By amydeng2000
Investigate ambiguous non-emergency health symptoms through structured intake, tracking, testing, analysis, and low-risk experiment planning, with support for file inspection and artifact creation.
A Codex and Claude Code skill for investigating ambiguous, non-emergency health symptoms through intake, tracking, testing, analysis, and careful experiment planning.
The skill is designed to reduce activation energy for people who want to act on vague health questions like "I've been feeling more tired lately" without jumping straight to premature conclusions or unsafe experiments.
This skill is not medical advice and does not replace a clinician. It is intended for organizing information, generating hypotheses, and planning safer next actions.
In Codex, paste this into the chat:
$skill-installer install https://github.com/amydeng2000/health-self-investigation-skill/tree/main/skills/health-self-investigation
The $ is part of the Codex skill invocation.
Then restart Codex so the skill is loaded.
This does not require cloning the repo.
From a terminal:
claude plugin marketplace add amydeng2000/health-self-investigation-skill
claude plugin install health-self-investigation@health-self-investigation
Or from inside Claude Code:
/plugin marketplace add amydeng2000/health-self-investigation-skill
/plugin install health-self-investigation@health-self-investigation
Then restart Claude Code or run /reload-plugins. Invoke it with:
/health-self-investigation:health-self-investigation I have been feeling more tired lately.
If your GitHub CLI supports gh skill (gh >= 2.90.0):
gh skill install amydeng2000/health-self-investigation-skill health-self-investigation --agent claude-code --scope user
If gh says unknown command "skill", update GitHub CLI or use Option A.
If you prefer a plain, non-plugin Claude Code skill, clone or download the repo and copy the Claude Code skill folder into your Claude skills directory:
mkdir -p ~/.claude/skills
cp -R claude-skills/health-self-investigation ~/.claude/skills/
Then restart Claude Code. Invoke it with:
/health-self-investigation I have been feeling more tired lately.
Copy the contents of:
skills/health-self-investigation/references/portable-core.md
Paste it into ChatGPT, Claude, or another assistant's project/system instructions.
Use $health-self-investigation. I've been feeling more tired lately.
If installed through the Claude Code plugin marketplace, use the plugin-qualified slash command:
/health-self-investigation:health-self-investigation I've been feeling more tired lately.
If copied manually into ~/.claude/skills, use the skill slash command:
/health-self-investigation I've been feeling more tired lately.
/health-self-investigation I have two weeks of symptom logs and want help finding patterns.
/health-self-investigation I want to know what experiments are safe to try for my recurring afternoon crashes.
After pasting portable-core.md into project/system instructions, ask naturally:
I've been feeling more tired lately. Please use the health self-investigation process.
The skill is released under the MIT License. See skills/health-self-investigation/LICENSE.txt.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub amydeng2000/health-self-investigation-skill --plugin health-self-investigationImplementation of the Dr. Ralph technique - continuous self-referential AI loops for interactive iterative development. Run Claude in a while-true loop with the same prompt until task completion.
Guides users through a structured symptom interview, literature search, and evidence evaluation to prepare for medical appointments
Claude Code skill pack for OpenEvidence medical AI (24 skills)
Forces skill evaluation before every response
Continuous learning hooks for gladiator MCP (observe patterns, reflect on them)
Skill and agent authoring tools: generate, audit, and improve Claude Code skills, commands, and agents