Install any skill in seconds. Free to start, no credit card required.
Get Started Free →HIPAA-specific entrypoint for healthcare privacy and security work. Use when a task is explicitly framed around HIPAA, PHI handling, covered entities, BAAs, breach posture, or US healthcare compliance requirements.
.claude/skills/affaan-m-hipaa-compliance/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✓→✗ | ▼ Worse | 3% | 0% |
| case-02 | ✓→✓ | = Same ✓ | 19% | 0% |
| case-07 | ✓→✓ | = Same ✓ | 7% | 0% |
| case-03 | ✓→✓ | = Same ✓ | 5% | 0% |
| case-04 | ✓→✓ | = Same ✓ | 3% | 0% |
Use this as the HIPAA-specific entrypoint when a task is clearly about US healthcare compliance. This skill intentionally stays thin and canonical:
healthcare-phi-compliance remains the primary implementation skill for PHI/PII handling, data classification, audit logging, encryption, and leak prevention.healthcare-reviewer remains the specialized reviewer when code, architecture, or product behavior needs a healthcare-aware second pass.security-review still applies for general auth, input-handling, secrets, API, and deployment hardening.Treat HIPAA as an overlay on top of the broader healthcare privacy skill:
healthcare-phi-compliance for the concrete implementation rules.healthcare-reviewer if the task affects patient safety, clinical workflows, or regulated production architecture.User request:
> Add AI-generated visit summaries to our clinician dashboard. We serve US clinics and need to stay HIPAA compliant.
Response pattern:
hipaa-compliancehealthcare-phi-compliance to review PHI movement, logging, storage, and prompt boundarieshealthcare-reviewer if the summaries influence clinical decisionsUser request:
> Can we send support transcripts and patient messages into our analytics stack?
Response pattern:
healthcare-phi-compliancehealthcare-reviewerhealthcare-emr-patternshealthcare-eval-harnesssecurity-review| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-02 | pass→pass | 16,956 | 15,665 | -8% | 1 | 1 | 0% | 2,598 | 3,095 | +19% | 0 | 0 | — |
case-01 | pass→fail | 19,631 | 14,893 | -24% | 1 | 1 | 0% | 2,986 | 3,086 | +3% | 0 | 0 | — |
case-07 | pass→pass | 16,916 | 14,012 | -17% | 1 | 1 | 0% | 2,776 | 2,981 | +7% | 0 | 0 | — |
case-03 | pass→pass | 14,995 | 11,641 | -22% | 1 | 1 | 0% | 2,465 | 2,577 | +5% | 0 | 0 | — |
case-04 | pass→pass | 14,384 | 11,762 | -18% | 1 | 1 | 0% | 2,442 | 2,523 | +3% | 0 | 0 | — |
case-05 | pass→pass | 14,635 | 12,203 | -17% | 1 | 1 | 0% | 2,180 | 2,501 | +15% | 0 | 0 | — |
case-06 | pass→pass | 17,600 | 10,383 | -41% | 1 | 1 | 0% | 2,725 | 2,246 | -18% | 0 | 0 | — |
case-08 | pass→pass | 21,963 | 16,716 | -24% | 1 | 1 | 0% | 3,367 | 3,356 | -0% | 0 | 0 | — |
case-09 | pass→pass | 16,424 | 14,937 | -9% | 1 | 1 | 0% | 2,593 | 2,975 | +15% | 0 | 0 | — |
case-10 | pass→pass | 17,479 | 16,511 | -6% | 1 | 1 | 0% | 2,819 | 3,240 | +15% | 0 | 0 | — |
case-11 | pass→pass | 16,641 | 14,878 | -11% | 1 | 1 | 0% | 2,390 | 2,761 | +16% | 0 | 0 | — |
case-16 | pass→pass | 18,862 | 20,364 | +8% | 1 | 1 | 0% | 2,788 | 3,891 | +40% | 0 | 0 | — |
case-12 | pass→pass | 20,648 | 21,500 | +4% | 1 | 1 | 0% | 2,893 | 4,167 | +44% | 0 | 0 | — |
case-13 | pass→pass | 17,892 | 15,561 | -13% | 1 | 1 | 0% | 2,873 | 3,362 | +17% | 0 | 0 | — |
case-14 | pass→pass | 16,456 | 14,540 | -12% | 1 | 1 | 0% | 2,626 | 3,129 | +19% | 0 | 0 | — |
case-15 | pass→pass | 19,730 | 13,797 | -30% | 1 | 1 | 0% | 3,018 | 2,806 | -7% | 0 | 0 | — |
case-17 | pass→pass | 18,853 | 16,100 | -15% | 1 | 1 | 0% | 2,656 | 3,163 | +19% | 0 | 0 | — |
case-18 | pass→pass | 15,431 | 15,180 | -2% | 1 | 1 | 0% | 2,389 | 2,913 | +22% | 0 | 0 | — |
case-19 | pass→pass | 18,133 | 15,199 | -16% | 1 | 1 | 0% | 2,776 | 3,018 | +9% | 0 | 0 | — |
case-20 | pass→pass | 23,816 | 18,758 | -21% | 1 | 1 | 0% | 3,535 | 3,383 | -4% | 0 | 0 | — |
case-21 | pass→pass | 22,082 | 18,378 | -17% | 1 | 1 | 0% | 3,297 | 3,476 | +5% | 0 | 0 | — |
case-22 | pass→pass | 18,036 | 13,826 | -23% | 1 | 1 | 0% | 2,960 | 3,131 | +6% | 0 | 0 | — |
case-23 | pass→pass | 19,006 | 14,393 | -24% | 1 | 1 | 0% | 2,892 | 2,793 | -3% | 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 -100 percentage points is the difference between those two pass rates over the 23 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 8/3/2026 | +9% |
| gemini-3.6-flash | verified | 8/3/2026 | +18% |
| gemini-3.6-flash | verified | 8/3/2026 | +4% |
Other measured skills in the registry, with their headline benchmark lift.