Install any skill in seconds. Free to start, no credit card required.
Get Started Free →- **Role**: You are a proactive coaching intelligence grounded in behavioral psychology and habit formation. You transform passive software dashboards into active, tailored productivity partners.
.claude/skills/dev-dennis-040-product-behavioral-nudge-engine/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 21% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 68% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 49% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 10% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 151% | 0% |
name: Behavioral Nudge Engine description: Behavioral psychology specialist that adapts software interaction cadences and styles to maximize user motivation and success. color: "#FF8A65"
Concrete examples of what you produce:
typescript// Behavioral Engine: Generating a Time-Boxed Sprint Nudge export function generateSprintNudge(pendingTasks: Task[], userProfile: UserPsyche) { if (userProfile.tendencies.includes('ADHD') || userProfile.status === 'Overwhelmed') { // Break cognitive load. Offer a micro-sprint instead of a summary. return { channel: userProfile.preferredChannel, // SMS message: "Hey! You've got a few quick follow-ups pending. Let's see how many we can knock out in the next 5 mins. I'll tee up the first draft. Ready?", actionButton: "Start 5 Min Sprint" }; } // Standard execution for a standard profile return { channel: 'EMAIL', message: `You have ${pendingTasks.length} pending items. Here is the highest priority: ${pendingTasks[0].title}.` }; }
You continuously update your knowledge of:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 17,883 | 19,277 | +8% | 1 | 1 | 0% | 3,623 | 4,395 | +21% | 0 | 0 | — |
case-02 | fail→fail | 11,307 | 12,154 | +7% | 1 | 1 | 0% | 2,063 | 3,639 | +76% | 0 | 0 | — |
case-03 | pass→pass | 6,370 | 5,996 | -6% | 1 | 1 | 0% | 1,274 | 2,334 | +83% | 0 | 0 | — |
case-04 | pass→pass | 10,724 | 9,562 | -11% | 1 | 1 | 0% | 2,130 | 3,106 | +46% | 0 | 0 | — |
case-05 | pass→pass | 12,952 | 10,711 | -17% | 1 | 1 | 0% | 2,583 | 3,337 | +29% | 0 | 0 | — |
case-06 | pass→pass | 13,223 | 14,392 | +9% | 1 | 1 | 0% | 2,015 | 3,369 | +67% | 0 | 0 | — |
case-07 | fail→fail | 14,519 | 22,658 | +56% | 1 | 1 | 0% | 3,055 | 5,484 | +80% | 0 | 0 | — |
case-18 | pass→pass | 14,156 | 13,402 | -5% | 1 | 1 | 0% | 2,534 | 3,891 | +54% | 0 | 0 | — |
case-08 | fail→pass | 8,796 | 8,252 | -6% | 1 | 1 | 0% | 1,710 | 2,876 | +68% | 0 | 0 | — |
case-09 | pass→pass | 13,623 | 12,194 | -10% | 1 | 1 | 0% | 3,270 | 4,162 | +27% | 0 | 0 | — |
case-10 | pass→pass | 10,732 | 9,850 | -8% | 1 | 1 | 0% | 2,221 | 3,222 | +45% | 0 | 0 | — |
case-11 | pass→pass | 10,649 | 11,118 | +4% | 1 | 1 | 0% | 2,071 | 3,403 | +64% | 0 | 0 | — |
case-12 | pass→pass | 14,443 | 17,592 | +22% | 1 | 1 | 0% | 2,766 | 4,882 | +77% | 0 | 0 | — |
case-13 | pass→pass | 16,689 | 17,402 | +4% | 1 | 1 | 0% | 3,245 | 4,996 | +54% | 0 | 0 | — |
case-14 | fail→pass | 12,015 | 11,288 | -6% | 1 | 1 | 0% | 2,797 | 4,168 | +49% | 0 | 0 | — |
case-15 | fail→pass | 14,947 | 11,011 | -26% | 1 | 1 | 0% | 3,025 | 3,328 | +10% | 0 | 0 | — |
case-16 | fail→pass | 5,104 | 7,682 | +51% | 1 | 1 | 0% | 1,027 | 2,574 | +151% | 0 | 0 | — |
case-17 | fail→fail | 14,724 | 11,953 | -19% | 1 | 1 | 0% | 2,595 | 3,581 | +38% | 0 | 0 | — |
case-19 | fail→pass | 6,203 | 10,095 | +63% | 1 | 1 | 0% | 1,227 | 3,282 | +167% | 0 | 0 | — |
case-20 | pass→pass | 13,959 | 12,016 | -14% | 1 | 1 | 0% | 2,962 | 3,759 | +27% | 0 | 0 | — |
case-21 | pass→pass | 15,986 | 10,137 | -37% | 1 | 1 | 0% | 3,430 | 3,380 | -1% | 0 | 0 | — |
case-22 | pass→pass | 15,813 | 10,724 | -32% | 1 | 1 | 0% | 3,372 | 3,375 | +0% | 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 +27 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.