Longevity OS
SQLite health tracker with BH-corrected pattern scans and N-of-1 trial design
Test report
- Verdict
- Works with setup
- Score
- Tested
- Aug 7, 2026
- Environment
- Claude Code 2.x (agent harness)
Twenty-one files ship with the author's own home directory baked in, so `python scripts/setup.py` dies with PermissionError on /Users/A.Y before the skill does anything; after rewriting those paths the statistics engine is genuinely good, returning 400 Benjamini-Hochberg-corrected correlations across lags 0-7 where a hand-rolled query only produced nine uncorrected r values. The weekly report is still broken: asked for 2026-03-16 to 2026-03-22, a week holding 30 diet entries and 41 body metrics, it answered "no data" because it converts the date range into a day count and looks back from today instead.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 3/5
- Triggers reliably 5/5
- Output vs. baseline 7/10
- Docs & honesty 2/5
What Longevity OS does
Turns a local SQLite database of diet, exercise, sleep, body metrics, biomarkers and supplements into correlation scans, anomaly detection and N-of-1 trial proposals, dispatched through nine department sub-agents. Triggers on health logging, biomarker review, weekly health reports and self-experimentation requests. Ships a Python modeling engine, a schema, importers and a local dashboard alongside the skill body.
How to install Longevity OS
git clone https://github.com/albert-ying/longevity-os.git
mkdir -p ~/.claude/skills
cp -r longevity-os ~/.claude/skills/longevity-os
rm -rf ~/.claude/skills/longevity-os/.git
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Longevity OS
-
/longevity-osSQLite health tracker with BH-corrected pattern scans and N-of-1 trial design
It also activates on plain-language prompts like these:
-
Which of my logged habits predict my sleep quality and HRV? -
Generate my weekly health report from last week's tracked data -
Log today's supplements and check for any biomarker anomalies
Frequently asked questions
- Is the Longevity OS skill free?
- Yes. The skill itself is free from albert-ying/longevity-os. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Longevity OS work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Aug 7, 2026. Verdict: Works with setup. Twenty-one files ship with the author's own home directory baked in, so `python scripts/setup.py` dies with PermissionError on /Users/A.Y before the skill does anything; after rewriting those paths the statistics engine is genuinely good, returning 400 Benjamini-Hochberg-corrected correlations across lags 0-7 where a hand-rolled query only produced nine uncorrected r values. The weekly report is still broken: asked for 2026-03-16 to 2026-03-22, a week holding 30 diet entries and 41 body metrics, it answered "no data" because it converts the date range into a day count and looks back from today instead.
- What is the Longevity OS SkillProof Score?
- 6.8/10 — installs cleanly 3/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 2/5.
- How do I install Longevity OS?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Longevity OS with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.