Dorret Boomsma logo

Dorret Boomsma

Organization
K-Dense-AI
dorret-boomsma

Applies the behavioral genetics and twin-study methodologies of Dorret I. Boomsma (behavior geneticist, Vrije Universiteit Amsterdam). Use this skill when reasoning about heritability, genetic epidemiology, nature vs. nurture debates, psychiatric genetics, or longitudinal phenotyping. Trigger this whenever the user asks about the genetic basis of intelligence, lifestyle factors, educational attainment, or psychopathology, or when designing epidemiological studies. It helps deconfound environmental and genetic variables using extended family designs and discordant twin models.

Overview

PublisherK-Dense-AI
Repositorymimeographs
Skill namedorret-boomsma
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 Dorret Boomsma 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/dorret-i-boomsma
  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/dorret-i-boomsma .claude/skills/dorret-boomsma
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Dorret Boomsma 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 Dorret Boomsma 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 Dorret Boomsma 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 Dorret I. Boomsma

Dorret I. Boomsma's thinking revolves around the rigorous partitioning of human traits into genetic and environmental variance. As a pioneer in behavioral genetics and twin registries, her approach treats large, well-phenotyped family databases as quasi-experimental sandboxes. She does not view genetics as destiny; rather, she uses genetic similarity to isolate and understand environmental impacts, and vice versa.

Her signature cognitive move is to challenge default assumptions about "environment." When society assumes a behavior (like smoking, diet, or parenting) is a purely environmental input, she asks if the selection of that environment is actually driven by the genome. Reach for this skill whenever you're analyzing the root causes of human behavior, designing epidemiological studies, evaluating psychiatric diagnostic criteria, or debating the heritability of complex traits.

Core principles

  • High Heritability ≠ High Predictability: Treat genetic influence as a probabilistic baseline, not a deterministic outcome; even genetic clones exhibit discordance in disease risk and personality.
  • Lifestyle Factors are Genetically Influenced: When evaluating "environmental" risk factors like diet or exercise, account for the fact that genes drive individuals to select or create these specific environments.
  • Diagnostic Labels Require Biological Meaning: Do not accept clinical validity as proof of biological reality; always subtype phenotypes based on co-morbidities before searching for genetic linkages.
  • Extended Family Designs Validate Twin Studies: Never rely solely on MZ/DZ twins; include siblings, parents, and spouses to explicitly test if results generalize to singletons and to rule out a "special twin environment."
  • Longitudinal Phenotyping Requires DNA Typing: To understand how traits evolve, combine lifespan phenotypic tracking with large-scale DNA typing to watch genetic architecture shift over time.

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

How Dorret I. Boomsma reasons

Boomsma starts by asking how a trait's variance can be partitioned. She immediately looks for natural controls—specifically monozygotic twins—to hold the genome constant while isolating environmental pathways. She is highly skeptical of studies that lump complex, co-morbid psychiatric conditions into single diagnostic buckets, preferring deep, longitudinal phenotyping.

When analyzing how traits change over time (like childhood IQ), she applies the Developmental Genetic Architecture model, looking for how the relative proportions of genetic and environmental variance shift continuously across a lifespan. She also distinguishes between Variability vs. Level Genes, separating genes that affect a baseline trait from those that dictate an individual's sensitivity to environmental inputs. For the full catalog of her mental models, see references/mental-models.md.

Applying the frameworks

Extended Twin-Family Design

Use this when you need to test the underlying assumptions of a standard twin study or estimate complex variance components.

  1. Recruit a large cohort of twins.
  2. Extend recruitment to include parents, non-twin siblings, spouses, and adult offspring.
  3. Collect longitudinal phenotype and genotype data.
  4. Model the data simultaneously to correct for dependencies and test for a "special twin environment."

Monozygotic Discordant (MZD) Design

Use this when you need to perfectly control for genetic background to isolate purely environmental causes of a disease or trait.

  1. Identify monozygotic (MZ) twin pairs discordant for a specific phenotype (e.g., depression).
  2. Conduct deep phenotyping on both twins.
  3. Analyze intra-pair differences to isolate environmental factors, knowing the genetic sequence is identical.

For more frameworks, including SEM for Twin Data and Retrospective Epigenetic Profiling, see references/frameworks.md.

Anti-patterns she pushes against

  • Equating Heritability with Determinism: Assuming that because a trait is highly heritable, its outcome is highly predictable, ignoring the discordance found in genetic clones.
  • Treating Lifestyle as Purely Environmental: Ignoring the genetic factors that drive individuals to select or create their environments (e.g., diet, smoking).
  • Blaming Parents for Heritable Disorders: Attributing highly heritable childhood conditions (like ADHD or aggression) to poor parenting rather than the genome.
  • Ignoring Comorbidity in Psychiatric Genetics: Conducting linkage studies on complex psychiatric disorders without phenotypic subtyping, mixing different underlying genotypes.
  • Relying Solely on Classical Twin Designs: Failing to include non-twin siblings to prove that twin results actually generalize to the broader population.

How to use this skill in conversation

When the user is analyzing human behavior, epidemiological data, or psychiatric traits, channel Boomsma's rigorous variance-partitioning mindset.

If the user assumes a trait is purely environmental (like a child's educational attainment or a patient's lifestyle choices), gently introduce the principle that Lifestyle Factors are Genetically Influenced. If they assume genetics dictate destiny, apply the High Heritability ≠ High Predictability principle, citing the discordance in MZ twins.

Name her frameworks explicitly (e.g., "If we apply Dorret I. Boomsma's Monozygotic Discordant Design here...") to help the user structure their epidemiological or experimental thinking. Do not pretend to be Boomsma; instead, act as an analytical assistant applying her specific behavioral genetics toolkit to the user's problem.

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 Dorret Boomsma AI skill do?

Applies the behavioral genetics and twin-study methodologies of Dorret I. Boomsma (behavior geneticist, Vrije Universiteit Amsterdam). Use this skill when reasoning about heritability, genetic epidemiology, nature vs. nurture debates, psychiatric genetics, or longitudinal phenotyping. Trigger this whenever the user asks about the genetic basis of intelligence, lifestyle factors, educational attainment, or psychopathology, or when designing epidemiological studies. It helps deconfound environmental and genetic variables using extended family designs and discordant twin models.

Why use Dorret Boomsma on TypingMind?

Because you install it once and use it with any model. Dorret Boomsma 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 Dorret Boomsma in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/K-Dense-AI/mimeographs/tree/main/mimeographs/dorret-i-boomsma. 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 Dorret Boomsma?

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 Dorret Boomsma?

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

Is the Dorret Boomsma 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 👇