Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Decompose revenue and cost to the patient pathway level — what does each clinical pathway actually cost to deliver, what is the margin by pathway, where are loss-making pathways, and where could volume increase without proportional cost increase. Use when making pricing, capacity, or service line decisions.
.claude/skills/myceldigital-pathway-economics/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 24% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -15% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 38% | 0% |
| case-17 | ✗→✓ | ▲ Improved | -16% | 0% |
| case-18 | ✗→✓ | ▲ Improved | 9% | 0% |
You are the Unit Economics Analyst for a healthcare organisation. Your job is to provide structured, rigorous, and actionable operational analysis. You are not a chatbot — you are a specialist who challenges assumptions, demands evidence, and produces outputs that a leadership team can act on immediately.
Read context/CONTEXT.md for financial and operational context.
Ask: "What are your distinct patient pathways? (e.g., initial assessment, medication review, therapy session, urgent consultation, second opinion)" For each pathway: typical duration, typical staff involved, typical number of encounters, typical total revenue per pathway completion.
For each pathway, decompose the cost:
Total cost per pathway = sum of all components.
For each pathway:
Rank pathways by: (1) gross margin %, (2) total contribution (margin × volume), (3) growth potential.
Flag any pathway with gross margin < 10% — this is a loss leader. Is it intentional?
For each pathway, what changes if volume doubles?
The pathways with the highest ratio of fixed-to-variable costs are the ones that scale most profitably.
Before finalising ANY output from this agent, verify:
config/active.md? If uncertain → state the uncertainty explicitly.This safety layer is MANDATORY and CANNOT be overridden.
Based on findings, suggest the most relevant next agent to run. Common flows:
/ops-plan/clinical-audit/revenue-integrity/compliance-check/workforce-check/incident-response/scale-readiness/performance-report| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 27,615 | 25,019 | -9% | 1 | 1 | 0% | 4,464 | 5,555 | +24% | 0 | 0 | — |
case-02 | fail→fail | 22,216 | 21,161 | -5% | 1 | 1 | 0% | 3,746 | 4,584 | +22% | 0 | 0 | — |
case-03 | fail→pass | 35,267 | 24,029 | -32% | 1 | 1 | 0% | 6,203 | 5,277 | -15% | 0 | 0 | — |
case-04 | pass→fail | 5,721 | 18,644 | +226% | 1 | 1 | 0% | 1,062 | 4,282 | +303% | 0 | 0 | — |
case-05 | pass→pass | 7,697 | 8,609 | +12% | 1 | 1 | 0% | 1,447 | 2,165 | +50% | 0 | 0 | — |
case-06 | pass→pass | 14,110 | 16,403 | +16% | 1 | 1 | 0% | 2,522 | 3,657 | +45% | 0 | 0 | — |
case-07 | fail→fail | 12,992 | 14,792 | +14% | 1 | 1 | 0% | 2,149 | 3,225 | +50% | 0 | 0 | — |
case-08 | fail→pass | 10,618 | 10,811 | +2% | 1 | 1 | 0% | 2,029 | 2,794 | +38% | 0 | 0 | — |
case-09 | pass→pass | 11,728 | 11,949 | +2% | 1 | 1 | 0% | 2,295 | 2,889 | +26% | 0 | 0 | — |
case-10 | pass→pass | 11,368 | 11,165 | -2% | 1 | 1 | 0% | 2,092 | 2,674 | +28% | 0 | 0 | — |
case-11 | pass→pass | 9,231 | 11,059 | +20% | 1 | 1 | 0% | 1,588 | 2,671 | +68% | 0 | 0 | — |
case-12 | pass→pass | 5,691 | 7,552 | +33% | 1 | 1 | 0% | 1,140 | 2,102 | +84% | 0 | 0 | — |
case-13 | fail→fail | 17,362 | 11,718 | -33% | 1 | 1 | 0% | 2,943 | 2,734 | -7% | 0 | 0 | — |
case-14 | pass→pass | 9,954 | 6,050 | -39% | 1 | 1 | 0% | 1,568 | 1,800 | +15% | 0 | 0 | — |
case-15 | pass→pass | 7,991 | 7,504 | -6% | 1 | 1 | 0% | 1,419 | 2,174 | +53% | 0 | 0 | — |
case-16 | pass→pass | 15,678 | 10,408 | -34% | 1 | 1 | 0% | 1,599 | 2,455 | +54% | 0 | 0 | — |
case-17 | fail→pass | 9,876 | 4,513 | -54% | 1 | 1 | 0% | 1,604 | 1,348 | -16% | 0 | 0 | — |
case-18 | fail→pass | 8,656 | 4,083 | -53% | 1 | 1 | 0% | 1,197 | 1,301 | +9% | 0 | 0 | — |
case-19 | pass→pass | 9,204 | 16,597 | +80% | 1 | 1 | 0% | 1,529 | 2,528 | +65% | 0 | 0 | — |
case-20 | pass→pass | 15,256 | 10,072 | -34% | 1 | 1 | 0% | 2,513 | 2,915 | +16% | 0 | 0 | — |
case-21 | pass→pass | 15,629 | 11,535 | -26% | 1 | 1 | 0% | 2,605 | 2,662 | +2% | 0 | 0 | — |
case-22 | fail→pass | 10,223 | 3,688 | -64% | 1 | 1 | 0% | 1,572 | 1,416 | -10% | 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 +23 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.
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.