Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Maps the full customer journey from first touch to advocacy. Generates a comprehensive customer-journey.md with all stages, touchpoints, emotions, pain points, opportunities, Mermaid diagrams, and metrics. Use when mapping customer experience, designing onboarding flows, identifying churn risks, or optimizing conversion funnels.
.claude/skills/onewave-ai-customer-journey-mapper/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | 113% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 123% | 0% |
| case-17 | ✗→✓ | ▲ Improved | 109% | 0% |
| case-12 | ✓→✗ | ▼ Worse | 78% | 0% |
| case-09 | ✓→✗ | ▼ Worse | -62% | 0% |
Produce a comprehensive, actionable customer journey map spanning every stage from initial awareness through long-term advocacy.
references/journey-stages.md — the seven stages and the dimensions to analyze for eachreferences/output-template.md — exact structure for the generated customer-journey.mdreferences/mermaid-diagrams.md — both required Mermaid diagrams and the satisfaction scoring guidereferences/examples.md — invocation examples, research protocol, and ambiguity handlingreferences/examples.md for the research protocol.references/journey-stages.md for the dimensions to cover per stage.customer-journey.md to the current working directory following references/output-template.md. Include both Mermaid diagrams per references/mermaid-diagrams.md.| Input | Description | Example | |---|---|---| | Product/Service | What is being sold or offered | "B2B SaaS project management tool" | | Target Persona | Who the primary customer is | "VP of Engineering at mid-market companies, 200-1000 employees" | | Touchpoints | Known interaction points (optional) | "Google search, blog, demo request, sales call, onboarding email sequence" | | Channels | Active marketing/sales/support channels | "Website, email, LinkedIn, phone, in-app, Slack community" |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-02 | fail→fail | 36,494 | 43,182 | +18% | 1 | 1 | 0% | 6,228 | 6,918 | +11% | 0 | 0 | — |
case-12 | pass→fail | 27,032 | 41,139 | +52% | 1 | 1 | 0% | 3,855 | 6,849 | +78% | 0 | 0 | — |
case-01 | fail→fail | 20,047 | 22,907 | +14% | 1 | 1 | 0% | 3,206 | 2,800 | -13% | 0 | 0 | — |
case-03 | fail→fail | 39,676 | 10,530 | -73% | 1 | 1 | 0% | 6,224 | 1,584 | -75% | 0 | 0 | — |
case-04 | fail→fail | 15,002 | 4,373 | -71% | 1 | 1 | 0% | 2,406 | 1,343 | -44% | 0 | 0 | — |
case-05 | fail→pass | 22,010 | 48,307 | +119% | 1 | 1 | 0% | 3,214 | 6,856 | +113% | 0 | 0 | — |
case-06 | fail→pass | 21,090 | 40,532 | +92% | 1 | 1 | 0% | 3,081 | 6,858 | +123% | 0 | 0 | — |
case-11 | fail→fail | 25,320 | 41,626 | +64% | 1 | 1 | 0% | 3,594 | 6,853 | +91% | 0 | 0 | — |
case-07 | pass→pass | 24,179 | 45,129 | +87% | 1 | 1 | 0% | 3,448 | 6,867 | +99% | 0 | 0 | — |
case-08 | pass→pass | 29,669 | 47,564 | +60% | 1 | 1 | 0% | 4,204 | 6,862 | +63% | 0 | 0 | — |
case-09 | pass→fail | 27,683 | 13,401 | -52% | 1 | 1 | 0% | 4,157 | 1,587 | -62% | 0 | 0 | — |
case-10 | pass→pass | 23,468 | 41,740 | +78% | 1 | 1 | 0% | 3,531 | 6,864 | +94% | 0 | 0 | — |
case-13 | fail→fail | 21,911 | 42,818 | +95% | 1 | 1 | 0% | 3,211 | 6,851 | +113% | 0 | 0 | — |
case-14 | fail→fail | 22,900 | 46,297 | +102% | 1 | 1 | 0% | 3,564 | 6,859 | +92% | 0 | 0 | — |
case-15 | fail→fail | 21,139 | 37,258 | +76% | 1 | 1 | 0% | 3,575 | 6,852 | +92% | 0 | 0 | — |
case-16 | fail→fail | 22,190 | 50,548 | +128% | 1 | 1 | 0% | 3,420 | 6,852 | +100% | 0 | 0 | — |
case-17 | fail→pass | 18,918 | 38,802 | +105% | 1 | 1 | 0% | 3,270 | 6,849 | +109% | 0 | 0 | — |
case-18 | fail→fail | 17,876 | 7,931 | -56% | 1 | 1 | 0% | 3,120 | 1,307 | -58% | 0 | 0 | — |
case-19 | fail→fail | 19,051 | 11,145 | -41% | 1 | 1 | 0% | 3,308 | 1,291 | -61% | 0 | 0 | — |
case-20 | pass→fail | 23,291 | 33,124 | +42% | 1 | 1 | 0% | 4,101 | 6,869 | +67% | 0 | 0 | — |
case-21 | pass→pass | 15,181 | 21,456 | +41% | 1 | 1 | 0% | 1,975 | 4,620 | +134% | 0 | 0 | — |
case-22 | pass→pass | 11,528 | 19,235 | +67% | 1 | 1 | 0% | 2,239 | 4,264 | +90% | 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, and 18 counted toward the lift figure. The other 4 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of 0 percentage points is the difference between those two pass rates over the 18 comparable cases. 6 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.