health-skillz — security grade SAFE, quality 73/100

Security audit verdict: SAFE · quality 73/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by jmandel · Claude Skill · ★ 80

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is health-skillz safe to install? View the security audit →

About health-skillz

Health Skillz Health Skillz helps people collect SMART on FHIR records from patient portals, review/export them locally, and optionally share them with AI using end-to-end encrypted upload. Documentation Design and architecture: Environment/runbook notes: This README intentionally stays high-level. API contracts, data structures, security model, and protocol details are documented in . Try It Now A live instance is available at health-skillz.joshuamandel.com. Download the skill: health-record-assistant.zip Install in Claude: Settings - Skills - Upload zip Ask: "Can you look at my health records?" Epic sandbox test credentials: Username: Password: Local Development Prerequisites Bun A SMART on FHIR client registration (or sandbox client IDs) Quick Start Health check: If you use a different port, update the URL accordingly. Configuration (High-Level) The server reads

agentsclaude-skillsehrehr-dataepichealthhealthcaresmart-on-fhir-fhir

Quick Facts

Stars80
Forks7
LanguageTypeScript
CategoryClaude Skill
Quality Score73.2578538021368/100
Open Issues4
Last Updated2026-06-08
Created2026-01-12
Platformsclaude-code, node
Est. Tokens~887k

Compatible Skills

These tools work well together with health-skillz for enhanced workflows:

  • starknet-agentic — semantic(0.19)+complementary+same_lang+similar_pop+shared_platform (52%)
  • openpaw — semantic(0.18)+complementary+same_lang+similar_pop+shared_platform (51%)

health-skillz alternative? Top 6 similar tools

Looking for a health-skillz alternative? If you're comparing health-skillz with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • HealthChain by healthchainai · ⭐ 221

    Python SDK for healthcare AI — typed, validated FHIR tools for agents, real-time EHR connectivity, production

  • dentalpin by dentalpin · ⭐ 81

    The open source agentic dental software. Built for AI.

  • dentalpin by martinezsalmeron · ⭐ 50

    The open source agentic dental software. Built for AI.

  • tutor-skills by RoundTable02 · ⭐ 400

    A Claude Code skill that turns PDFs, docs, and codebases into Obsidian study vaults

  • daymon by daymonio · ⭐ 365

    Daymon puts your favorite AI to work 24/7. It schedules, remembers, and orchestrates your own virtual team. Fr

  • mcp-server-code-execution-mode by elusznik · ⭐ 337

    An MCP server that executes Python code in isolated rootless containers with optional MCP server proxying. Imp

More Claude Skill Tools

Explore other popular claude skill tools:

View all Claude Skill tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is health-skillz?

health-skillz is A Claude Skill for connecting to and analyzing personal health records via SMART on FHIR. It is categorized as a Claude Skill with 80 GitHub stars.

What programming language is health-skillz written in?

health-skillz is primarily written in TypeScript. It covers topics such as agents, claude-skills, ehr.

How do I install or use health-skillz?

You can find installation instructions and usage details in the health-skillz GitHub repository at github.com/jmandel/health-skillz. The project has 80 stars and 7 forks, indicating an active community.

What are the best alternatives to health-skillz?

The top alternatives to health-skillz on Agent Skills Hub include HealthChain, dentalpin, dentalpin. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Claude Skill tools