Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Apply behavioral psychology, cognitive biases, and 70+ mental models to marketing for conversion optimization, pricing, copy, and campaigns. Use for persuasion, behavioral science, why people buy, consumer behavior, or neuromarketing.
.claude/skills/borghei-marketing-psychology/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-06 | ✗→✓ | ▲ Improved | 93% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 97% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 10% | 0% |
| case-02 | ✓→✓ | = Same ✓ | 65% | 0% |
| case-01 | ✓→✓ | = Same ✓ | 58% | 0% |
Applied behavioral science for marketing — identifying which psychological principles apply to specific challenges and showing exactly how to implement them. The skill diagnoses behavioral barriers, prescribes 2-3 relevant principles from a catalog of 70+ mental models, and turns them into concrete, testable changes to landing pages, pricing, email, copy, and ads.
references/mental-models.mdreferences/application-playbooks.mdLoad the reference that matches the task — keep this file lean and pull detail on demand:
scripts/persuasion_auditor.py — audits copy for Cialdini's 7 principles plus behavioral economics techniques; flags what's applied and what's missing.scripts/cognitive_bias_checker.py — identifies cognitive biases leveraged (or missed) in copy, pricing pages, and landing pages.scripts/pricing_psychology_analyzer.py — analyzes pricing page structure for anchoring, decoy effect, charm pricing, framing, and tier design.bashpython scripts/persuasion_auditor.py page.html python scripts/cognitive_bias_checker.py pricing_page.html --json python scripts/pricing_psychology_analyzer.py pricing.json
In Scope: Behavioral psychology principles applied to marketing, conversion optimization, pricing strategy, copy improvement, campaign design. 70+ mental models with implementation guides.
Out of Scope: Academic psychology research, clinical applications, UX research methodology (use product-team), A/B test statistical analysis tools, consumer psychology outside marketing context.
Limitations: Psychology provides hypotheses, not certainties. All changes must be A/B tested. What works for consumer SaaS may not work for enterprise. Cultural context matters significantly. Principles should be applied ethically — persuasion that helps customers make good decisions, not manipulation.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-02 | pass→pass | 9,067 | 9,170 | +1% | 1 | 1 | 0% | 1,472 | 2,427 | +65% | 0 | 0 | — |
case-01 | pass→pass | 16,138 | 18,774 | +16% | 1 | 1 | 0% | 2,543 | 4,017 | +58% | 0 | 0 | — |
case-03 | pass→pass | 10,319 | 7,649 | -26% | 1 | 1 | 0% | 1,484 | 2,286 | +54% | 0 | 0 | — |
case-04 | pass→pass | 12,911 | 12,967 | +0% | 1 | 1 | 0% | 1,815 | 3,092 | +70% | 0 | 0 | — |
case-05 | pass→pass | 13,762 | 13,785 | +0% | 1 | 1 | 0% | 2,148 | 3,162 | +47% | 0 | 0 | — |
case-06 | fail→pass | 8,526 | 2,773 | -67% | 1 | 1 | 0% | 795 | 1,531 | +93% | 0 | 0 | — |
case-07 | fail→pass | 4,824 | 3,017 | -37% | 1 | 1 | 0% | 772 | 1,517 | +97% | 0 | 0 | — |
case-08 | fail→pass | 8,185 | 2,236 | -73% | 1 | 1 | 0% | 1,356 | 1,489 | +10% | 0 | 0 | — |
case-09 | pass→pass | 17,625 | 12,386 | -30% | 1 | 1 | 0% | 2,573 | 3,042 | +18% | 0 | 0 | — |
case-10 | pass→pass | 12,942 | 11,338 | -12% | 1 | 1 | 0% | 1,836 | 2,692 | +47% | 0 | 0 | — |
case-11 | pass→pass | 9,031 | 10,532 | +17% | 1 | 1 | 0% | 1,452 | 2,585 | +78% | 0 | 0 | — |
case-18 | pass→pass | 16,722 | 25,091 | +50% | 1 | 1 | 0% | 2,499 | 3,113 | +25% | 0 | 0 | — |
case-12 | pass→pass | 14,342 | 15,280 | +7% | 1 | 1 | 0% | 2,463 | 3,535 | +44% | 0 | 0 | — |
case-13 | pass→pass | 13,734 | 15,750 | +15% | 1 | 1 | 0% | 2,177 | 3,576 | +64% | 0 | 0 | — |
case-14 | pass→pass | 14,856 | 16,527 | +11% | 1 | 1 | 0% | 2,381 | 3,417 | +44% | 0 | 0 | — |
case-15 | pass→pass | 11,705 | 13,995 | +20% | 1 | 1 | 0% | 1,785 | 3,124 | +75% | 0 | 0 | — |
case-16 | pass→pass | 14,318 | 12,801 | -11% | 1 | 1 | 0% | 2,278 | 2,978 | +31% | 0 | 0 | — |
case-17 | pass→pass | 12,114 | 12,248 | +1% | 1 | 1 | 0% | 1,806 | 2,981 | +65% | 0 | 0 | — |
case-19 | pass→pass | 10,896 | 9,875 | -9% | 1 | 1 | 0% | 1,613 | 2,621 | +62% | 0 | 0 | — |
case-20 | fail→fail | 14,256 | 17,066 | +20% | 1 | 1 | 0% | 3,077 | 4,685 | +52% | 0 | 0 | — |
case-21 | fail→fail | 21,642 | 21,774 | +1% | 1 | 1 | 0% | 3,333 | 4,376 | +31% | 0 | 0 | — |
case-22 | fail→fail | 27,272 | 28,509 | +5% | 1 | 1 | 0% | 4,527 | 5,778 | +28% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +14 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.