---
name: marketing-experiment-design
description: "Turn a marketing hypothesis into a measurable experiment and decision plan. Use when the user requests marketing experiment design. Select relevant methods for the requested outcome; unrelated tasks do not require this skill."
metadata:
  version: "1.0.0"
---

# Marketing Experiment Design

Turn a marketing hypothesis into a measurable experiment and decision plan.

## OLLIE Runtime integration

Use this capability under the active OLLIE Operator. Read live Workspace Context and tenant bindings for client facts and required inputs. This generic package contains no client configuration. Consume ask-ollie-authority-core for authority, outloop-access-fallback for access and recovery, email-lifecycle-core for communication, and the bootstrapper Runtime Contract for ownership, scheduling and completion. Preserve domain constraints; this Skill creates no competing execution path. Use one method, combine skills, or fill missing steps with authorized tools as the task requires.

External access uses the active Workspace’s approved Outloop capabilities. Never request, read, embed or expose credentials. A service named in a method is a possible dependency, not an access grant. Local file and application work uses the host’s authorized tools.

## Required inputs

- Objective and baseline
- Available audience
- Budget limits
- Observation window

## Methods

### Define the decision

Define the hypothesis, primary metric, unit of comparison and decision rule before choosing creative variants. Avoid changing multiple unrelated factors without acknowledging confounding.

### Use approved economics

Use approved economics and capacity constraints to design scenarios. Keep observed results separate from estimates and do not invent target ROAS or margin defaults.

### Check measurement limits

Check tracking coverage, attribution lag, seasonality and overlap with other campaigns. Specify what data would be insufficient for a conclusion.

### Prepare the test brief

Produce a test brief, measurement table and next-action rules. Launching, increasing spend or stopping campaigns requires the active Runtime authority and workspace policy.

## Completion

Verify findings against source evidence and read back the resulting artifact or authorized change. Report inputs used, methods selected, output location, assumptions and unresolved dependencies. Do not report a plan, queue entry, draft, test fixture or accepted request as a completed external action. Use the task’s requested format; if a tool is unavailable, finish independent work and identify the exact unfulfilled deliverable.

## Test before relying on it

Read [the synthetic evaluation cases](references/evaluation.md) for activation, output and isolation checks. These cases are test instructions, not evidence that a host or provider test has passed.