agentsclimarketplace

Klaviyo weekly

Skill NovateStudioGit/novate-studio-skills/email-marketing/klaviyo-weekly

Monday morning Klaviyo intelligence — pulls last 7 days of campaign + flow performance, attributes revenue, flags underperformers, recommends one A/B test, one flow tweak, and one new campaign theme for the week ahead. ~2 min, fully automated. Trigger when the user says "weekly report", "Monday update", "how did emails do last week", "Klaviyo weekly", or per-cron on Mondays.From its SKILL.md

Install
npx -y skills add NovateStudioGit/novate-studio-skills --skill klaviyo-weekly

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

4.8 KB, ~1.2k tokens by cl100k_base, as published. Nobody here has run it

Brand scoping

Outputs live under ~/notes/Klaviyo/<brand>/<subfolder>/, where <brand> is resolved at run time from the connected Klaviyo account's organizationName attribute (via mcp__claude_ai_Klaviyo__klaviyo_get_account_details). For ExampleBrand, this resolves to ExampleBrand. If multiple brands are connected, ask Will which brand the current run is for.

/klaviyo-weekly

The agency Monday strategy call, run as a skill. Pulls real numbers from Klaviyo, attributes revenue, and outputs three concrete moves for the week ahead. Replaces the "let me hop on a call to walk you through the dashboard" call.

Flow

  1. Resolve the brand + date range — default: last 7 days for the brand connected to the Klaviyo MCP. If multiple brands in scope, ask which.
  2. Pull campaign performancemcp__claude_ai_Klaviyo__klaviyo_get_campaigns filtered to send dates in range. For each, call klaviyo_get_campaign_report to get opens / clicks / conversions / revenue.
  3. Pull flow performancemcp__claude_ai_Klaviyo__klaviyo_get_flows. For each active flow, call klaviyo_get_flow_report for the date range.
  4. Pull baseline metricsmcp__claude_ai_Klaviyo__klaviyo_query_metric_aggregates for Placed Order (total brand revenue) over the same window. Compute email revenue share = (email-attributed revenue) / (total revenue).
  5. Compute the table — see ## Output structure below.
  6. Generate recommendations — exactly three:
    • One A/B test to run this week. Pick a high-volume campaign type and a single variable (subject line / send time / CTA / preview text). Specify hypothesis + variant + success metric.
    • One flow tweak — identify the lowest-performing flow step in the report and propose a specific edit (subject line rewrite, delay adjustment, content swap).
    • One new campaign theme — based on what hasn't been covered in the last 14 days, propose a theme + product + segment for a fresh send.
  7. Save the report~/notes/Klaviyo/<brand>/weekly-reports/YYYY-MM-DD.md.
  8. Print summary to chat — top-line numbers + three recommendations + link to the file. No emojis.

Output structure

# Klaviyo Weekly — [brand] — YYYY-MM-DD (week of YYYY-MM-DD to YYYY-MM-DD)

## Headline numbers

- **Email revenue share:** N% (benchmark: 30-40%)
- **Total email revenue:** $X
- **Campaigns sent:** N
- **Active flows:** N
- **Total emails delivered:** N
- **Avg open rate:** N% (with iOS MPP caveat)
- **Avg click rate:** N%
- **Avg unsubscribe rate:** N% (red flag at >0.5%)
- **Avg complaint rate:** N% (red flag at >0.1%)

## Campaigns

| Send date | Campaign | Segment | Delivered | Open % | CTR | Revenue | RPR |
|---|---|---|---|---|---|---|---|
| ... | ... | ... | ... | ... | ... | ... | ... |

Top performer: **[name]** — why it worked (one line).
Bottom performer: **[name]** — what likely hurt it (one line).

## Flows

| Flow | Step | Delivered | Open % | CTR | Revenue | Issue? |
|---|---|---|---|---|---|---|

Top: **[flow + step]**.
Underperforming: **[flow + step]** — specific issue.

## Three moves for this week

### 1. A/B test
**Hypothesis:** ...
**Variable:** subject line / send time / CTA / preheader
**Test on:** [campaign type]
**Success metric:** [open / CTR / revenue]
**Sample size needed:** N per variant

### 2. Flow tweak
**Flow:** [name]
**Step:** [N]
**Current state:** ...
**Proposed change:** ...
**Expected impact:** ...

### 3. New campaign theme
**Theme:** ...
**Product(s):** ...
**Segment:** ...
**Why now:** ...
**Brief for `/klaviyo-campaign`:** [one-line prompt to feed straight in]

What this skill does NOT do

  • Does not auto-implement recommendations — those are surfaced for Will to invoke /klaviyo-campaign, /klaviyo-flow, or /klaviyo-ab.
  • Does not pull SMS performance separately — bundled into the same metrics where Klaviyo treats them as one channel.
  • Does not deliver a multi-week trend report — that's a different skill (/klaviyo-monthly if ever needed).

Failure modes

  • No campaigns sent in range → still output flow + revenue numbers, note "no campaigns this week" + recommend one for next week.
  • Klaviyo MCP not connected → tell Will, stop.
  • Multiple brands connected, ambiguous → ask which brand before running.

Cadence

Designed to run every Monday. Can be scheduled via the /schedule skill or cron to fire automatically. The output overwrites nothing — each report is its own dated file.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 326,452. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.