Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Prepare to get the most out of a medical appointment — for yourself or someone you care for — with the right questions, the information to bring, and how to make sure you're heard. Use when asked help me prepare for a doctor's appointment, questions to ask the doctor, advocate for my parent at the doctor, or how do I get the most from this appointment. Produces a focused list of what to raise and ask (prioritized, since time is short), the history and info to bring, note-taking and 'teach-back'
.claude/skills/mohitagw15856-medical-appointment-advocate/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -5% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 15% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 21% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 69% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 69% | 0% |
Medical appointments are short, stressful, and easy to leave without your real questions answered — especially when advocating for an aging parent or a sick family member. Good preparation changes the outcome: knowing what to raise first, what to bring, how to make sure you understood, and how to speak up when concerns get brushed off. This helps you walk in ready and walk out clear. It's navigation help, not medical advice.
Ask for these if not provided:
Agenda (prioritized): most important concern/question first → then the rest]. Bring: symptom timeline · current medication list · relevant records · written questions. To understand: take notes · ask for plain language · teach-back ("so I should…"). If dismissed: "I'm still worried about X — what else could it be?]" · ask for the reasoning + next steps. Before you leave, confirm: diagnosis/plan · medications (how/when) · follow-up · warning signs · who to call.
> Navigation and advocacy support — not medical advice. Your clinician is the authority on diagnosis and treatment.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 26,554 | 16,473 | -38% | 1 | 1 | 0% | 3,144 | 2,998 | -5% | 0 | 0 | — |
case-02 | fail→pass | 25,581 | 21,555 | -16% | 1 | 1 | 0% | 2,952 | 3,402 | +15% | 0 | 0 | — |
case-03 | fail→pass | 22,861 | 21,724 | -5% | 1 | 1 | 0% | 2,780 | 3,365 | +21% | 0 | 0 | — |
case-04 | fail→pass | 16,440 | 17,076 | +4% | 1 | 1 | 0% | 1,785 | 3,008 | +69% | 0 | 0 | — |
case-05 | fail→fail | 11,494 | 16,203 | +41% | 1 | 1 | 0% | 1,955 | 2,951 | +51% | 0 | 0 | — |
case-06 | fail→pass | 16,920 | 18,102 | +7% | 1 | 1 | 0% | 1,920 | 3,238 | +69% | 0 | 0 | — |
case-07 | fail→fail | 20,369 | 17,029 | -16% | 1 | 1 | 0% | 2,259 | 2,905 | +29% | 0 | 0 | — |
case-08 | fail→pass | 15,239 | 10,147 | -33% | 1 | 1 | 0% | 1,595 | 2,675 | +68% | 0 | 0 | — |
case-09 | fail→pass | 16,396 | 16,808 | +3% | 1 | 1 | 0% | 1,766 | 2,785 | +58% | 0 | 0 | — |
case-10 | fail→pass | 15,753 | 19,711 | +25% | 1 | 1 | 0% | 2,457 | 3,441 | +40% | 0 | 0 | — |
case-11 | pass→pass | 22,286 | 11,689 | -48% | 1 | 1 | 0% | 2,632 | 2,868 | +9% | 0 | 0 | — |
case-12 | fail→pass | 17,123 | 16,431 | -4% | 1 | 1 | 0% | 1,888 | 2,907 | +54% | 0 | 0 | — |
case-13 | fail→fail | 11,832 | 17,867 | +51% | 1 | 1 | 0% | 1,814 | 2,947 | +62% | 0 | 0 | — |
case-14 | fail→pass | 15,650 | 12,697 | -19% | 1 | 1 | 0% | 1,739 | 3,005 | +73% | 0 | 0 | — |
case-15 | fail→pass | 10,369 | 14,533 | +40% | 1 | 1 | 0% | 1,637 | 2,470 | +51% | 0 | 0 | — |
case-16 | pass→pass | 19,064 | 19,553 | +3% | 1 | 1 | 0% | 2,094 | 3,616 | +73% | 0 | 0 | — |
case-17 | fail→pass | 12,206 | 14,958 | +23% | 1 | 1 | 0% | 1,319 | 2,884 | +119% | 0 | 0 | — |
case-18 | fail→pass | 8,996 | 15,606 | +73% | 1 | 1 | 0% | 1,566 | 2,756 | +76% | 0 | 0 | — |
case-19 | fail→pass | 14,383 | 15,324 | +7% | 1 | 1 | 0% | 1,473 | 2,743 | +86% | 0 | 0 | — |
case-20 | pass→pass | 17,385 | 15,118 | -13% | 1 | 1 | 0% | 2,024 | 2,671 | +32% | 0 | 0 | — |
case-21 | pass→pass | 15,089 | 11,966 | -21% | 1 | 1 | 0% | 1,311 | 2,615 | +99% | 0 | 0 | — |
case-22 | pass→pass | 12,292 | 15,837 | +29% | 1 | 1 | 0% | 2,098 | 2,844 | +36% | 0 | 0 | — |
case-23 | fail→fail | 8,956 | 18,620 | +108% | 1 | 1 | 0% | 1,402 | 3,717 | +165% | 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. 23 cases were attempted. The headline lift of +61 percentage points is the difference between those two pass rates over the 23 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.