Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Strategic advisory for digital health founders on HIPAA scope, FDA SaMD classification, EHR integration, and payor/provider GTM. Use when scoping a healthtech idea, classifying PHI, or mentioning HIPAA, FDA SaMD, EHR, or telehealth.
.claude/skills/borghei-healthtech-advisor/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -24% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 28% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 97% | 0% |
| case-17 | ✗→✓ | ▲ Improved | 66% | 0% |
| case-20 | ✗→✓ | ▲ Improved | 133% | 0% |
Strategic frameworks for digital health and healthtech founders, operators, and product leaders. Complements (does not replace) the RA/QM compliance domain. RA/QM covers regulatory and quality management for medical devices; this skill covers business-side strategy for health software companies.
> Disclaimer: Frameworks and orientation only. Not legal, regulatory, clinical, or compliance advice. Healthtech businesses need licensed counsel (HIPAA, FDA, fraud-and-abuse), clinical advisors, and qualified RA/QM specialists. Use this skill to organize strategy; engage specialists for binding decisions.
healthtech, digital health, HIPAA, PHI, BAA, business associate, covered entity, FDA SaMD, software as medical device, EHR, EMR, FHIR, HL7, telehealth, digital therapeutics, DTx, payor, provider, value-based care, fee-for-service, RPM, remote patient monitoring
python scripts/phi_scope_checker.py description.txtreferences/gtm_patterns.mdGoal: Determine whether HIPAA applies, in what capacity (Covered Entity, Business Associate, neither), and what BAAs you need with whom.
Steps:
Time Estimate: 4-8 weeks for first scope and BAA template.
Goal: Determine whether your software is regulated as a medical device by the FDA, and at which classification.
Steps:
references/fda_samd_basics.mdra-qm-team/fda-compliance/ and ra-qm-team/iec-62304-compliance/ for the implementation workTime Estimate: 4-12 weeks for classification, then RA/QM-driven submission timelines.
Goal: Pick the buyer segment and sales motion that matches your product.
Steps:
references/gtm_patterns.mdTime Estimate: 4-8 weeks for GTM strategy decision.
Scans a product description for indicators of PHI handling and HIPAA scope. Identifies whether you're likely a Covered Entity, Business Associate, both, or operating outside HIPAA (consumer wellness data).
bashpython scripts/phi_scope_checker.py description.txt python scripts/phi_scope_checker.py description.txt --json
references/hipaa_basics.md — HIPAA scope, Covered Entity vs Business Associate, BAA requirements, common pitfallsreferences/fda_samd_basics.md — Software as Medical Device classification, IMDRF framework, US vs EUreferences/gtm_patterns.md — Payor, provider, employer, individual, pharma, government — sales cycles, contract structures, decision criteriareferences/value_based_care_primer.md — Fee-for-service vs VBC, capitation, shared savings, ACOs, common modelsassets/hipaa_scope_template.md — Document template for capturing HIPAA scope decisions and BAA inventoryra-qm-team/ for medical-device-grade compliance work (ISO 13485, MDR, FDA, IEC 62304)legal/ for BAA / DPA templates and contract reviewengineering/cs-security-engineer — healthtech security goes beyond standard SaaSbusiness-growth/pricing-strategy — healthtech pricing has unusual constraints (PMPM, capitation, fee-for-service)c-level-advisor/cs-fundraising-advisor — healthtech investor expectations differ from generic SaaS| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-11 | pass→pass | 11,736 | 16,242 | +38% | 1 | 1 | 0% | 1,777 | 4,028 | +127% | 0 | 0 | — |
case-09 | pass→pass | 22,836 | 20,051 | -12% | 1 | 1 | 0% | 3,384 | 4,313 | +27% | 0 | 0 | — |
case-01 | fail→pass | 15,782 | 3,780 | -76% | 1 | 1 | 0% | 2,538 | 1,919 | -24% | 0 | 0 | — |
case-02 | pass→pass | 13,365 | 15,091 | +13% | 1 | 1 | 0% | 1,996 | 3,775 | +89% | 0 | 0 | — |
case-03 | pass→pass | 13,732 | 14,589 | +6% | 1 | 1 | 0% | 2,132 | 3,802 | +78% | 0 | 0 | — |
case-10 | pass→pass | 15,077 | 16,339 | +8% | 1 | 1 | 0% | 2,239 | 3,908 | +75% | 0 | 0 | — |
case-04 | pass→pass | 19,880 | 20,533 | +3% | 1 | 1 | 0% | 3,014 | 4,700 | +56% | 0 | 0 | — |
case-05 | fail→fail | 18,329 | 20,623 | +13% | 1 | 1 | 0% | 2,699 | 4,580 | +70% | 0 | 0 | — |
case-06 | pass→pass | 8,492 | 6,017 | -29% | 1 | 1 | 0% | 1,337 | 2,393 | +79% | 0 | 0 | — |
case-07 | pass→pass | 13,711 | 6,688 | -51% | 1 | 1 | 0% | 2,161 | 2,627 | +22% | 0 | 0 | — |
case-08 | pass→pass | 12,974 | 17,595 | +36% | 1 | 1 | 0% | 2,072 | 4,319 | +108% | 0 | 0 | — |
case-12 | fail→pass | 10,312 | 1,999 | -81% | 1 | 1 | 0% | 1,441 | 1,847 | +28% | 0 | 0 | — |
case-13 | fail→pass | 13,848 | 17,474 | +26% | 1 | 1 | 0% | 2,276 | 4,481 | +97% | 0 | 0 | — |
case-14 | pass→pass | 12,288 | 10,183 | -17% | 1 | 1 | 0% | 1,954 | 3,050 | +56% | 0 | 0 | — |
case-15 | pass→pass | 32,313 | 13,739 | -57% | 1 | 1 | 0% | 2,340 | 3,666 | +57% | 0 | 0 | — |
case-16 | pass→pass | 9,798 | 5,167 | -47% | 1 | 1 | 0% | 1,487 | 2,425 | +63% | 0 | 0 | — |
case-17 | fail→pass | 13,169 | 10,123 | -23% | 1 | 1 | 0% | 1,840 | 3,051 | +66% | 0 | 0 | — |
case-18 | pass→pass | 9,248 | 10,659 | +15% | 1 | 1 | 0% | 1,358 | 3,099 | +128% | 0 | 0 | — |
case-19 | pass→pass | 6,663 | 7,802 | +17% | 1 | 1 | 0% | 1,141 | 2,719 | +138% | 0 | 0 | — |
case-20 | fail→pass | 7,736 | 6,359 | -18% | 1 | 1 | 0% | 1,061 | 2,473 | +133% | 0 | 0 | — |
case-21 | pass→pass | 7,185 | 3,255 | -55% | 1 | 1 | 0% | 967 | 2,041 | +111% | 0 | 0 | — |
case-22 | fail→fail | 34,107 | 37,125 | +9% | 1 | 1 | 0% | 6,187 | 7,698 | +24% | 0 | 0 | — |
case-23 | fail→pass | 30,436 | 22,331 | -27% | 1 | 1 | 0% | 5,786 | 5,062 | -13% | 0 | 0 | — |
case-24 | pass→pass | 14,469 | 11,633 | -20% | 1 | 1 | 0% | 2,090 | 3,267 | +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. 24 cases were attempted. The headline lift of +25 percentage points is the difference between those two pass rates over the 24 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.