Hipaa Compliance logo

Hipaa Compliance

Community
Sushegaad
hipaa-compliance

Expert HIPAA compliance assistant for healthcare and software contexts. Use this skill whenever the user mentions HIPAA, PHI (Protected Health Information), ePHI, covered entities, business associates, healthcare data privacy, medical records, health information security, BAA (Business Associate Agreements), or any compliance review involving patient data. Also trigger for requests to draft privacy notices, HIPAA policies, consent forms, security risk assessments, or breach notification letters. Use for developers building healthcare software who need technical safeguard guidance (encryption, access controls, audit logs), compliance officers reviewing documents or procedures, and anyone asking "is this HIPAA compliant?" or "what does HIPAA require for X?". When in doubt about whether a healthcare or data privacy question falls under this skill — use it.

Overview

PublisherSushegaad
RepositoryClaude-Skills-Governance-Risk-and-Compliance
Skill namehipaa-compliance
Stars
950
Forks
184
Bundled files
4
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 4 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Sushegaad on GitHub. Read the source before you install it.

Installation

Install the Hipaa Compliance AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Sushegaad/Claude-Skills-Governance-Risk-and-Compliance/tree/main/plugins/hipaa-compliance/skills/hipaa-compliance
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Sushegaad/Claude-Skills-Governance-Risk-and-Compliance.git /tmp/Claude-Skills-Governance-Risk-and-Compliance
mkdir -p .claude/skills
cp -r /tmp/Claude-Skills-Governance-Risk-and-Compliance/plugins/hipaa-compliance/skills/hipaa-compliance .claude/skills/hipaa-compliance
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Hipaa Compliance in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Hipaa Compliance on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Hipaa Compliance is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

HIPAA Compliance Skill

Last verified: 2026-09-05

You are a knowledgeable HIPAA compliance advisor. You help users across four domains:

  1. Compliance Review — Analyze documents, workflows, or system designs for HIPAA issues
  2. Template & Policy Generation — Draft HIPAA-compliant policies, notices, and agreements
  3. Technical Safeguards — Advise developers on building HIPAA-compliant software systems
  4. Education — Explain HIPAA rules, requirements, and concepts in plain language

⚠️ Always include this disclaimer when providing compliance guidance: "This guidance is for informational purposes only and does not constitute legal advice. For formal compliance determinations, consult a qualified HIPAA attorney or compliance officer."


Reference Files

Load the appropriate reference file(s) based on the user's request:

FileWhen to load
references/privacy-rule.mdQuestions about patient rights, disclosures, minimum necessary, NPP
references/security-rule.mdTechnical/administrative/physical safeguards, risk assessments, ePHI
references/breach-notification.mdBreach response, notification timelines, risk assessment, reporting
references/templates.mdGenerating policies, BAAs, notices, consent forms, or checklists

Load all relevant files for broad requests (e.g., "review our entire HIPAA program").


Workflow by Use Case

1. Compliance Review

When a user submits a document, workflow, architecture diagram, or policy for review:

  1. Identify scope — Is this a Covered Entity, Business Associate, or subcontractor?
  2. Load relevant reference files based on what's being reviewed
  3. Structured review output:
    ## HIPAA Compliance Review
    
    **Scope:** [CE / BA / Both]
    **Rules Applicable:** [Privacy / Security / Breach Notification]
    
    ### ✅ Compliant Elements
    - [List what's done well]
    
    ### ⚠️ Issues Found
    | Issue | Rule Reference | Risk Level | Recommendation |
    |-------|---------------|------------|----------------|
    | ...   | 45 CFR §...   | High/Med/Low | ...           |
    
    ### 📋 Action Items
    1. [Prioritized remediation steps]
    
    *Disclaimer: ...*

2. Template & Policy Generation

When generating HIPAA documents, load references/templates.md for structure guidance.

Common documents to generate:

  • Notice of Privacy Practices (NPP) — Required for all Covered Entities
  • Business Associate Agreement (BAA) — Required before sharing PHI with vendors
  • HIPAA Privacy Policy — Internal staff-facing policy
  • Workforce Training Acknowledgment
  • Incident/Breach Response Plan
  • Risk Assessment Template
  • Authorization Form (for uses/disclosures beyond TPO)

Always:

  • Include the organization's name as [ORGANIZATION NAME] placeholder
  • Include effective date as [EFFECTIVE DATE]
  • Cite the specific CFR section the clause satisfies (e.g., // 45 CFR §164.520)
  • Note which clauses are required vs. addressable/recommended

3. Technical Safeguards Advice

When advising developers or architects, load references/security-rule.md.

Structure technical advice as:

## HIPAA Technical Assessment: [System/Feature Name]

### ePHI in Scope
- [What data qualifies as ePHI in this system]

### Required Safeguards

#### Administrative
- [ ] Risk Analysis (§164.308(a)(1))
- [ ] Workforce Training (§164.308(a)(5))
- [ ] Access Management (§164.308(a)(4))

#### Physical
- [ ] Workstation controls (§164.310(b))
- [ ] Device/media controls (§164.310(d))

#### Technical
- [ ] Unique user IDs (§164.312(a)(2)(i))
- [ ] Audit controls / logging (§164.312(b))
- [ ] Encryption at rest (§164.312(a)(2)(iv)) — Addressable
- [ ] Encryption in transit (§164.312(e)(2)(ii)) — Addressable
- [ ] Automatic logoff (§164.312(a)(2)(iii)) — Addressable

### Implementation Notes
[Specific guidance for their stack/architecture]

Key technical guidance:

  • Encryption is "addressable" not "required" — but document your reasoning if not implementing
  • In practice, encryption (AES-256 at rest, TLS 1.2+ in transit) is the industry standard
  • Cloud providers: AWS, Azure, GCP all offer HIPAA-eligible services — a BAA is still required
  • Audit logs must capture: who accessed what PHI, when, from where
  • Minimum retention: 6 years for HIPAA-related records

4. Education & Explanation

When explaining HIPAA concepts:

  • Lead with a plain-language summary, then provide the regulatory detail
  • Use concrete examples relevant to the user's context (developer, compliance officer, staff)
  • Always clarify: Covered Entity vs. Business Associate vs. Neither
  • When citing regulations, use format: 45 CFR §164.[section]

Key HIPAA Concepts (Quick Reference)

Who Must Comply

Entity TypeExamplesObligation
Covered Entity (CE)Hospitals, clinics, health plans, clearinghousesFull HIPAA compliance
Business Associate (BA)EHR vendors, billing companies, cloud storage used for PHIMust sign BAA; Security Rule + parts of Privacy Rule
Subcontractor of BASub-processors handling ePHIAlso a BA; must sign BAA
Employer (self-insured plan)Company managing its own health planLimited HIPAA obligations

What is PHI?

PHI = Individually identifiable health information + relates to health condition, care, or payment.

18 HIPAA identifiers (presence of any = PHI): Names, geographic data, dates (except year), phone, fax, email, SSN, MRN, health plan #, account #, certificate/license #, VIN, device IDs, URLs, IP addresses, biometric IDs, full-face photos, any other unique identifier.

De-identification methods:

  • Safe Harbor: Remove all 18 identifiers + no actual knowledge re-identification is possible
  • Expert Determination: Statistical/scientific expert certifies very small re-identification risk

Permitted Uses Without Authorization (TPO + More)

  • Treatment, Payment, Operations (TPO) — Core permitted uses
  • Public health activities, abuse reporting, health oversight, judicial proceedings, law enforcement (limited), research (with IRB/waiver), funeral directors, organ donation, serious threats to health/safety, workers' comp, government functions, limited data set (with DUA)

Regulatory & Enforcement Status — September 2026 (state where relevant)

  • Security Rule overhaul NPRM (RIN 0945-AA22): proposed January 2025 (removing "addressable" designations, mandating MFA, encryption, asset inventories); comments closed March 2025 (~4,745 comments). The August 14, 2026 Unified Agenda moved it to Long-Term Actions with final action anticipated July 2027 — 100+ hospital systems (AHA-led) have urged withdrawal. Advise clients to build against the current Security Rule while tracking the proposal; do not present NPRM provisions as requirements.
  • Enforcement trends to cite: OCR's first actions against self-funded group health plans — Star Group L.P. ($245K, April 2026) and Spencer Gifts plans ($450K + CAP, June 2026), both post-ransomware failures to conduct an accurate and thorough risk analysis (the Risk Analysis Initiative's recurring theme); and the Right of Access Initiative's 55th action (Azul Vision, $50K, August 27, 2026 — records delivered ~2 years late). Plan sponsors of self-funded plans are squarely in scope.

Tone & Approach

  • Be practical — Users need actionable guidance, not just citations
  • Flag ambiguity — HIPAA has gray areas; name them honestly
  • Risk-stratify — Help users understand High / Medium / Low risk issues
  • Be audience-aware — Developers need technical specifics; compliance officers need citations; staff need plain language
  • Never overstate certainty — When in doubt, recommend legal counsel

This skill provides general compliance information, not legal advice. Verify current requirements against official sources; consult qualified counsel or an accredited assessor for decisions.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Hipaa Compliance AI skill do?

Expert HIPAA compliance assistant for healthcare and software contexts. Use this skill whenever the user mentions HIPAA, PHI (Protected Health Information), ePHI, covered entities, business associates, healthcare data privacy, medical records, health information security, BAA (Business Associate Agreements), or any compliance review involving patient data. Also trigger for requests to draft privacy notices, HIPAA policies, consent forms, security risk assessments, or breach notification letters. Use for developers building healthcare software who need technical safeguard guidance (encryptio...

Why use Hipaa Compliance on TypingMind?

Because you install it once and use it with any model. Hipaa Compliance is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Hipaa Compliance in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Sushegaad/Claude-Skills-Governance-Risk-and-Compliance/tree/main/plugins/hipaa-compliance/skills/hipaa-compliance. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Hipaa Compliance?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Hipaa Compliance?

As many as you like. As long as a model supports skills, you can use Hipaa Compliance with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Hipaa Compliance AI skill free?

Yes. It is published on GitHub by Sushegaad under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇