hipaa-safeguards
Map HIPAA Security Rule safeguards and run a risk analysis for systems handling PHI. Use when asked to become HIPAA-compliant, assess HIPAA safeguards, prepare for handling PHI/ePHI, or scope a BAA. Produces a HIPAA assessment — the administrative/physical/technical safeguards with required-vs-addressable status, a risk analysis, BAA scope, and a prioritised remediation plan.
git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills /tmp/hipaa-safeguards && cp -r /tmp/hipaa-safeguards/plugins/pm-compliance/skills/hipaa-safeguards ~/.claude/skills/hipaa-safeguardsSKILL.md
# HIPAA Safeguards Skill
HIPAA's Security Rule is a list of safeguards for electronic protected health information (ePHI), split
into administrative, physical, and technical — some **required**, some **addressable** (you must do them
*or* document why an equivalent is reasonable). This skill maps your controls to that list, runs the
risk analysis HIPAA mandates, and flags where you're exposed — so handling PHI is defensible, not hopeful.
## Required Inputs
Ask for these only if they aren't already provided:
- **Your role** — covered entity, or business associate (a vendor handling PHI for one). Both owe Security Rule safeguards.
- **The ePHI flow** — where PHI is created, received, stored, transmitted, and who can access it.
- **Current safeguards** — what's in place for access control, encryption, audit logging, backups, training.
- **Business associates** — third parties touching PHI (each needs a BAA).
## Output Format
### HIPAA Assessment: [entity] ([covered entity / business associate])
**1. ePHI inventory & flow** — where PHI lives and moves; the systems in scope.
**2. Safeguards** — a table per category; status `met` / `partial` / `gap`, and required vs. addressable:
| Category | Safeguard | Req/Addr | Status | Notes |
|---|---|---|---|---|
| Technical | Encryption of ePHI at rest & in transit | Addressable | partial | TLS yes; disk encryption pending |
| Administrative | Security risk analysis | Required | gap | Not yet performed |
| Physical | Facility access controls | Required | met | |
**3. Risk analysis** — the required (§164.308(a)(1)) assessment: threats to ePHI, likelihood × impact, and the residual risk after controls. This is the control auditors check first and the one most often missing.
**4. BAA scope** — which business associates need a Business Associate Agreement, and what each must guarantee.
**5. Remediation** — prioritised gaps (required-and-gap first), owners, dates. For addressable items not implemented, the documented justification + alternative.
## Programmatic Helper
`scripts/hipaa_checklist.py` (stdlib only) scores safeguard coverage and surfaces unmet **required**
safeguards (the ones with no "addressable" escape hatch):
```bash
# safeguards.json: [{"category":"Technical","safeguard":"...","required":true,"status":"met|partial|gap"}, ...]
python3 scripts/hipaa_checklist.py safeguards.json
python3 scripts/hipaa_checklist.py safeguards.json --json
```
## Quality Checks
- [ ] A documented security risk analysis exists (or is the top remediation item) — it's required and foundational
- [ ] Each safeguard is marked required vs. addressable, and addressable-not-done items have a written justification + alternative
- [ ] Encryption of ePHI in transit and at rest is assessed explicitly
- [ ] Every business associate has (or is flagged as needing) a BAA
- [ ] Audit logging / access review for PHI access is covered
## Anti-Patterns
- [ ] Do not treat "addressable" as "optional" — you must implement it or document why an equivalent is reasonable; silence is a violation
- [ ] Do not skip the risk analysis — it's explicitly required and the most-cited gap in OCR enforcement
- [ ] Do not handle PHI through a vendor without a BAA — that alone is a breach
- [ ] Do not present this as legal certification — flag that compliance counsel / a security assessor must validate, especially the risk analysis
- [ ] Do not conflate HIPAA with SOC 2 or GDPR — overlapping controls, different legal requirements; map each separately
## Based On
HIPAA Security Rule (45 CFR §164.308–312) — administrative, physical, and technical safeguards + required risk analysis.Conduct a structured ethical review of an AI or ML feature, model, or product. Use when preparing to deploy an AI system, assessing algorithmic risk, auditing a model for bias, or producing a responsible AI impact assessment. Produces a structured ethics review covering fairness, transparency, privacy, safety, accountability, and societal impact with a risk tier score, pre-deployment checklist, and prioritised mitigations.
Structure AI and ML product decisions with the rigour of any product decision. Use when building AI-powered features, evaluating LLM integrations, designing AI products, or assessing AI readiness. Produces a complete AI product canvas covering problem definition, model approach, data requirements, evaluation framework, UX design, responsible AI checklist, and launch monitoring plan.
Transform feature briefs into structured design briefs that give designers the context they need before opening Figma. Use when asked to write a design brief, create a design handoff, brief a designer on a new feature, or translate a PRD into design requirements. Produces a brief with user goal, emotional context, success criteria, constraints, edge cases, and out-of-scope boundaries.
Design statistically rigorous A/B tests and interpret experiment results. Use when asked to design an experiment, run an A/B test, calculate sample size, interpret test results, or assess whether an experiment was successful. Produces a complete experiment design with hypothesis, sample size, run time, success criteria, and risk flags — or a results interpretation with ship/iterate/kill recommendation.
Synthesises user signals from multiple research sources into a unified, weighted insight brief. Use when you have data from interviews, support tickets, NPS verbatims, app reviews, or sales calls and need to reconcile contradictions, surface the underlying need behind requests, or answer 'what are users really telling us'. Produces ranked insights with confidence ratings, source weighting rationale, divergent signal analysis by user segment, and a research gap identification section.
Structure a product data analysis, metric deep-dive, funnel analysis, or cohort study. Use when asked to analyse product metrics, investigate a drop in conversion, explain a data change to stakeholders, or find the root cause of a metric movement. Produces a structured analysis with question, root cause, confidence level, and recommended action.
Interpret product metrics against goals and surface actionable signals. Use when asked to analyse product health, review key metrics, investigate a performance issue, produce a health report, or assess product-market fit signals. Produces a structured health report with RAG status, trend analysis, root cause hypotheses, and prioritised actions.
Structure a retention analysis, churn investigation, or engagement deep-dive for any product team. Use when asked to analyse user retention, investigate churn, measure DAU/MAU, or build a retention improvement plan. Produces a retention snapshot with root cause hypotheses, aha-moment correlation, and prioritised interventions.