Hire an AI email delivery recovery and quiet-subscriber plan

Everything it can hand back

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

• An email setup score out of 100, each failed check with the exact fix, and the DMARC records to add
• An inbox health score out of 100, a diagnosis, and a staged recovery plan with gates at each stage
• An engaged definition, a send split and a drip plan with stop rules for adding quiet contacts
• A three-email sunset flow, the rules for who counts as unengaged and a monthly clean-out step
• A review of list growth, campaigns, flows and deliverability, ranked causes and a channel health score out of 100

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

• Generic copy that could fit any brand.
• Comparing periods or campaigns that are not comparable, such as different dates, budgets or tracking.
• Calling a test winner before there is enough data.

What a good result looks like

An example, not your task: Your emails are going to spam, or open rates have been falling.

• outputs/step-01-email-setup-health-checker.md. A setup score out of 100, each failed check with its exact fix, and the DMARC records to add.
• outputs/step-02-inbox-placement-recovery-planner.md. An inbox health score, a diagnosis and a staged send plan with a gate at each stage.
• outputs/step-03-engaged-list-expander.md. Your engaged definition, the send split, a drip plan for quiet contacts and stop rules.
• outputs/step-04-sunset-flow-and-list-cleaner.md. The unengaged segment, a three-email sunset flow, monthly suppression and a region check.
• outputs/step-05-email-and-sms-performance-reader.md. Ranked causes, list growth, campaigns, flows, deliverability and a channel health score.
• HAND-BACK SUMMARY. Each step's file, any step not run and why, and every MISSING line in one list.

How the work is checked

• Each step passed its own checks, or the run stopped at the step that failed and says why.
• The steps ran in order, and each one used the result of the one before.
• Nothing was invented to fill a gap. Every gap is a MISSING: line.
• Nothing was sent, published or paid for without a clear yes.
• 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.

Capabilities

• Check the email setup. Checks your sending domain, DMARC, smart sending, attribution, tracking and list settings against a fixed list. It scores the setup and gives the exact fix for each fault.
• Fix the faults and export. A pause. You fix the faults the check found and export your last 60 days of campaign results.
• Plan the recovery. Diagnoses the likely cause, scores inbox health and builds the engaged groups. It plans a staged ramp with a gate at each stage and a restart order.
• Widen the engaged list. Defines engaged from your buying cycle, sizes it, splits the sends and plans a slow drip of quiet contacts into engaged sends, with stop rules and a monthly check.
• Send to the engaged only. A pause. You send to the engaged group only for two weeks, then export the quiet subscribers and their open history.
• Sunset the quiet ones. First asks you to confirm how people opted in and where they live, and names the consent rule for that region. It is not legal advice, so a qualified person confirms. Then it defines unengaged with conditions, guards against false signals, writes a three-email sunset flow and sets a monthly rule that suppresses those who never answer.
• Read the results. Checks nothing is broken, then reads list growth, campaigns, flows and deliverability in order. It ranks the causes and scores channel health.

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 fix-inbox-placement-and-win-back-your-opens 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/fix-inbox-placement-and-win-back-your-opens/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

• Your email platform settings and DNS records for your sending domain
• Screenshots or exports of your sign-up forms, pages and tracking settings (optional)
• After the first pause, your last 60 days of campaign results
• Your flows, and the offer you will use to win people back (optional)
• After the second pause, the quiet subscribers and their open history
• Where your subscribers live and how they signed up (needed before any clean-out)

Tools and access

• 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: A paid service that needs an account. It builds segments from email and site activity with OR rules, and shows complaint and bounce rates for each send.
• Shopify: A paid platform that needs an account. Order and checkout events from the store feed the engaged segment.
• 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: 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.

Functions and deliverables

• Email delivery recovery and quiet-subscriber plan: Check email setup and results. Plan a cautious restart and messages for quiet readers, then review what happens after approved sends.
  • An email setup score out of 100, each failed check with the exact fix, and the DMARC records to add
  • An inbox health score out of 100, a diagnosis, and a staged recovery plan with gates at each stage
  • An engaged definition, a send split and a drip plan with stop rules for adding quiet contacts
  • A three-email sunset flow, the rules for who counts as unengaged and a monthly clean-out step
  • A review of list growth, campaigns, flows and deliverability, ranked causes and a channel health score out of 100
• 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
• Engaged list expander: Plan an engaged list expander drip that adds quiet contacts back to your email sends in small steps, with sizes for your list and a stop rule.
  • A definition of "engaged" with a day limit for each signal
  • A drip plan that adds random groups of quiet contacts to engaged sends, with sizes for your list
  • A split of your campaigns between broad reach and narrow goals
  • A monthly check and a stop rule if deliverability slips
• 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
• 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
• 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

Tasks you can use it for

• Your emails are going to spam, or open rates have been falling.
• You send to the whole list and complaints or unsubscribes have crept up.
• You want to email a bigger group again without losing your inbox placement.

Limits to check before starting

• You have not sent in the last 60 days, or you are a brand-new sender: use the Email setup health checker on its own first.
• Your mail reaches the inbox and you only want lapsed buyers back: use the Lapsed buyer email results planner workflow.
• You only need a win-back email series: use the Win-back flow builder.
• You want this month's email and SMS results read: use the Email and SMS results reviewer.

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.

• Download the handoff pack. It's a zip with HANDOFF.md and every skill file this workflow uses.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• Give it your sending domain settings and your platform's list and tracking settings.
• When it pauses, fix the faults it found, export 60 days of campaigns and give them back.
• Pause again after step 3. Send to the engaged group only for two weeks, then export the quiet subscribers.
• Before step 4, tell it where your subscribers live and how they opted in. Nothing is suppressed until you confirm both.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/fix-inbox-placement-and-win-back-your-opens 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.