marketing-psychology

A Claude Code skill that applies psychological principles and mental models — anchoring, loss aversion, social proof, framing, scarcity — to specific marketing decisions, not abstract theory.

Apply behavioral science to specific marketing moves

Source Corey Haines
License MIT
First documented

Trigger phrases

Phrases that activate this skill when typed to Claude Code:

  • marketing psychology
  • cognitive bias
  • persuasion
  • anchoring
  • why do people buy

What it does

marketing-psychology is a Claude Code skill from Corey Haines’s marketing-skills repo. It turns Claude into a behavioral-science consultant who maps psychological principles — anchoring, loss aversion, social proof, framing, scarcity, the peak-end rule — onto specific marketing decisions you’re making. The skill activates when you mention “marketing psychology”, “cognitive bias”, “persuasion”, “anchoring”, or “why do people buy”.

The output of a session is a per-decision recommendation: which principle applies, how it’s already in play (or absent) on your page/email/flow, the specific change to test, and the ethical line — the skill won’t recommend dark-pattern tactics even when they’d convert.

When to use it

Reach for it when:

  • You have a pricing page, paywall, or hero you want pressure-tested for psychological levers
  • You’re choosing between two design options and want a non-vibes argument
  • You want to understand why a winning test won, so you can apply the pattern elsewhere

When not to reach for it:

  • You’re looking for permission to use dark patterns; the skill won’t supply it
  • You haven’t shipped anything yet — psychology amplifies clarity, doesn’t generate it

Install

The skill is distributed via Corey Haines’s marketing-skills repo. Install via the repo’s recommended path — copy the marketing-psychology SKILL.md into your project’s .claude/skills/marketing-psychology/ directory, or use the repo’s plugin install if you’ve set it up.

Once installed, the skill activates on the trigger phrases above. The first time it runs, it will check for .agents/product-marketing-context.md (or .claude/product-marketing-context.md) — populating that file with your product context first dramatically improves output quality across all of Haines’s marketing skills.

What a session looks like

A typical session has three phases:

  1. Decision framing. What’s the actual choice? Pricing display, CTA copy, social-proof placement, scarcity messaging? The skill resists “general psychology advice” without a target.
  2. Principle mapping. Which 2–3 principles apply, why, and how a competitor or category leader is using each one already.
  3. Test recommendation. Specific change to make, hypothesis form, the pattern that emerges if it works (so you can apply it to adjacent decisions).

The discipline that makes it work: principle to specific change. “Use loss aversion” is empty advice. “Reframe the upgrade screen from ‘unlock X’ to ‘don’t lose X you’ve already started using’” is a test you can run.

Receipts

Honest reporting on what marketing-psychology produces and where it has limits:

Where it works well:

  • The principle-to-test translation is exactly the right level of abstraction
  • The ethics line keeps the skill in territory you can defend in public
  • “How a category leader uses this principle” examples make abstract levers concrete

Where it backfires:

  • Some principles are fashionable rather than well-replicated; the skill leans toward the well-tested ones but no science is bulletproof
  • Without testing, you can’t tell which principle won — the skill recommends, your A/B program validates

Pattern that works: pair with ab-test-setup. The psychology session generates hypotheses; the test infrastructure tells you which ones are real.

Source and attribution

Originally written by Corey Haines. The canonical SKILL.md and any supporting files live in the marketing-psychology folder of his marketing-skills repository.

License: MIT. You can install, adapt, and redistribute the skill, with attribution preserved.

This page documents the skill from a practitioner’s perspective. For the formal spec and any updates, defer to the source repo.