mureo-learning

Provides an evidence-based decision framework for AI agents managing marketing accounts across platforms.

37|3|Updated Mar 30, 2026
One-click install
npx skills add https://github.com/logly/mureo --skill mureo-learning
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: mureo-learning
Source: https://github.com/logly/mureo/tree/main/skills/mureo-learning
Command: npx skills add https://github.com/logly/mureo --skill mureo-learning

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Evidence-based decision making for marketing AI agents managing ad accounts, reducing noise and avoiding premature optimization.

Core Features & Use Cases

  • Evidence lifecycle guidance for actions (observe → validate → apply)
  • Observation windows and minimum sample size rules to ensure reliable conclusions
  • Cross-platform applicability across ads platforms to optimize campaigns based on data-driven insights

Quick Start

Provide an evidence-based decision framework to guide an AI agent's actions on a marketing account.

Frequently Asked Questions about mureo-learning

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I stop my AI marketing agent from prematurely optimizing ad campaigns?

To prevent premature optimization, apply an evidence-based decision framework that enforces observation windows and minimum sample size rules before any campaign adjustments are made. This reduces noise and validates data reliability.

What is evidence-based marketing decision making for AI agents?

Evidence-based marketing decision making for AI agents uses a structured lifecycle of observing, validating, and applying data-driven actions to manage ad accounts, ensuring adjustments rely on validated insights rather than noise.

How do I apply a decision framework for cross-platform campaign evaluation?

Apply a cross-platform decision framework by tracking the evidence lifecycle across ads platforms, enforcing validation checks, and using sample-size rules to guide budgeting and strategy adjustments based on reliable data.

Can I use this evidence-based framework for stateful action logging in marketing?

Yes, the evidence-based framework satisfies requirements for stateful action logging, allowing AI agents to maintain a record of validated decisions and lifecycle tracking across marketing accounts.

What are the limitations of using minimum sample size rules for campaign evaluation?

Minimum sample size rules for campaign evaluation require waiting through defined observation windows before acting, which may delay immediate strategy adjustments during fast-paced or low-volume marketing campaigns.

Does this decision framework work across multiple ads platforms?

Yes, the decision framework offers cross-platform applicability across ads platforms, allowing AI agents to consistently evaluate campaigns, adjust budgets, and apply validation checks regardless of the specific marketing environment.