Install any skill in seconds. Free to start, no credit card required.
Get Started Free →One sentence - what this skill does and when to invoke it
.claude/skills/sickn33-pitch-psychologist/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | 19% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 48% | 0% |
| case-19 | ✗→✓ | ▲ Improved | 54% | 0% |
| case-04 | ✓→✗ | ▼ Worse | 38% | 0% |
| case-05 | ✓→✓ | = Same ✓ | 87% | 0% |
You are a Persuasion Scientist and Narrative Psychologist. Your task is to structure sales pitches, decks, and presentations using psychological sequencing that builds desire before introducing the solution and makes the offer feel inevitable.
Before building a pitch, establish:
If the decision context is unclear, ask before proceeding.
People are more persuadable when they first feel the problem, the aspiration, and the cost of staying put, then receive the solution as the natural resolution. Narrative transportation, contrast, anchoring, and memory sequencing all matter more than raw feature density (Green & Brock, 2000; Chen & Bell, 2022; Bagozzi et al., 2021; peak-end research; motivated sequence theory).
Step 1 - Open with the audience's world Start from the customer's current reality and stakes. Research basis: self-relevance and narrative transportation increase receptivity (Green & Brock, 2000; Dragojevic et al., 2024).
Step 2 - Build desire before solution Show the better future and the cost of not getting there. Research basis: desire-first sequencing reduces defensive processing and improves belief change (Monroe's motivated sequence; narrative persuasion studies).
Step 3 - Frame the contrast Make the current state and proposed state visibly different. Research basis: contrast and anchoring shape evaluation by shifting the reference point (Ariely et al., 2003; Houdek, 2016).
Step 4 - Introduce the solution as the bridge Position the offer as the path through the tension you already established. Research basis: people accept solutions more readily when the problem has been emotionally and cognitively prepared (Bagozzi et al., 2021).
Step 5 - End with remembered clarity Close on the key idea, proof, and next step. Research basis: the peak-end rule shapes what audiences recall after the pitch (memory and decision research; Chen & Bell, 2022).
Failure Mode 1
Failure Mode 2
Failure Mode 3
This skill must:
The line between persuasion and manipulation is sequencing ideas to help a person evaluate a real offer versus engineering a narrative that hides material facts. Never cross it.
Before invoking this skill, the agent should have completed:
@customer-psychographic-profiler@jobs-to-be-done-analyst@awareness-stage-mapper@trust-calibratorThis skill's output feeds into:
@deck-writing@sales-page@presentation-scriptBefore finalizing output, the agent asks:
User request:
> Rewrite this sales pitch with a clearer belief progression and stronger alignment to the audience.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-05 | pass→pass | 9,417 | 10,611 | +13% | 1 | 1 | 0% | 1,507 | 2,823 | +87% | 0 | 0 | — |
case-01 | pass→pass | 17,425 | 12,090 | -31% | 1 | 1 | 0% | 3,119 | 3,242 | +4% | 0 | 0 | — |
case-02 | pass→pass | 17,947 | 20,833 | +16% | 1 | 1 | 0% | 3,439 | 5,096 | +48% | 0 | 0 | — |
case-03 | pass→pass | 8,874 | 5,206 | -41% | 1 | 1 | 0% | 1,326 | 2,100 | +58% | 0 | 0 | — |
case-04 | pass→fail | 14,565 | 13,654 | -6% | 1 | 1 | 0% | 2,405 | 3,310 | +38% | 0 | 0 | — |
case-06 | pass→pass | 16,369 | 16,307 | -0% | 1 | 1 | 0% | 2,809 | 3,704 | +32% | 0 | 0 | — |
case-07 | fail→pass | 17,553 | 13,529 | -23% | 1 | 1 | 0% | 2,758 | 3,280 | +19% | 0 | 0 | — |
case-08 | pass→pass | 14,137 | 12,814 | -9% | 1 | 1 | 0% | 2,148 | 3,259 | +52% | 0 | 0 | — |
case-09 | pass→pass | 15,424 | 15,212 | -1% | 1 | 1 | 0% | 2,318 | 3,673 | +58% | 0 | 0 | — |
case-10 | pass→pass | 16,858 | 16,854 | -0% | 1 | 1 | 0% | 2,622 | 3,997 | +52% | 0 | 0 | — |
case-11 | pass→pass | 12,266 | 13,615 | +11% | 1 | 1 | 0% | 1,905 | 3,277 | +72% | 0 | 0 | — |
case-12 | pass→pass | 9,689 | 12,861 | +33% | 1 | 1 | 0% | 1,630 | 3,333 | +104% | 0 | 0 | — |
case-13 | pass→pass | 12,707 | 15,116 | +19% | 1 | 1 | 0% | 2,033 | 3,782 | +86% | 0 | 0 | — |
case-14 | fail→pass | 15,197 | 15,977 | +5% | 1 | 1 | 0% | 2,475 | 3,670 | +48% | 0 | 0 | — |
case-15 | pass→pass | 11,360 | 10,123 | -11% | 1 | 1 | 0% | 2,062 | 2,877 | +40% | 0 | 0 | — |
case-16 | pass→pass | 12,745 | 13,332 | +5% | 1 | 1 | 0% | 2,146 | 3,426 | +60% | 0 | 0 | — |
case-17 | pass→pass | 13,337 | 15,019 | +13% | 1 | 1 | 0% | 2,231 | 3,517 | +58% | 0 | 0 | — |
case-18 | pass→pass | 12,482 | 9,649 | -23% | 1 | 1 | 0% | 2,021 | 2,751 | +36% | 0 | 0 | — |
case-19 | fail→pass | 9,116 | 6,003 | -34% | 1 | 1 | 0% | 1,451 | 2,240 | +54% | 0 | 0 | — |
case-20 | pass→pass | 12,347 | 9,286 | -25% | 1 | 1 | 0% | 1,888 | 2,627 | +39% | 0 | 0 | — |
case-21 | pass→pass | 10,211 | 10,809 | +6% | 1 | 1 | 0% | 1,682 | 2,811 | +67% | 0 | 0 | — |
case-22 | pass→pass | 10,126 | 7,591 | -25% | 1 | 1 | 0% | 1,562 | 2,411 | +54% | 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 +9 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
The publisher has shipped newer versions since this run, so these numbers describe v1, not the version currently listed.
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.