Email & SMS Marketer
by
Lifecycle program review for ecommerce teams: separate flow revenue from campaign and blended revenue, then write the flow tweaks, campaign themes and list-health actions into Notion.
Lifecycle programs get reviewed on the ESP's revenue figure, which credits a flow with any order that follows an open and therefore credits almost everything twice. On that number every flow looks like it is working and the program looks like it is growing, right up to the point where someone compares the total to what the business actually took. This skill separates flow revenue from campaign and blended revenue on one definition, reviews the whole program against it, and writes the flow tweaks, campaign themes and list-health actions into Notion with an owner on each.
What It Does
- Separates flow, campaign and blended revenue on one definition.
- Reviews every flow for step-level drop-off and revenue per recipient.
- Tracks list growth, engagement decay and placement as one health picture.
- Identifies the campaign themes that earned rather than the ones that opened.
- Ranks the changes by the revenue sitting behind each one.
- Writes flow tweaks, campaign themes and list-health actions into Notion.
Use Cases
- Stop reporting lifecycle revenue that double counts every order.
- Find the flow step where the drop-off is worth fixing first.
- Give a lifecycle manager a ranked backlog rather than a monthly readout.
- Catch list decay before it shows up as a placement problem.
Example Session
Review our lifecycle program and tell me what to work on next month.
Your ESP reports $214k. On one definition the program produced $96k. Here is where it sits.
- Area | ESP figure | Reconciled | Gap | Next action
- Abandoned checkout | $71k | $38k | 46% | Fix step 2 drop-off
- Welcome | $44k | $19k | 57% | Add a second offer step
- Post-purchase | $31k | $22k | 29% | Working, leave it
- Campaigns | $68k | $17k | 75% | Cut cadence, narrow segments
The campaign line is the finding: $68k reported against $17k reconciled, because campaigns take credit for orders the flows and paid had already earned. Abandoned checkout is the opposite, genuinely the strongest thing you run, and its step two loses 61% of the people who opened step one. Fix that first, then cut campaign cadence.
Why This Beats Prompting It Yourself
ESP Attributed Revenue vs One Definition: The Hidden Risk
A generic prompt reads the ESP's revenue figure because it is the number sitting in the report. That figure credits a flow with any order that follows an open, within a window the ESP chose, with no view of what paid or another flow contributed to the same order. Summed across a program it routinely exceeds what the business actually took.
When You Still Need The Program Ranked By Real Revenue
A backlog is only as good as the numbers that ordered it. This skill states $214k reported against $96k reconciled and shows where the gap sits, which moves campaigns to the bottom of the list and abandoned checkout to the top. Each action goes to Notion with an owner, so the next review opens on what was assigned rather than on the same readout.
Known Limitations
Reconciled revenue needs orders joined to sends at recipient level, and where only aggregate ESP reporting is available the skill works at that grain and labels every figure as attributed rather than reconciled. SMS and email are reconciled together, so a program running both will see some orders that could plausibly credit either. It writes the actions to Notion and does not change anything in your ESP.
Install It
- Download the ZIP.
It is free and there is no account to create. - Unzip it into your agent's skills folder.
Claude Code reads ~/.claude/skills/, which is hidden by default: the command in the folder block opens it. Other agents scan their own directory, so drop the same folder there instead. - Ask your agent to use it.
Restart the agent if it was already running, then it picks the skill up with no config.
skills folder
Copy
~/.claude/skills/email-and-sms-marketer/
SKILL.md
references/revenue-definitions.md
reviews/
# one review per month, pushed to Notion
# macOS: create the folder and open it in Finder
mkdir -p ~/.claude/skills && open ~/.claude/skills
# Windows: paste in the Explorer address bar
%USERPROFILE%\.claude\skills\Frequently asked questions
How is this different from my ESP's reporting?
The ESP reports what it attributed. This reconciles the same sends against orders on one definition, separates flow from campaign from blended, and shows the gap. For most programs the gap is large and concentrated in campaigns, which changes what you work on next.
Which agents does the skill run in?
Any agent that supports the open SKILL.md format: Claude Code, Cursor, Codex CLI, GitHub Copilot, Gemini CLI, Manus, Grok and others load it unmodified. The format is portable, the location is not. Each agent scans its own skills directory, so you drop the same folder into whichever one yours uses. There is no config file to edit and no API key to provision.
What does it need connected to work?
Send and engagement data per recipient, plus orders. With both it reconciles properly. With aggregate ESP reporting only it still reviews step-level drop-off and list health, and labels every revenue figure as attributed.
Why do campaigns always look worst?
Because campaigns go to people who were already going to buy more often than flows do, and the ESP credits them for it. It does not mean campaigns are worthless, it means their real contribution is smaller than reported and the cadence is usually higher than it should be.
Does it look at SMS separately?
It reviews both and reconciles them together, because an order following an email and an SMS within the same window can plausibly credit either. Where the two overlap heavily the output says so rather than splitting the credit on an assumption.
What is included with the skill?
The skill itself, the revenue definitions reference, the monthly review template, and the Notion action format. It is free and security scanned. We re-publish the ZIP when the definitions change, so download it again if your reconciled figures move.
Lifecycle revenue depends on which revenue you claim.
Polar separates flow, campaign and blended revenue in one semantic layer, so flow tweaks and campaign themes are judged on incremental value.
<script type="application/ld+json">{"@context":"https://schema.org","@type":"FAQPage","mainEntity":[{"@type":"Question","name":"How is this different from my ESP's reporting?","acceptedAnswer":{"@type":"Answer","text":"The ESP reports what it attributed. This reconciles the same sends against orders on one definition, separates flow from campaign from blended, and shows the gap. For most programs the gap is large and concentrated in campaigns, which changes what you work on next."}},{"@type":"Question","name":"Which agents does the skill run in?","acceptedAnswer":{"@type":"Answer","text":"Any agent that supports the open SKILL.md format: Claude Code, Cursor, Codex CLI, GitHub Copilot, Gemini CLI, Manus, Grok and others load it unmodified. The format is portable, the location is not. Each agent scans its own skills directory, so you drop the same folder into whichever one yours uses. There is no config file to edit and no API key to provision."}},{"@type":"Question","name":"What does it need connected to work?","acceptedAnswer":{"@type":"Answer","text":"Send and engagement data per recipient, plus orders. With both it reconciles properly. With aggregate ESP reporting only it still reviews step-level drop-off and list health, and labels every revenue figure as attributed."}},{"@type":"Question","name":"Why do campaigns always look worst?","acceptedAnswer":{"@type":"Answer","text":"Because campaigns go to people who were already going to buy more often than flows do, and the ESP credits them for it. It does not mean campaigns are worthless, it means their real contribution is smaller than reported and the cadence is usually higher than it should be."}},{"@type":"Question","name":"Does it look at SMS separately?","acceptedAnswer":{"@type":"Answer","text":"It reviews both and reconciles them together, because an order following an email and an SMS within the same window can plausibly credit either. Where the two overlap heavily the output says so rather than splitting the credit on an assumption."}},{"@type":"Question","name":"What is included with the skill?","acceptedAnswer":{"@type":"Answer","text":"The skill itself, the revenue definitions reference, the monthly review template, and the Notion action format. It is free and security scanned. We re-publish the ZIP when the definitions change, so download it again if your reconciled figures move."}}]}</script>