Occupational Health Analyzer
Occupational 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. It reads the work-health records you log with the /work command and turns them into a report on sitting time, screen exposure, workstation ergonomics, work-related symptoms, and suggested screenings. Records are stored as JSON files in the project folder on your own machine.
Not a medical device. The skill does not diagnose occupational disease or issue certificates. Treat its report as notes to discuss with an occupational-medicine doctor or your workplace health service.
What it analyzes
- Sedentary and screen (VDT) risk. Each is scored on four factors worth 1 to 10 points, for a total of 4 to 40: low (4-13), medium (14-26), or high (27-40). Inputs include daily sitting or screen hours, break frequency, weekly exercise minutes, 20-20-20 rule compliance, lighting, and current symptom severity.
- Overall risk. The highest single score sets the level, and it is raised one step when several factors are high or three or more are medium. Shift work, repetitive strain, and job stress are also considered.
- Work-related symptoms such as neck, shoulder, and back pain, eye strain, and wrist pain, tracked for severity and trend.
- Ergonomics. A 100-point checklist covering chair, monitor, keyboard and mouse, desk, and environment (lighting, noise, temperature). A lower score means fewer problems.
- Screening suggestions by job type, for example yearly vision and musculoskeletal checks for office work, hearing tests for noisy workplaces, and lung-function checks for dusty or chemical environments.
- Correlations with the sleep, fitness, and mental-health trackers in the same project.
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
Then log data and ask for analysis. The /work command supports assess, issue, ergonomic, screening, environment, status, trend, and recommend (upstream examples are written in Chinese):
/work assess office work, 8 hours a day, mostly at a computer
/work issue neck_pain moderate
/work ergonomic monitor eye level, 60cm away
/work trend
Trend analysis needs at least three assessment records.
Output
A Markdown report with an overall risk level, sedentary and screen scores with advice, active issues and whether they are improving, ergonomic fixes ranked by priority, recommended screenings, and a one-week action plan. High-risk patterns produce an explicit warning to see an occupational-medicine specialist.
Limitations
- Scores depend entirely on what you self-report.
- The thresholds are the project's own heuristics; the skill file does not cite a validation study.
- It will not replace workplace health surveillance or handle acute health problems.
FAQ
Does my data leave my machine? Records are stored as local files and the project states it does no uploads of its own. The analysis runs through Claude Code, so the content you ask about is sent to the model Claude Code uses.
Is it built for company-wide programs? No. The project describes itself as a personal health record, with no multi-user or compliance features.
Alternatives
- Mental Health Analyzer: the stress and mood side of work strain, from the same project.
- Sleep Analyzer: useful for shift workers, since sleep data feeds the correlation step.
- Fitness Analyzer: tracks the exercise minutes the sedentary score relies on.
- AI Health Analyzer: a cross-module overview of your health records.
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.