Rehabilitation Analyzer
Rehabilitation 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 log a recovery program, exercises, and functional assessments with the /rehab command, and the skill turns those records into a progress report: how range of motion, strength, and balance are changing, how pain behaves around training, and whether you are keeping to the plan.
Not a substitute for your physical therapist. The skill will not prescribe exercises, diagnose injuries or complications, change your rehab phase, or predict recovery time. Plans and decisions stay with your therapist and doctor.
What it analyzes
- Functional trends. Range of motion in degrees with an improvement rate per week and plateau detection; muscle strength on the manual muscle testing (MMT) scale; balance tests such as single-leg stance time.
- Pain patterns. Morning pain versus pain after activity, and which exercises or intensities line up with flare-ups.
- Adherence. Completed sessions divided by planned sessions, reported weekly, monthly, and overall, and by exercise type.
- Goals. Percent complete per goal, estimated time to reach it, and goals that are falling behind.
- Phase readiness. Whether the goals of the current phase are met before moving on, which is a prompt to talk to your therapist, not an automatic change.
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 /rehab command covers start, exercise, assess, progress, goals, and plan. Examples from the upstream docs:
/rehab start acl-surgery 2025-05-01
/rehab exercise straight_leg_raise 3x15 pain2
/rehab assess rom knee_flexion 120
/rehab assess strength quadriceps 4/5
/rehab progress
Supported program types listed upstream include orthopedic recovery (ACL reconstruction, meniscus surgery, fractures, joint replacement, spine surgery), sports injuries, neurological rehab such as stroke, and cardiac surgery recovery. Records are saved to data/rehabilitation-tracker.json plus dated log files.
Output
A progress report with a summary, ROM, strength, and balance trends, pain control, adherence percentage, goals achieved, in progress, and behind, phase progress, and general suggestions plus the date of the next assessment. A shorter brief is available for quick checks.
Limitations
- Measurements such as ROM degrees and MMT grades should come from your therapist; self-measured values make trends less reliable.
- Suggestions are general. The skill explicitly does not handle acute pain or new injuries; contact your care team for those.
FAQ
Can I share the report with my therapist? Yes. Reports are generated in Markdown, so you can save, print, or send them.
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
- Fitness Analyzer: once formal rehab ends, tracks general training volume and progress.
- Health Trend Analyzer: correlates symptoms, medication, and other records over time.
- AI Health Analyzer: 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.