• Reads: the mode, what the user wants to test, SEND profile (

  promotional|retention|cold-outbound|newsletter

  ), baseline outcome rate, list size/send volume, alpha, power, MDE, multiplicity/sequential rule, guardrails, decision owner/rule, and any finished ESP results export.
• Writes: a user-facing test-design or read-out doc plus a

  ### Handoff Summary

  .
• Promotes: the chosen mode, hypothesis, design parameters, calculated read-out, and any explicitly owner-approved action (ask before writing memory).
• Done when: mode/unit/profile and design parameters are stated; the matrix isolates one variable per cell and keeps a control; and a read-out reports effect/interval/statistical/practical flags with

  Calculated

  provenance. Without a precommitted action rule and owner, return

  decision: UNDECIDED

  .
• Primary next skill: performance-analyzer (read results back over the window) or email-quality-auditor (gate the program before scaling a winner).

Emit the standard shape from skill-contract.md §Handoff Summary Format: Status / Objective / Key Findings / Evidence (label each Measured / User-provided / Estimated) / Assumptions / Open Loops / Recommended Next Skill.

See CONNECTORS.md for tool category placeholders. Every input is the user's own data, manually exported. Keyed ESP APIs (Klaviyo, Mailchimp, HubSpot, Customer.io) are an optional Tier-2/3 MCP convenience — never required to design a test or read one out.

Statistical facts (keyless):

python3 "${CLAUDE_PLUGIN_ROOT}/scripts/connectors/experiment.py" proportion --control <events> <n> --variant <events> <n> --alpha <alpha> --min-lift <relative-bar>

returns rates, effect size, intervals, p-value, and separate statistical/practical flags. Revenue-per-recipient samples use

continuous

; prospective sizing uses

samplesize

. Every derived value is

Calculated

; the helper emits no winner or business action.

~~email platform

~~email platform

~~web analytics

send-time

~~email platform

hold-out

~~web analytics

~~ecommerce

1. Pick the mode. Choose

   a-b

   ,

   multivariate

   ,

   send-time

   , or

   hold-out

   from the request (default per the Quick Start table when unambiguous) and state it back. Then pick design (plan a new test) or read-out (call a finished one). If neither a baseline+lift target nor a results export is present, stop and return NEEDS_INPUT naming the missing input.
2. Hypothesis. Write it falsifiable: Because [observation], we believe [one change] will [raise primary metric] by [X points / X%] for [segment]; we'll know when [metric] moves past the design threshold. One change per hypothesis. For

   send-time

   , the "one change" is the deploy hour/day; for

   hold-out

   , it is the presence of the send itself.
3. Variant matrix — one variable per cell (mode-specific).

   • a-b

     — one change (subject or preheader or CTA or creative), two cells + control. Never change two things in one cell — a winner must be attributable to one variable.

   • multivariate

     — cross 2+ factors, one variable held distinct per cell, only when the list is large enough to power every cell (see step 5): a 2×2 subject×CTA test is 4 cells, each needing a full sample. If underpowered, collapse to

     a-b

     per step 6.

   • send-time

     — the isolated variable is the deploy hour/day; hold subject, segment, and creative constant. Randomly split the segment, deploy each arm at its assigned time, and compare same-window engagement — do not confound with a content change. Cover a full weekday/weekend cycle so time-of-day isn't confounded with day-of-week.

   • hold-out

     — carve a randomly-selected control that receives nothing (or the current default), sized to detect the incremental effect on the business metric (conversion / revenue-per-recipient), not just opens. The hold-out measures the send's incremental lift, so power it on the conversion baseline, not the open baseline.
   • Keep a control in every design.
4. Metrics. Name a primary metric tied to the mode + goal (open for a subject test, click/CTOR for a CTA/creative test, same-window engagement for

   send-time

   , conversion or revenue-per-recipient for

   hold-out

   ), secondary metrics for context, and guardrails that must not get worse (unsubscribe rate, spam-complaint rate, hard-bounce). A subject-line winner that lifts opens but spikes unsubscribes is a guardrail breach, not a win.
5. Sample size, MDE, duration, power — from the baseline. Precommit alpha, power, MDE, comparison count, read date, and any sequential rule. Use the user's policy when supplied; otherwise disclose

   alpha=.05

   and

   power=.80

   as conventional assumptions. Use

   experiment.py samplesize

   ; the table below is only the

   .05/.80

   two-sided reference case.

   Baseline rate	MDE ±1pt	±2pt	±3pt	±5pt
   5% (click)	~7,800	~2,100	~1,000	~400
   20% (CTOR)	~25,000	~6,400	~2,900	~1,100
   40% (open)	~37,700	~9,500	~4,300	~1,600

   Then duration = (recipients/cell × number of cells) ÷ (sendable recipients/day), floored at a full send cycle (≥ 1–2 weeks for lifecycle flows, and ≥ a full weekday/weekend cycle for a

   send-time

   test so day-of-week mix is covered). State the no-peeking rule: fix the sample and the read date at design time; do not call a winner early. If the user gives a relative lift (e.g. "15% lift on a 2% click baseline"), convert to the absolute MDE (0.3pt) before reading the table.

   multivariate

   multiplies the per-cell sample by the number of cells;

   hold-out

   sizes on the conversion baseline (typically a much lower rate → larger sample).
6. List-size reality — small lists need bigger MDE or longer runs. If the list can't supply the recipients/cell the table demands, say so and give the options explicitly, in this order:
   • Widen the MDE — only a bigger effect is detectable on this list; a 1-point subject-line tweak is unmeasurable on a 4,000-recipient list, so test bolder changes.
   • Run longer / pool sends — accumulate the sample across multiple sends of the same test.
   • Fewer cells — collapse a

     multivariate

     design to a single

     a-b

     .
   • Accept lower power / don't test — if even the widest reasonable MDE is underpowered, recommend shipping the stronger creative on judgment rather than running an underpowered test that will read noise as signal.
7. Significance read (keyless compute or documented math). Name the method and apply the gate:
   • Two-proportion z-test for open / click / CTOR / conversion rate comparisons (report the z, the p, and the observed lift) — the default for

     a-b

     ,

     multivariate

     cell-vs-control, and

     send-time

     arm comparisons.
   • Mann-Whitney U for non-normal continuous metrics (revenue per recipient for a

     hold-out

     , time-on-page from the landing export).
   • Bootstrap confidence interval when a CI on the lift is more useful than a bare p-value.
   • For

     multivariate

     with several cells against one control, note the multiple-comparison inflation and apply a Bonferroni-style adjustment (α ÷ number of comparisons) before calling any cell a winner.
   • Compare with the declared alpha and precommitted practical-effect boundary separately. Prefer

     experiment.py

     ; if unavailable, show the same inputs and formulas. Adjust alpha or use the declared familywise procedure for multiple cells, and do not treat an unplanned early look as a terminal read.
8. Apply decision ownership. Report direction, effect/interval, statistical flag, practical flag, sample completion, and every guardrail first. Name the decision owner and precommitted rule. Apply that rule only if both exist; otherwise emit

   decision: UNDECIDED

   . An early unplanned look is incomplete evidence, and a guardrail triggers an action only under its declared stop/escalation rule.
9. Label provenance. Export counts and baselines are

   User-provided

   (or

   Measured

   only when directly instrumented under the repository convention); p-values, intervals, power, and effects are

   Calculated

   ; assumptions and table lookups are

   Estimated

   . Reference measurement-protocol.md and send-benchmark.md.

• SEND Benchmark — SEND-E context and the four typed program profiles
• measurement-protocol.md — preregistration, multiplicity/sequential controls, practical effects, provenance, and decision ownership
• skill-contract.md — shared contract, Handoff Summary Format, Output Voice, termination rules
• CONNECTORS.md —

  ~~email platform

  ,

  ~~web analytics

  ,

  ~~ecommerce

  own-data export recipes
• SECURITY.md — untrusted-data boundary for exported results