Family Health Analyzer
Family Health Analyzer is a Claude Code skill from WellAlly Health (formerly Claude-Ally-Health), an MIT-licensed, local-first personal health record project maintained by WellAlly Tech. You add family members and their diagnoses with the /family command, and the skill looks for patterns in that history: conditions that cluster in the family, early-onset cases, and what that suggests for screening and prevention.
Statistics, not genetics. The skill works only from the family history you enter. It does not diagnose hereditary disease or predict whether any individual will get sick. For genetic questions, see a doctor or a certified genetic counselor. Every report carries this disclaimer.
What it analyzes
- Family clustering. Conditions that appear across several relatives, such as hypertension or diabetes.
- Early-onset cases, usually defined in the skill as a diagnosis before age 50.
- Hereditary risk score. A weighted mix of affected first-degree relatives (40%), early-onset cases (30%), and degree of clustering (30%), reported as low (under 40%), medium (40-69%), or high (70% and above). This is a heuristic from the skill file, not a clinical risk model.
- Prevention suggestions grouped into screening (what to check and how often, from what age), lifestyle, and when to see a specialist.
- Links to other modules. It reads the project's hypertension and diabetes trackers and your profile, and can relate family history to your own medication records.
How to use it
WellAlly Health is a Claude Code project, not a standalone package. Clone it and start Claude Code in the folder:
git clone https://github.com/huifer/WellAlly-health.git
cd WellAlly-health
claude
The /family command supports add-member, add-history, track, list, risk, and report. Examples adapted from the upstream docs (which are in Chinese):
/family add-member father Zhang San 1960-05-15 blood type A
/family add-history father hypertension diagnosed at 50
/family add-history mother diabetes onset at 55
/family risk
/family report
Data is stored in data/family-health-tracker.json.
Output
A short text summary in the terminal, plus a full HTML report with ECharts visuals: a family tree, a hereditary risk heatmap, a disease distribution chart, and a timeline of prevention actions.
Limitations
- Results are only as good as the history you know and enter. Missing or uncertain diagnoses weaken every estimate.
- It ignores genetic testing, environment, and lifestyle except where you record them.
- It stores health information about relatives, so treat the data folder as sensitive.
FAQ
Does it replace genetic testing? No. It is a structured way to organize family history before talking to a doctor or genetic counselor.
Does my data leave my machine? Records are stored as local files. The analysis runs through Claude Code, so the content you ask about is sent to the model Claude Code uses.
Alternatives
- Health Trend Analyzer: tracks your own measurements and lab values over time.
- AI Health Analyzer: cross-module overview of your health records.
- Emergency Card: a quick-reference card with your allergies, conditions, and medications.
Browse more in the skills category or the health tag.
Comments
No comments yet. Be the first to comment!
Related Tools
Related Insights

Anthropic Subagent: The Multi-Agent Architecture Revolution
Deep dive into Anthropic multi-agent architecture design. Learn how Subagents break through context window limitations, achieve 90% performance improvements, and real-world applications in Claude Code.
How to pick an AI coding CLI for your repo
Match Claude Code, Codex CLI, OpenCode, Pi, omp, DeepSeek Harness, and Grok Build to the work you actually run. Docs rechecked 2026-10-06.
Skills + Hooks + Plugins: How Anthropic Redefined AI Coding Tool Extensibility
An in-depth analysis of Claude Code's trinity architecture of Skills, Hooks, and Plugins. Explore why this design is more advanced than GitHub Copilot and Cursor, and how it redefines AI coding tool extensibility through open standards.