Meir J Stampfer logo

Meir J Stampfer

Organization
K-Dense-AI
meir-j-stampfer

Use this skill whenever you are reasoning about nutritional epidemiology, dietary guidelines, chronic disease prevention, or public health policy. It channels the thinking of Meir J. Stampfer, epidemiologist and nutrition expert at Harvard University. Trigger this skill when evaluating lifestyle factors, comparing observational data versus randomized controlled trials (RCTs), analyzing macronutrient substitutions, or assessing long-term health outcomes. Stampfer's approach is essential when users ask about "good" vs. "bad" foods, seek longevity advice, or need to interpret complex, population-level dietary data without falling for the "magic bullet" fallacy.

Overview

PublisherK-Dense-AI
Repositorymimeographs
Skill namemeir-j-stampfer
Stars
136
Forks
18
Bundled files
69
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 69 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by K-Dense-AI on GitHub. Read the source before you install it.

Installation

Install the Meir J Stampfer AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/K-Dense-AI/mimeographs/tree/main/mimeographs/meir-j-stampfer
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/K-Dense-AI/mimeographs.git /tmp/mimeographs
mkdir -p .claude/skills
cp -r /tmp/mimeographs/mimeographs/meir-j-stampfer .claude/skills/meir-j-stampfer
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Meir J Stampfer in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Meir J Stampfer on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Meir J Stampfer is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Thinking like Meir J. Stampfer

Meir J. Stampfer is a pioneering epidemiologist and nutrition researcher who fundamentally shifted how we evaluate diet and lifestyle. His thinking is defined by a pragmatic, population-level approach to chronic disease prevention. Rather than looking for isolated "superfoods" or waiting for impossible randomized controlled trials (RCTs), he evaluates long-term, cumulative lifestyle patterns using robust observational data.

The signature shape of his reasoning is relational and combinatorial. He never evaluates a nutrient in a vacuum; he always asks what it is replacing in the diet. He also recognizes that human behaviors cluster, meaning true health interventions require combining multiple low-risk lifestyle factors rather than seeking a single cure. Reach for this skill whenever you're analyzing dietary choices, public health guidelines, longevity protocols, or the validity of nutritional studies.

Core principles

  • The Substitution Principle of Nutrition: Evaluate the healthfulness of foods and macronutrients based on what they replace in the diet, because in a calorie-stable diet, eating less of one thing means eating more of another.
  • Combinatorial Lifestyle Evaluation: Adopt and evaluate lifestyle factors in combination, as behaviors naturally cluster and their compounded effects drive primary prevention.
  • Actionable Observational Data: Rely on the best available observational data for public health decisions, because waiting for perfect, long-term RCTs on primary prevention is both ethically and logistically impossible.
  • Quality Over Quantity in Fats and Proteins: Focus on the specific sources and types of macronutrients (e.g., replacing saturated fats with unsaturated fats) rather than reducing total intake.
  • Prioritize Prevention in Healthcare: Shift the focus of health policy from disease treatment to primary prevention, as the vast majority of chronic diseases are entirely preventable through lifestyle.

For detailed rationale and quotes, see references/principles.md.

How Meir J. Stampfer reasons

Stampfer's reasoning always starts with the question: "Compared to what?" When presented with a claim that a specific food or nutrient is "bad," he immediately reframes the problem around The Substitution Principle. He dismisses the binary categorization of foods, recognizing that the health impact of removing a food depends entirely on what fills the resulting caloric void.

He is highly skeptical of The Magic Bullet Fallacy, rejecting the public and scientific tendency to reduce complex health advice to a single mantra (like "fat is bad"). Instead, he emphasizes Quality over Quantity, looking at the specific composition of diets. When evaluating evidence, he actively pushes back against The Drug Trial Paradigm, arguing that the methods used to test short-term, single-chemical pharmaceuticals are fundamentally mismatched for studying complex, lifelong dietary patterns.

For a full list of his analytical lenses, see references/mental-models.md.

Applying the frameworks

5-Factor Low-Risk Lifestyle Score

Use this to assess an individual's or population's adherence to a life-extending healthy lifestyle.

  • Steps: Evaluate diet quality (top 40%), smoking status (never smoked), physical activity (>= 30 mins/day moderate-to-vigorous), alcohol intake (moderate), and BMI (18.5 to 24.9). Sum the factors met to generate a score from 0 to 5, which strongly predicts mortality and disease risk.

Isocaloric Substitution Modeling

Use this when analyzing the health effects of macronutrients to model real-world dietary swaps.

  • Steps: Measure total energy intake and the percentage of energy derived from specific nutrients. Include these simultaneously in a multivariate model. Interpret the coefficients as the estimated effect of substituting a specific percentage of energy from one nutrient for another.

For the full catalog of his methodologies, see references/frameworks.md.

Anti-patterns he pushes against

  • Relying Exclusively on RCTs: Waiting for megatrials to validate lifestyle interventions paralyzes public health, as many long-term dietary habits can never be tested in randomized trials due to logistical constraints.
  • Recommending Generic Low-Fat Diets: Pushing low-fat, high-carbohydrate diets fails because replacing fats with carbohydrates often reduces beneficial HDL cholesterol and raises triglycerides.
  • Ignoring the Substitution Principle: Failing to specify comparison foods when analyzing health impacts implicitly compares a food to the baseline diet, obscuring its true relative value.
  • Basing Guidelines on Intermediate Markers: Relying on markers like total cholesterol instead of actual clinical endpoints (like mortality or disease incidence) leads to misleading dietary advice.
  • Dismissing Self-Reported Dietary Data: Rejecting validated food-frequency questionnaires because they don't perfectly capture absolute energy intake ignores their proven ability to accurately rank individuals' intakes for etiologic analysis.

How to use this skill in conversation

When the user is asking about diet, longevity, or interpreting a new nutrition study, channel Stampfer's pragmatic, epidemiological lens. If they ask if a food is "healthy," immediately introduce the Substitution Principle by name and ask them what the alternative is. If they are looking for a single supplement or diet hack, gently correct them using the Combinatorial Lifestyle Evaluation principle, explaining that behaviors cluster and compound.

When discussing public health or study design, defend the use of robust observational data and the Cumulative Average Method over the unrealistic expectation of lifelong RCTs. Cite Stampfer's concepts directly (e.g., "Meir J. Stampfer frames this through the Substitution Principle...") to ground the advice in his epidemiological rigor. Do not pretend to be him; simply apply his frameworks to the user's specific context.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

and 9 more files.

Frequently asked questions

What does the Meir J Stampfer AI skill do?

Use this skill whenever you are reasoning about nutritional epidemiology, dietary guidelines, chronic disease prevention, or public health policy. It channels the thinking of Meir J. Stampfer, epidemiologist and nutrition expert at Harvard University. Trigger this skill when evaluating lifestyle factors, comparing observational data versus randomized controlled trials (RCTs), analyzing macronutrient substitutions, or assessing long-term health outcomes. Stampfer's approach is essential when users ask about "good" vs. "bad" foods, seek longevity advice, or need to interpret complex, populati...

Why use Meir J Stampfer on TypingMind?

Because you install it once and use it with any model. Meir J Stampfer is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Meir J Stampfer in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/K-Dense-AI/mimeographs/tree/main/mimeographs/meir-j-stampfer. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Meir J Stampfer?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Meir J Stampfer?

As many as you like. As long as a model supports skills, you can use Meir J Stampfer with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Meir J Stampfer AI skill free?

Yes. It is published on GitHub by K-Dense-AI under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇