Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Create an end-to-end user journey map with stages, touchpoints, emotions, pain points, and opportunity areas. Use when mapping the full user experience for a product, feature, or service.
.claude/skills/owl-listener-journey-map/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 94% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 21% | 0% |
| case-10 | ✓→✗ | ▼ Worse | 80% | 0% |
| case-12 | ✓→✗ | ▼ Worse | 47% | 0% |
| case-14 | ✓→✗ | ▼ Worse | -19% | 0% |
Create a comprehensive user journey map for product design and UX analysis.
You are a senior UX researcher helping a design team map the user journey for $ARGUMENTS. If the user provides files (research data, personas, analytics), read them first.
The user will describe the product/feature and target user. Work through these steps:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 12,722 | 20,685 | +63% | 1 | 1 | 0% | 2,186 | 4,241 | +94% | 0 | 0 | — |
case-02 | pass→pass | 14,060 | 18,493 | +32% | 1 | 1 | 0% | 2,111 | 3,059 | +45% | 0 | 0 | — |
case-03 | pass→pass | 15,748 | 25,190 | +60% | 1 | 1 | 0% | 2,732 | 4,524 | +66% | 0 | 0 | — |
case-04 | pass→pass | 13,159 | 19,667 | +49% | 1 | 1 | 0% | 2,171 | 3,869 | +78% | 0 | 0 | — |
case-05 | fail→fail | 9,227 | 16,501 | +79% | 1 | 1 | 0% | 1,432 | 3,381 | +136% | 0 | 0 | — |
case-06 | fail→pass | 12,671 | 11,096 | -12% | 1 | 1 | 0% | 1,881 | 2,277 | +21% | 0 | 0 | — |
case-07 | pass→pass | 11,786 | 12,577 | +7% | 1 | 1 | 0% | 1,826 | 2,351 | +29% | 0 | 0 | — |
case-08 | pass→pass | 9,788 | 5,976 | -39% | 1 | 1 | 0% | 1,618 | 1,352 | -16% | 0 | 0 | — |
case-09 | pass→pass | 15,964 | 27,722 | +74% | 1 | 1 | 0% | 2,676 | 4,740 | +77% | 0 | 0 | — |
case-10 | pass→fail | 13,195 | 20,038 | +52% | 1 | 1 | 0% | 1,978 | 3,557 | +80% | 0 | 0 | — |
case-11 | fail→fail | 13,118 | 20,871 | +59% | 1 | 1 | 0% | 2,055 | 4,223 | +105% | 0 | 0 | — |
case-12 | pass→fail | 12,618 | 16,921 | +34% | 1 | 1 | 0% | 1,902 | 2,804 | +47% | 0 | 0 | — |
case-13 | fail→fail | 12,191 | 17,867 | +47% | 1 | 1 | 0% | 2,127 | 3,537 | +66% | 0 | 0 | — |
case-14 | pass→fail | 8,759 | 5,008 | -43% | 1 | 1 | 0% | 1,463 | 1,187 | -19% | 0 | 0 | — |
case-15 | pass→pass | 13,921 | 12,771 | -8% | 1 | 1 | 0% | 2,318 | 2,661 | +15% | 0 | 0 | — |
case-16 | fail→fail | 4,578 | 15,815 | +245% | 1 | 1 | 0% | 864 | 2,804 | +225% | 0 | 0 | — |
case-17 | fail→fail | 9,366 | 6,045 | -35% | 1 | 1 | 0% | 1,501 | 1,400 | -7% | 0 | 0 | — |
case-18 | fail→fail | 10,663 | 18,576 | +74% | 1 | 1 | 0% | 1,655 | 3,510 | +112% | 0 | 0 | — |
case-19 | fail→fail | 12,411 | 10,922 | -12% | 1 | 1 | 0% | 1,885 | 2,085 | +11% | 0 | 0 | — |
case-20 | fail→fail | 6,311 | 5,000 | -21% | 1 | 1 | 0% | 1,100 | 1,169 | +6% | 0 | 0 | — |
case-21 | pass→pass | 10,547 | 8,394 | -20% | 1 | 1 | 0% | 1,739 | 1,903 | +9% | 0 | 0 | — |
case-22 | pass→fail | 17,876 | 25,447 | +42% | 1 | 1 | 0% | 3,058 | 4,784 | +56% | 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 -33 percentage points is the difference between those two pass rates over the 22 comparable cases. 4 cases got worse with the skill loaded, and they are included in that figure.
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.