyo email campaigns with open and click rates and placed-order revenue, against the week before. Use when the user asks for this, or when it runs on a schedule."
---
# Klaviyo weekly campaign report
Every Monday: last week's Klaviyo email campaigns with open and click rates and placed-order revenue, against the week before.
For an online store, the Klaviyo question on Monday is simple: how much did last week's emails sell, and which one did it? Answering it means opening each campaign, checking the attribution metric and adding up revenue by hand, then doing the same for the week before to know whether it was good.
The agent asks Klaviyo's reporting API for all of it in two calls, one per week, using Placed Order as the conversion metric. You get revenue per campaign, rates that match what Klaviyo shows, and a one-line answer to "was it a good week".
## Two ways to get the data
Use the API or MCP route when you have an MCP server, a CLI or an API token for the app. Otherwise, if you can drive a browser the user is signed in to (Claude in Chrome, a Playwright or Chrome DevTools MCP server), use the browser route. Say which one you used.
## Route A: API or MCP server
### What you need
- A Klaviyo private API key with `campaigns:read` and `metrics:read` in `KLAVIYO_API_KEY`.
- Or Klaviyo's official MCP server, connected read-only as a custom connector at `https://mcp.klaviyo.com/mcp?read-only=true` (OAuth; Owner, Admin or Manager role); its `get_campaign_report` tool wraps the same report. The built-in Claude and ChatGPT connectors do not take the read-only parameter.
If something is missing, say what and stop; do not invent numbers.
### Steps
1. **Find the conversion metric** (Klaviyo): List metrics with `GET /api/metrics` and take the ID of "Placed Order" (from your Shopify or other store integration). Save it in the skill so later runs skip this step.
2. **Request last week's campaign values** (Klaviyo): `POST /api/campaign-values-reports` with `timeframe: { start, end }` for last Monday to Sunday, `conversion_metric_id`, `filter: equals(send_channel,"email")` and `statistics: ["recipients", "open_rate", "click_rate", "unsubscribe_rate", "conversions", "conversion_value", "revenue_per_recipient"]`.
3. **Request the week before** (Klaviyo): Same call with the previous week. The reporting endpoints have tight rate limits, so make one call per week rather than one per campaign, and wait out a `429` with its `Retry-After`.
4. **Name the campaigns** (Klaviyo): Look up each `campaign_id` with `GET /api/campaigns/{id}` for its name and send time.
5. **Write the report**: Total revenue, recipients and campaigns for both weeks, then one row per campaign with rates and revenue, sorted by revenue. Flag a campaign whose unsubscribe rate is over twice the week's average.
## Route B: the browser
### What you need
- Signed in to Klaviyo with a user on the right account; the Analyst role is enough to read campaigns and reports.
If something is missing, say what and stop; do not invent numbers.
### Steps
Start at https://www.klaviyo.com/campaigns. The user is signed in already; never type passwords or codes, and ask if a sign-in page appears.
1. **Open the sent campaigns list**: The URL opens Campaigns in the account you used last; switch accounts from the picker at the bottom left if the store is wrong. Filter the list to channel `Email` and status `Sent`, and set the date picker to last Monday through Sunday.
2. **Read each campaign's numbers**: Each row shows recipients, open rate, click rate and placed order revenue. Where a column is missing, open the campaign's report (click the campaign, then **View report**) and read unsubscribe rate and Placed Order revenue from the summary tiles.
3. **Do the week before**: Move the date picker one week back and read the same numbers. If the store sends more than about ten campaigns a week, use **Analytics > Reports** instead: a campaign performance report over the two weeks, exported as CSV.
4. **Write the report**: Total revenue, recipients and campaign count for both weeks, one row per campaign sorted by revenue, revenue per recipient, and a flag on any unsubscribe rate over twice the week's average.
Note: The list shows revenue under the account's attribution settings (Settings > Attribution), the same values the API returns, so both routes agree. A Friday send keeps collecting orders inside the attribution window, so Monday's figure can still grow. For stores with dozens of campaigns a week, the exported report is faster than opening each one.
## The report
- **Revenue from campaigns** last week and the change on the week before.
- **Per campaign**: recipients, open rate, click rate, orders and revenue.
- **Revenue per recipient**, to compare big and small sends fairly.
- **Flags**: unsubscribe spikes.
- One line on which campaign earned its place.
## Post it to Briefkin
When `BRIEFKIN_TOKEN` is set, or `~/.config/briefkin/env` exists (the installer from https://briefkin.dev/docs writes it), also send the result to the user's Briefkin board as one card. Keep the `item_key` the same on every run so the card updates in place, use a new `event_id` per run, and put today's real numbers in place of the example ones. If the request fails, say so once and carry on.
```bash
[ -n "${BRIEFKIN_TOKEN:-}" ] || . ~/.config/briefkin/env
curl -sS -X POST "${BRIEFKIN_URL:-https://briefkin.dev}/v1/events" \
-H "authorization: Bearer $BRIEFKIN_TOKEN" \
-H "content-type: application/json" \
-d @- <<'JSON'
{
"v": 1,
"event_id": "klaviyo-weekly-campaign-report/<date of this run, e.g. 2026-10-16>",
"item_key": "klaviyo-weekly-campaign-report",
"project": "Acme Store",
"source": "Klaviyo weekly campaign report skill",
"kind": "update",
"title": "$18,240 from 3 email campaigns last week",
"summary": "Campaign revenue rose **18%** on the week before ($15,410). The VIP early access email earned **$0.80 per recipient**, five times the full-list restock email.",
"widget": [
{
"type": "Table",
"props": {
"columns": [
"Campaign",
"Recipients",
"Open rate",
"Click rate",
"Revenue"
],
"align": [
"left",
"right",
"right",
"right",
"right"
],
"rows": [
[
"VIP early access: fall drop",
12400,
"52.1%",
"4.8%",
"$9,860"
],
[
"Fall restock is here",
41200,
"38.4%",
"1.9%",
"$6,130"
],
[
"Weekly picks #42",
39800,
"35.2%",
"1.2%",
"$2,250"
],
[
"Total",
93400,
"",
"",
"$18,240"
]
]
}
},
{
"type": "Callout",
"props": {
"text": "Small, targeted sends beat the full list again: the VIP segment is 13% of recipients and 54% of revenue.",
"tone": "info"
}
}
]
}
JSON
```
Widgets come from the Briefkin catalog (https://briefkin.dev/v1/catalog). Without a token, just give the user the report.
## Run it on a schedule
Suggested: Mondays at 8:00 (`0 8 * * 1`). From cron, with the agent signed in on that machine:
```bash
0 8 * * 1 claude -p "Run the klaviyo-weekly-campaign-report skill"
# Codex: codex exec, Gemini CLI: gemini -p, Copilot CLI: copilot -p, OpenCode: opencode run
```
Or use the agent's own scheduler (Claude Code routines, Codex automations, Claude or ChatGPT scheduled tasks): https://briefkin.dev/skills/klaviyo-weekly-campaign-report#schedule
Source: https://briefkin.dev/skills/klaviyo-weekly-campaign-report
A Klaviyo private API key with campaigns:read and metrics:read in KLAVIYO_API_KEY.
Or Klaviyo's official MCP server, connected read-only as a custom connector at https://mcp.klaviyo.com/mcp?read-only=true (OAuth; Owner, Admin or Manager role); its get_campaign_report tool wraps the same report. The built-in Claude and ChatGPT connectors do not take the read-only parameter.
https://mcp.klaviyo.com/mcp, which signs in with OAuth; it also runs locally with uvx klaviyo-mcp-server@latest and a private key in PRIVATE_API_KEY. In Claude Code, run claude mcp add --transport http klaviyo "https://mcp.klaviyo.com/mcp?read-only=true"; Cursor and Codex take the same URL in their MCP config. Its reporting tools are get_campaign_report and get_flow_report, alongside tools for campaigns, flows, lists, segments, profiles and templates (docs).KLAVIYO_API_KEY, and send Authorization: Klaviyo-API-Key <key>.read-only=true on the MCP URL (or READ_ONLY=true locally) disables every tool that can write to your account, and disable-tools-with-user-generated-content=true keeps subscriber-written content out of the agent's context.
It should, when you use the same conversion metric and attribution settings: the reporting API returns the values Klaviyo's own campaign reports use. Small gaps come from orders still arriving inside the attribution window, so Monday's figure for a Friday send can still grow.
No; flows such as welcome or abandoned cart run every day and have a separate flow values report. Add a second card for them, or a monthly check, rather than mixing them into the campaign week.
No. The skill runs with your own agent and gives you the report in the chat. With a Briefkin token set, each run also posts it to your board as a report card, so you can glance at it instead of asking again.
Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot CLI, OpenCode, Windsurf and Amp all read SKILL.md files. The install command puts it in ~/.claude/skills and ~/.agents/skills, where they look. ChatGPT, the Claude app and Grok take the prompt instead. Pick your agent under "Install and run it" and the commands change to match.
Yes. Switch the data source to "Your browser" and the steps change to the Klaviyo pages themselves: the agent opens www.klaviyo.com/campaigns in a browser you are signed in to and reads the numbers off the page. Claude Code, Codex, Cursor, Claude app and ChatGPT can drive a browser out of the box; Gemini CLI, Copilot CLI and OpenCode need a Playwright or Chrome DevTools MCP server first. It is slower than the API and needs you signed in, so it suits a report you run by hand or from a scheduler on your own computer.
Skills are free to use with any agent. Briefkin is where their results land: one board for every report, number and question your agents send, with a ping when something needs you.
Free during the open beta. No card.