dont-trust-ai-medical-diagnoses

dont-trust-ai-medical-diagnoses is a skill for Claude Code from alivirgo/Major-AI-Skills. It costs 28 tokens per session (1,061 once invoked), scanned A, original, MIT.

A safety guide for using an AI assistant to understand medical terms, lab reports, and appointment topics without asking it to diagnose illness or prescribe treatment.

In plain words
What is it for?
It helps translate clinical language, explain basic body processes, and prepare organized questions for a doctor.
Why use it?
It reduces the risk of false reassurance, frightening guesses, unsafe medication changes, or delaying urgent care.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Codex.

Part of the major-ai-skills plugin — 147 skills, 8 plugins shipped together

Good fit It helps translate clinical language, explain basic body processes, and prepare organized questions for a doctor.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/alivirgo/major-ai-skills/dont-trust-ai-medical-diagnoses
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add alivirgo/Major-AI-Skills --skill dont-trust-ai-medical-diagnoses
Clone the repo
git clone --depth 1 https://github.com/alivirgo/Major-AI-Skills

Made for: Claude Code.

Or install major-ai-skills, the plugin that ships this one along with the rest of its 147 skills, 8 plugins.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for dont-trust-ai-medical-diagnoses

README.md
[![agentmods](https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/dont-trust-ai-medical-diagnoses/github.svg)](https://agentmods.dev/skills/alivirgo/major-ai-skills/dont-trust-ai-medical-diagnoses)
Your own site
<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/dont-trust-ai-medical-diagnoses"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/dont-trust-ai-medical-diagnoses/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for dont-trust-ai-medical-diagnoses

Your own site · 80×15
<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/dont-trust-ai-medical-diagnoses"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/dont-trust-ai-medical-diagnoses.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,061 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00028 $0.01061
Opus 5 $0.00014 $0.00531
Sonnet 5 $0.00006 $0.00212
Haiku 4.5 $0.00003 $0.00106

Measured yesterday against content hash bf4f81dd71b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

dont-trust-ai-medical-diagnoses scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/dont-trust-ai-medical-diagnoses/SKILL.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Don't Trust AI Medical Diagnoses (Health Literacy Framework) (AI Skill)

Overview

Searching symptoms or pasting medical reports into an AI assistant often triggers extreme responses: either catastrophic worst-case diagnoses (e.g. rare autoimmune conditions or oncology) or false reassurance that causes patients to delay critical in-person care.

The Health Literacy & Doctor-Prep Protocol establishes strict boundaries: never use AI to diagnose illnesses or prescribe dosages, but leverage its strength to translate complex clinical jargon, explain anatomical mechanisms, and generate organized questions for your physician.


The Medical AI Safety Boundary

┌─────────────────────────────────────────────────────────────┐
│                 Safe vs. Dangerous Medical AI               │
│                                                             │
│  ❌ DANGEROUS USE CASES (Do Not Outsource to AI):           │
│  • Diagnosing chest pain, acute abdominal pain, or rashes   │
│  • Adjusting prescription medication dosages                │
│  • Deciding whether to skip emergency medical care          │
│                                                             │
│  ✅ SAFE, HIGH-LEVERAGE USE CASES (Literacy & Prep):        │
│  • Translating lab report acronyms (e.g. eGFR, ALT, MCV)    │
│  • Understanding standard anatomical terminology            │
│  • Generating a prioritized list of questions for your doctor│
└─────────────────────────────────────────────────────────────┘

Master Health Literacy Prompt Templates

Pattern 1: The Lab Report Jargon Translator

Use to demystify complex lab results before your doctor appointment:

Here is a line from my lab report:
"[PASTE SPECIFIC LAB TEST NAME & REFERENCE RANGE]"

Task:
1. Explain what [TEST NAME] measures in plain English using a simple biological analogy.
2. What is the standard purpose of this test in routine checkups?
3. Generate 2 clear, informed questions I can ask my physician during my follow-up appointment.

Do NOT attempt to diagnose my health or tell me if I have a disease.

Read the full file on GitHub · 104 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday Changed · -9 tokens per session bf4f81dd71b6
  2. 7d ago First seen · 104 lines · 37 tokens per session scan A 55eaa52757ae

Subscribe to this mod's changes

dont-trust-ai-medical-diagnoses is a skill published in the GitHub repository alivirgo/Major-AI-Skills (1 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 1,061 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.

Related

Other skills, from other repositories

andrej-karpathy-v2

ANDREJ KARPATHY — SKILL COMPLETA v2.0 workflow skill. Use this skill when the user needs Agente que simula Andrej Karpathy — ex-Director of AI da Tesla, co-fundador da OpenAI, fundador da Eureka Labs, e o maior educador de deep learning do mundo and the operator should preserve the upstream workflow, copied support…

diegosouzapw/awesome-omni-skills · 94 tokens

ai-engineering-toolkit

AI Engineering Toolkit workflow skill. Use this skill when the user needs 6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching and the operator…

diegosouzapw/awesome-omni-skills · 81 tokens

azure-lab-services

Expert knowledge for Azure Lab Services development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when configuring lab plans, VM templates/schedules, VNet-integrated labs…

MicrosoftDocs/Agent-Skills · 115 tokens

azure-education-hub

Expert knowledge for Azure Education Hub development including troubleshooting, and limits & quotas. Use when managing Azure for Students credits, yearly quotas, renewals, or Dev Tools for Teaching sign-in issues, and other Azure Education Hub related development tasks. Not for Azure Lab Services (use…

MicrosoftDocs/Agent-Skills · 88 tokens

andrej-karpathy

ANDREJ KARPATHY — SKILL COMPLETA v2.0 workflow skill. Use this skill when the user needs Agente que simula Andrej Karpathy — ex-Director of AI da Tesla, co-fundador da OpenAI, fundador da Eureka Labs, e o maior educador de deep learning do mundo and the operator should preserve the upstream workflow, copied support…

diegosouzapw/awesome-omni-skills · 92 tokens

ai-content-filter

Professional Ai Content Filter Expert skill. Integrate LLM API workflows, safe system prompt guidelines, and agentic workflows.

AtulPurohit/Antigravity-Awesome-Skills · 28 tokens