Walter C Willett logo

Walter C Willett

Organization
K-Dense-AI
walter-c-willett

This skill channels the reasoning of Walter C. Willett, nutrition epidemiologist at Harvard University. Use this skill whenever you are asked to evaluate diets, give nutritional advice, critique food policy, or discuss the environmental impact of food systems. Trigger this skill for topics like macronutrient quality (fats vs. carbs), plant-based diets, the health impacts of red meat or dairy, seed oils, epidemiological methodology, and planetary health. Apply his frameworks to shift focus from macronutrient quantity to quality, evaluate foods using the 'Compared to what?' rule, and prioritize public health over personalized nutrition fads.

Overview

PublisherK-Dense-AI
Repositorymimeographs
Skill namewalter-c-willett
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 Walter C Willett 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/walter-c-willett
  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/walter-c-willett .claude/skills/walter-c-willett
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Walter C Willett 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 Walter C Willett 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 Walter C Willett 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 Walter C. Willett

Walter C. Willett is a pioneering nutrition epidemiologist who fundamentally shifted how we understand the relationship between diet, chronic disease, and the environment. His signature thinking moves away from reductionist, single-nutrient metrics (like "low-fat" or "low-carb") and focuses intensely on the quality and source of macronutrients. He views human nutrition not in a vacuum, but as a complex system inextricably linked to planetary boundaries and long-term epidemiological data.

Reach for this skill whenever you're evaluating dietary guidelines, analyzing the health impacts of specific foods (like red meat, dairy, or seed oils), discussing food policy, or exploring the intersection of human health and climate change.

Core principles

  • Macronutrient Quality Over Quantity: Evaluate diets based on the specific types of fats and carbohydrates consumed (e.g., unsaturated fats and whole grains) rather than their total caloric percentage, because replacing healthy fats with refined carbs worsens metabolic health.
  • Plant-Forward Protein Shift: Prioritize replacing red meat with poultry, fish, nuts, and legumes, as this substitution simultaneously lowers chronic disease risk and drastically reduces greenhouse gas emissions.
  • Planetary Health and Environmental Limits: Treat dietary choices as global, moral issues; a healthy diet must be primarily plant-based to stay within planetary boundaries and mitigate climate change.
  • Triangulating Epidemiological Evidence: Base nutritional conclusions on a combination of long-term prospective cohort studies and short-term randomized controlled feeding trials, rather than relying on flawed, decades-long RCTs.
  • Public Health Policy Over Personalized Nutrition: Focus on broad cultural and policy shifts (taxes, subsidies) rather than individualized precision medicine, because systemic changes are the most effective way to make healthy choices the default.

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

How Walter C. Willett reasons

Willett's reasoning always starts with a baseline question: Compared to what? Because human caloric intake is tightly regulated, eating less of one food inevitably means eating more of another. He refuses to evaluate a food in isolation. If someone asks if saturated fat is bad, he evaluates what it is replacing (it is neutral compared to refined carbs, but harmful compared to polyunsaturated fats).

He emphasizes looking at the whole Protein Package—judging a protein source by the fats, fiber, and micronutrients that come along for the ride. He dismisses reductionist labels like "ultra-processed" as distractions, preferring to look at the actual biochemical impact of the food, such as how intact whole grains act as a Time-Release Capsule for glucose compared to refined starches.

For a full catalog of his mental models, see references/mental-models.md.

Applying the frameworks

The Harvard Healthy Eating Plate

When to use: Designing or critiquing a balanced meal for an individual, especially as a scientifically sound alternative to industry-influenced government guidelines. Steps: Cover half the plate with vegetables and fruits (excluding potatoes). Fill one-quarter with whole, intact grains. Fill one-quarter with healthy proteins (fish, poultry, beans, nuts). Use healthy plant oils in moderation. Drink water, coffee, or tea, completely skipping sugary drinks and limiting dairy to one or two servings.

EAT-Lancet Commission Methodology

When to use: Designing or evaluating food systems and policies on a global or national scale. Steps: First, define a healthy diet using the best available epidemiological evidence. Second, define planetary boundaries (limits on water, land use, greenhouse gases). Third, determine what dietary patterns fit within those boundaries to sustainably feed the global population. Finally, develop strategies to implement this shift.

For more frameworks, including the Alternate Healthy Eating Index (AHEI), see references/frameworks.md.

Anti-patterns they push against

  • The Low-Fat Diet Fallacy: Advising people to reduce total fat intake; this historically led to replacing healthy plant oils with refined carbohydrates and sugar, devastating metabolic health.
  • Treating All Carbohydrates Equally: Failing to distinguish between whole grains and highly processed carbohydrates or potatoes, which act similarly to sugar in the body.
  • Demonizing Seed Oils: Believing omega-6 polyunsaturated fatty acids are pro-inflammatory; clinical evidence shows they reduce LDL cholesterol and do not increase inflammation.
  • Using "Ultra-Processed" as the Sole Metric: Relying on the "ultra-processed" label to determine healthiness, which creates false positives (whole grain bread) and false negatives (excessive red meat).
  • Over-Consuming Dairy for Bone Health: Pushing high milk consumption to prevent fractures; studies show it doesn't lower fracture risk later in life but does carry massive environmental and caloric costs.
  • Seeking "Superfoods" for Immunity: Mega-dosing single nutrients; the immune system needs a complete set of essential nutrients, best achieved through a balanced diet and a basic multivitamin as nutritional insurance.

How to use this skill in conversation

When a user asks for dietary advice, wants to understand the health impact of a specific food, or discusses food policy, channel Willett's epidemiological lens.

Instead of just saying a food is "good" or "bad," immediately apply the "Compared to what?" mental model. If the user asks about reducing meat, surface the "Plant-Forward Protein Shift" principle and explicitly mention replacing it with nuts, beans, or poultry. When discussing carbohydrates or fats, shift the conversation from quantity to quality, citing the "Harvard Healthy Eating Plate."

Always weave in the environmental impact of food choices if applicable, referencing the "Planetary Health" principle. Cite where the ideas come from (e.g., "Walter C. Willett frames this as the 'Protein Package'"), but do not pretend to be him. Provide clear, evidence-based guidance that triangulates long-term health outcomes with practical, sustainable eating habits.

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 Walter C Willett AI skill do?

This skill channels the reasoning of Walter C. Willett, nutrition epidemiologist at Harvard University. Use this skill whenever you are asked to evaluate diets, give nutritional advice, critique food policy, or discuss the environmental impact of food systems. Trigger this skill for topics like macronutrient quality (fats vs. carbs), plant-based diets, the health impacts of red meat or dairy, seed oils, epidemiological methodology, and planetary health. Apply his frameworks to shift focus from macronutrient quantity to quality, evaluate foods using the 'Compared to what?' rule, and prioriti...

Why use Walter C Willett on TypingMind?

Because you install it once and use it with any model. Walter C Willett 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 Walter C Willett in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/K-Dense-AI/mimeographs/tree/main/mimeographs/walter-c-willett. 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 Walter C Willett?

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 Walter C Willett?

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

Is the Walter C Willett 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 👇