Hire an AI email flow results and rebuild review

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• This month against last month, with the sums
• A verdict on last month's fix, helped, no change or worse
• One rebuilt flow with its first two emails reviewed and fixed
• A list of changes to approve, most important first
• The next three tests, with sample sizes

How it does the job well

• Write for one named audience and one action. Each asset has a single job.
• Use the customer's own words from reviews, calls or surveys before inventing language.
• Every claim needs proof the business can show. Leave unproven claims out or mark them.
• Judge results against the business goal, such as profit or qualified leads, not clicks alone.

Mistakes it avoids

• Calling a month good or bad from open rates alone. They are unreliable since Apple Mail privacy protection. Lead with clicks and placed orders.
• Rebuilding several flows at once. You cannot tell which one worked.
• Judging a rebuilt flow before it has had a full month of sends.
• Treating the benchmarks in the skills as promises. Compare with the store's own history first.
• Sending, scheduling or switching on anything.
• Generic copy that could fit any brand.

What a good result looks like

An example, not your task: You have email flows running and want one monthly check done the same way each time.

• This month. Your channel score, flow revenue and clicks against last month, with the sums shown.
• Last month's fix. Whether the flow rebuilt last month helped, made no change or got worse, with numbers.
• Path taken. Whether it fixed sending first, rebuilt a flow or did both, and why.
• Rebuilt flow. The one rebuilt flow, with a ready or needs your eyes mark for the first two emails.
• Changes to approve. Up to ten changes, most important first, each with where it goes and why.
• Next tests. The top three tests, each with a sample size and a win rule.

How the work is checked

• Every claim about change has this month's and last month's number beside it, with the sum shown.
• Only one flow was rebuilt.
• No rebuild was proposed in a month with sending trouble, except a missing welcome or cart flow.
• Every new email was reviewed, and the rounds stop at two.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

A second opinion

Before it hands back, your AI reviews the draft the way Claude Hopkins would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Read last time. Opens last month's saved summary, so it knows the score, the flow it rebuilt and the tests it set.
• Read the month. Runs the email and SMS performance reader and shows the change in score, flow revenue and clicks.
• Check the last fix. Compares the flow it rebuilt last month with the month before. It says helped, no change or worse.
• Score the flows. Runs the flow gap checker to find missing flows, wrong triggers and the weakest flow.
• Choose the path. If mail is landing badly, it fixes sending first and holds back rebuilds. If many contacts never open, it adds the sunset flow.
• Rebuild one flow. Picks one flow, missing core flows first, and runs the matching builder.
• Check the new copy. Reviews the first two emails and fixes them, for up to two rounds, until each is ready.
• Set the tests and save. Sets the top three tests and saves a summary for next month. It stops for your yes.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id monthly-email-flow-keeper only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/monthly-email-flow-keeper/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• Last month's and the month before's campaign list and flow revenue from your email tool (at least two months, so it can compare)
• Your live flows with trigger, filters, delay and number of emails (the first time)
• Deliverability and list growth figures if you have them
• Your brand file, offer and best sellers, for a rebuild
• What changed last month, such as a new pop-up or a sale (optional)

Helpful context (optional)

• A note of every change you made to flows or settings last month
• Site traffic for the same month, because flow revenue follows traffic

Tools and access

• Claude Code: It can keep the keeper folder, read last month's files. You start each run. It does not run on a timer unless you connect a scheduler.
• Klaviyo: Klaviyo is a paid email service. Export campaign and flow analytics, with test variants included, for at least the last two months (90 days is best). Other email tools have similar exports.
• Klaviyo: Paid service with an account. Any email tool that exports the same columns works too. Its export of campaign and flow analytics, by-provider report and test results give the figures this skill reads.
• Shopify: Paid store plan with an account. Traffic, orders and average order value show whether a drop is a site problem.
• Any good chat AI: Any current chat AI can read an exported file and apply the steps.
• Klaviyo: Paid service with an account. Not required, since you can paste a flow list instead. Its flow screens show triggers, filters, delays and revenue per flow, which is everything this check reads.
• Shopify: Paid store plan with an account. Not required. It provides the Checkout Started and Placed Order events, and the Added to Cart event with the right tracking.
• Klaviyo: Its sending domain, smart sending and attribution screens hold most of the settings checked. It is a paid service, and which settings you see may depend on your plan.
• Google Postmaster Tools: It shows your domain reputation and spam rate in Gmail after the set-up is fixed.
• Your DNS host: It is where the NS, TXT and DMARC records are added.
• Klaviyo: Paid service with an account. Its segments build the 14 to 90 day groups, and its delivery reports show opens by inbox provider.
• Google Postmaster Tools: It shows your domain reputation and spam rate for Gmail, which tells you if the problem is real.
• Klaviyo: Paid email service; the sunset steps need an account. Its profile properties, segments and suppression import match these steps, and billing is per active profile.
• Shopify: Paid plan needed. Order data keeps recent buyers out of the segment.
• Any good chat AI: Any current chat AI can write the conditions from your description.
• Klaviyo: Flows, filters, dynamic coupons and revenue per recipient reports match the steps in this skill. It is a paid service.
• Shopify: Order and customer data decide who drops out of the flow and who gets a code.
• Any good chat AI: Any current chat AI can run the skill from the pasted facts.
• Klaviyo: Its added-to-cart and checkout events, dynamic product blocks and flow filters match the steps.
• Shopify: The theme code, saved checkout link and order events feed both flows.
• Any good chat AI: Any current chat AI can run the skill from your pasted facts.
• Klaviyo: Viewed-product and active-on-site triggers, product feeds and dynamic blocks fit these steps.
• Shopify: Product views and cart events reach the email tool through its connection.
• Any good chat AI: Any current chat AI can run the skill from pasted facts.
• Klaviyo: Placed-order triggers, order-count splits and flow filters fit the steps.
• Shopify: Order, shipping and cancelled-order data drive the filters.
• Any good chat AI: Any current chat AI can run the skill from your pasted product facts.
• Klaviyo: A paid email tool (it has a free plan with limits). The predicted next-order date and customer value steps need it or a tool with the same fields.
• Shopify: A paid store plan. Its order history gives the gap between purchases.
• Any good chat AI: Any current chat AI can do the sums from pasted order data.
• Any good chat AI: Any current chat AI can count words, mark cuts and map the pacing. Paste the email as text.
• Klaviyo: Paid service with an account. Shows opens and clicks per email, so you can test whether the rules of thumb hold for your list.
• Klaviyo: Paid service with an account. Its A/B tests show win probability and placed order rate, and flows can split into paths for timing tests. Check that your plan includes A/B testing.
• Google Sheets: A test log with one row per test keeps hypothesis, sample, result and the next step in one place.

Functions and deliverables

• Email flow results and rebuild review: Review email results and sending problems. Get one proposed flow rebuild, copy checks and a short test list.
  • This month against last month, with the sums
  • A verdict on last month's fix, helped, no change or worse
  • One rebuilt flow with its first two emails reviewed and fixed
  • A list of changes to approve, most important first
  • The next three tests, with sample sizes
• Email and SMS results reviewer: Review email and SMS results against your own history. Get possible causes, tests to try and a house score with missing checks shown.
  • Observed findings and possible causes, kept separate
  • Campaign types to repeat or rework as tests
  • Delivery concerns supported by the supplied checks, with unknowns shown
  • A house score for judged areas, or NOT SCORED if no area can be judged
• Email automation gaps and trigger reviewer: Review a store’s email flows, triggers and timing. Get missing steps, possible rule conflicts and a house score based only on what was shown.
  • A score out of 100, with how it was worked out
  • Missing flow candidates, prioritized using available recipients and results
  • Trigger, filter and timing errors, each with a fix
  • The order to build or rework them
• Email setup health checker: Check your email setup for spam risks. Paste your DNS records and settings. You get a score out of 100 and the exact fix for each fault.
  • A score out of 100, with how it was worked out
  • A list of failed checks with a fix for each
  • A DMARC record to add and a plan to tighten it over time
  • A table of current against recommended settings
• Email deliverability recovery planner: Fix low email opens and spam placement. Give it your open rates and engaged counts. You get a score out of 100 and a staged recovery plan.
  • A health score out of 100, with what was measured and how
  • The likely cause, set-up or engagement
  • A weekly plan with gates for each stage, and which flows stay on
  • A tracker of open rate by segment, with rules to widen or hold
• Inactive subscriber cleanup planner: Define an inactive segment. Get a three-email re-engagement flow and monthly steps to suppress contacts with no opens or clicks.
  • A segment definition for unengaged profiles
  • A three-email sunset flow plan with timing
  • Monthly suppression steps
  • A rule for who is never suppressed, such as recent buyers
• Welcome flow builder: Build a welcome email flow for new subscribers. Give it your offer and best sellers. Get timing, filters, email outlines, SMS and tests.
  • The flow spec: trigger, filter, delays and exit rule
  • An outline for each email: purpose, sections, button placement and the offer line
  • Subject line and preview ideas for each email, and a three-text SMS plan if you use SMS
  • Targets to watch and the first three tests, with the offer-step test
• Cart and checkout email planner: Share your products, store terms and discount rules. Get separate cart and checkout email plans.
  • A check of which trigger your current flow uses
  • Install and test steps for the added-to-cart event, if it is missing
  • Two flow specs, cart and checkout, with filters, delays and exit rules
  • An outline for each email with subject ideas and notes on the product block
• Browse abandonment email flow builder: Share products, proof and offer rules. Get site-visit and product-view email flows, with entry rules, timing and message outlines.
  • A site abandon spec and one email outline
  • A browse abandon spec and four or five email outlines, with the discount last
  • Exit filters that hand shoppers to the cart and checkout flows
  • Delay tests and what to read after a month
• Post-purchase flow builder: Plan the six emails sent after an order. Get the trigger, an order-count split, outlines and subject ideas for each email.
  • A flow spec with the trigger, filters and a split by number of past orders
  • Six email outlines with subject line ideas
  • An opening line for first, second, third and later orders
  • Timing for each email and a rule for when to move it
  • A list of campaign winners to copy into the flow later
• Win-back flow builder: Share your order gaps and discount room. Get a win-back flow timed to how your buyers actually reorder.
  • A trigger day and an exit filter
  • Three to six email outlines with timing and an offer for each
  • A win-back segment definition for extra campaigns
  • A short subscriber-cancel branch, if you run a subscription
• Email draft reviewer: Paste your email draft to get cuts, a pacing map, subject line fixes, a score out of 100 and a ship or fix verdict before you send it.
  • A marked draft with cuts and rewrites
  • A line-length (pacing) map
  • Subject line rewrites
  • A score out of 100 with its sum, a ship or fix verdict, and three fixes
  • A list of I and we lines flipped to you, with before and after
• Email test planner: Plan email and popup A/B tests that can finish. Get a ranked test queue with sample sizes, run times and rules for calling a winner.
  • A ranked test queue, each test with a hypothesis
  • A sample size and run time for every test
  • Set-up notes, the winning metric and the rule for calling a result
  • A skip list of tests your volume can't support, with the reason
  • A test cadence and what to record after each result
• Brand profile builder: Share your website. Get a reusable profile covering your products, customers, voice and approved claims, with sources.
  • A folder of eight plain files, from a start file for your AI to a claims list and a change log
  • A tag on every fact, and every claim marked approved, pending or banned
  • A two-sentence diagnosis of your biggest gap, and a list of what's missing and who can answer it
  • A short slice for your next step, if you name one
• Claude Hopkins: Write specific ads or plan a small buyer test using Claude Hopkins’s recorded approach. Replace vague praise with facts and track cost per customer.
  • Your problem worked on the way Claude Hopkins would: their questions, their method, their push-back
  • The answer or the work, in Claude Hopkins's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step

Tasks you can use it for

• You have email flows running and want one monthly check done the same way each time.
• Email revenue slipped and you want to know whether to fix sending or a flow first.
• You rebuilt a flow last month and want to know whether it helped.

Limits to check before starting

• You have under two months of numbers or no live flows yet: use the Email and SMS results reviewer alone for a one-off check.
• You want to send a campaign or turn a flow on: do that in your email tool, because this agent never sends or switches anything on.
• You only want to rebuild one flow with no monthly check: use the matching flow builder, such as the welcome flow builder, on its own.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Start a chat with the agent. In Claude Code, add it as a skill or save it in .claude/agents, then ask it to run this month's check.
• Export last month's campaign and flow numbers from your email tool and put them in one folder, or attach them in the chat.
• The first time, paste your live flows. It saves them and reuses them.
• Read the changes to approve. Make the ones you agree with in your email tool. Nothing goes out until you do.
• Run it again next month. It compares against its saved summary.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/monthly-email-flow-keeper for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.