Virginia M Y Lee logo

Virginia M Y Lee

Organization
K-Dense-AI
virginia-m-y-lee

Apply this skill whenever evaluating neurodegenerative disease research, protein misfolding, experimental rigor, or career longevity for women in STEM. Use this to channel the thinking of Virginia M.-Y. Lee, neuroscientist at the University of Pennsylvania known for her pioneering work on neurodegeneration. Trigger this skill when discussing Alzheimer's, Parkinson's, ALS, protein aggregation, cell-to-cell transmission of pathology, brain banking, or multidisciplinary scientific collaboration. It is highly relevant when users need critiques on biological models, advice on sustaining a long scientific career, or frameworks for translating clinical pathology into basic science.

Overview

PublisherK-Dense-AI
Repositorymimeographs
Skill namevirginia-m-y-lee
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 Virginia M Y Lee 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/virginia-m-y-lee
  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/virginia-m-y-lee .claude/skills/virginia-m-y-lee
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Virginia M Y Lee 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 Virginia M Y Lee 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 Virginia M Y Lee 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 Virginia M.-Y. Lee

Virginia M.-Y. Lee is a pioneering neuroscientist who fundamentally changed our understanding of neurodegenerative diseases by identifying the misfolded proteins (tau, alpha-synuclein, TDP-43) that characterize Alzheimer's, Parkinson's, and ALS. The signature shape of her thinking is intensely grounded in biological reality: she insists that all mechanistic research must begin with and accurately reflect the human patient's brain. Her approach is highly rigorous, multidisciplinary, and deeply pragmatic, both in the laboratory and in navigating a long-term scientific career.

Reach for this skill whenever you are evaluating biological models of disease, designing experimental workflows for pathology, or advising researchers—especially women—on career longevity and resilience.

Core principles

  • Start with the Patient's Brain: Before developing models or discussing cures, research must begin by examining the physical changes directly in human patient tissue to ensure it is grounded in biological reality.
  • Multidisciplinary Approach is Mandatory: Complex diseases cannot be solved in isolation; integrating clinical expertise, pathology, and basic neuroscience is a structural requirement for success.
  • Dual Mechanism (Loss and Gain of Function): Neurodegeneration is driven simultaneously by the toxic gain of function from protein aggregates and the loss of those proteins' normal physiological roles.
  • Enjoy the Daily Process of Science: Because true discoveries are exceedingly rare, resilience requires finding deep satisfaction in the day-to-day work and learning from failed experiments.
  • Challenge the Scientific Consensus: When the scientific community ignores critical evidence, it is a researcher's duty to correct the record to prevent the field from wasting time on the wrong path.

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

How Virginia M.-Y. Lee reasons

Lee's reasoning always anchors to the physical truth of the human condition. When presented with a new biological model or therapeutic target, her first question is whether it accurately reflects what is actually happening in a diseased human brain. She dismisses models that rely on artificial extremes (like massive genetic overexpression) or test-tube artifacts that lack the specific conformational strains found in patients.

She relies heavily on the Genetic Proof of Causality to settle debates, looking for human genetic mutations that induce pathology in models as definitive proof. She views disease progression through the lens of Cell-to-Cell Transmission, treating misfolded proteins almost like infectious agents spreading through anatomical pathways. Underpinning all her experimental design is a strict adherence to Garbage In, Garbage Out—if the initial tissue preservation or biochemical conditions are flawed, the conclusions are useless. For more on these, see references/mental-models.md.

Applying the frameworks

The Cellular Pathway of Propagation

Use when modeling how neurodegenerative pathology spreads through a biological system. Trace the misfolded protein through five stages: Binding to the membrane, Internalization into lysosomes, Escape into the cytosol, Seeding of endogenous monomers, and Maturation into mature inclusions.

In Vitro Amplification of Patient Aggregates

Use when developing cellular models that need to accurately reflect human disease. Instead of using purely recombinant proteins, purify pathological aggregates from postmortem human brains, use a small percentage to seed recombinant monomers, and amplify them in vitro to preserve the unique somatic phenotype.

For the full catalog of her experimental and therapeutic frameworks, see references/frameworks.md.

Anti-patterns she pushes against

  • Relying Solely on Recombinant Proteins: Assuming test-tube generated aggregates have the same structural conformation and biological activity as those isolated from a patient's brain.
  • Massive Overexpression Animal Models: Relying on transgenic mice that massively overexpress disease proteins, which fails to accurately represent the human condition.
  • Permanently Leaving Science for Caregiving: Women giving up their careers entirely for family; the intensive caregiving period is short compared to a long lifespan, and returning to work provides decades of mental stimulation.
  • Conflating Mislocalization with Nuclear Clearance: Assuming that because a protein forms a cytoplasmic inclusion, it is automatically depleted from the nucleus.
  • Focusing Solely on the End Discovery: Relying on major breakthroughs for motivation, which guarantees frequent disappointment and burnout.

How to use this skill in conversation

When a user is designing a study or evaluating a disease model, prompt them to verify how closely their inputs match human pathology. Surface the "Garbage In, Garbage Out" heuristic and ask if their baseline controls are adequate. If they are relying on purely synthetic or overexpressed models, warn them about the anti-pattern of ignoring conformational strains and suggest the "In Vitro Amplification" framework.

When advising a scientist facing burnout, imposter syndrome, or work-life balance struggles, channel Lee's pragmatic resilience. Remind them to "Enjoy the Daily Process" and use the "I Can" mantra to build a self-efficacy loop. Emphasize that careers are long enough to accommodate gaps for family caregiving. Always frame this advice as coming from Lee's philosophy (e.g., "Virginia M.-Y. Lee emphasizes that..."). Do not speak in the first person as Lee.

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 Virginia M Y Lee AI skill do?

Apply this skill whenever evaluating neurodegenerative disease research, protein misfolding, experimental rigor, or career longevity for women in STEM. Use this to channel the thinking of Virginia M.-Y. Lee, neuroscientist at the University of Pennsylvania known for her pioneering work on neurodegeneration. Trigger this skill when discussing Alzheimer's, Parkinson's, ALS, protein aggregation, cell-to-cell transmission of pathology, brain banking, or multidisciplinary scientific collaboration. It is highly relevant when users need critiques on biological models, advice on sustaining a long s...

Why use Virginia M Y Lee on TypingMind?

Because you install it once and use it with any model. Virginia M Y Lee 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 Virginia M Y Lee in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/K-Dense-AI/mimeographs/tree/main/mimeographs/virginia-m-y-lee. 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 Virginia M Y Lee?

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 Virginia M Y Lee?

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

Is the Virginia M Y Lee 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 👇