New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Judea Pearl

by K-Dense-AI in K-Dense-AI/mimeo

Applies Judea Pearl's causal reasoning frameworks to distinguish correlation from causation, evaluate AI capabilities, and make counterfactual decisions.

MITAuto-check passedResearch & Science

Install Judea Pearl

skills CLI
$ npx skills add K-Dense-AI/mimeo --skill judea-pearl -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install K-Dense-AI/mimeo judea-pearl --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/K-Dense-AI/mimeo.git skills-src && mkdir -p .claude/skills && cp -r skills-src/output/judea-pearl .claude/skills/judea-pearl && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
judea-pearl
GitHub stars
282
Token cost
~1.7k tokens
SKILL.md length
809 words
Files
10 (incl. references)
Skills in repo
21
Repo updated
First seen
Licence
MIT

At a glance

Applies Judea Pearl's causal reasoning frameworks to distinguish correlation from causation, evaluate AI capabilities, and make counterfactual decisions.

  • Works in 3 steps: Association (Observation): "What is?"… → Intervention (Action): "What if I do X?"… → Counterfactuals (Retrospection): "What…
  • This skill for topics involving Bayesian networks
  • SKILL.md covers Core principles, How Judea Pearl reasons, Applying the frameworks and Anti-patterns he pushes against, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Judea Pearl is an agent skill from K-Dense-AI/mimeo. Applies Judea Pearl's causal reasoning frameworks to distinguish correlation from causation, evaluate AI capabilities, and make counterfactual decisions. Reach for this skill whenever Claude encounters questions about causal inference, structural causal models, the limitations of deep learning, AGI, experimental design, covariate selection, or personalized decision-making. Trigger this skill for topics involving Bayesian networks, the do-calculus, the Ladder of Causation, or when a user tries to answer 'what if'…

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 10 other files, including reference files (for example `AGENTS.md`, `references/anti-patterns.md` and `references/frameworks.md`).

It sits in Research & Science, covering Deep learning, Experimental design and Econometrics and empirical research. The repository describes itself as: Mimeograph an expert into a SKILL.md or AGENTS.md for your agent. The licence is MIT.

When your agent uses it

  • This skill for topics involving Bayesian networks
  • The do-calculus
  • The Ladder of Causation
  • A user tries to answer what if

Example prompts

  • “what if”
  • “questions using purely observational data. Pearl”
  • “Use the judea-pearl skill to apply Judea Pearl's causal reasoning frameworks to distinguish correlation from causation, evaluate AI capabilities…”
  • “/judea-pearl”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Association (Observation): "What is?" (Handled by standard statistics/deep learning).
  2. Intervention (Action): "What if I do X?" (Requires causal models and the do(x) operator).
  3. Counterfactuals (Retrospection): "What if I had done X instead?" (Requires structural causal models).

What it can do on your machine

Read from SKILL.md and the folder at commit a4cea18. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • arxiv.org

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Judea Pearl loads about 1.7k tokens when it runs, and up to ~9.2k if it reads all its reference files. Until then it costs about 171 tokens; SKILL.md has 809 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~171
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~9.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from K-Dense-AI/mimeo at commit a4cea18, republished under its MIT licence (© K-Dense-AI). 809 words, ~1,661 tokens.

Download SKILL.mdSave it as .claude/skills/judea-pearl/SKILL.md (or your agent's skills folder). This skill also uses 9 other files; get the full folder from GitHub.
name
judea-pearl
description
Applies Judea Pearl's causal reasoning frameworks to distinguish correlation from causation, evaluate AI capabilities, and make counterfactual decisions. Reach for this skill whenever Claude encounters questions about causal inference, structural causal models, the limitations of deep learning, AGI, experimental design, covariate selection, or personalized decision-making. Trigger this skill for topics involving Bayesian networks, the do-calculus, the Ladder of Causation, or when a user tries to answer 'what if' or 'why' questions using purely observational data. Pearl's principles are essential for moving beyond probability calculus into true causal understanding.

Thinking like Judea Pearl

Judea Pearl is a Turing Award-winning computer scientist and philosopher who revolutionized artificial intelligence and statistics by developing the mathematics of causal inference. His signature thinking style rejects the "Babylonian" approach of model-blind data fitting in favor of "Greek" science: building explicit, transparent causal models that explain the underlying mechanisms of reality. He insists that data alone is fundamentally dumb; it can only tell us about associations. To answer "what if" or "why" questions, we must step outside probability calculus and introduce causal assumptions.

Reach for this skill whenever you're evaluating AI capabilities, designing experiments, selecting covariates for statistical analysis, or making personalized decisions that require counterfactual reasoning.

Core principles

  • AI Requires Causal World Models: True intelligence cannot emerge from model-blind machine learning; it requires integrating causal models to predict interventions and imagine counterfactuals.
  • Insufficiency of Probability Calculus: Standard probability is symmetrical and cannot express directional causal facts; new mathematical operators like do(x) are required.
  • The Necessity of Untested Causal Assumptions: Every causal conclusion from observational data must rely on causal assumptions that cannot be tested by the data alone.
  • Missing Links Encode Assumptions: In causal path diagrams, the strong empirical claims are encoded in the missing links (claiming zero influence), not the present ones.

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

How Judea Pearl reasons

Pearl always begins by drawing a line between the associational (what is observed) and the causal (what is done or imagined). He asks: "Where is the causal model?" He dismisses attempts to answer causal questions using purely statistical techniques like propensity score matching or deep learning without an explicit structural model. He views causal diagrams not just as pictures, but as rigorous inference engines that automatically compute the logical implications of our assumptions.

He relies heavily on The Demarcation Line to separate statistics from causality, and views Causal Models as Parsimonious Encodings of reality. For more on his cognitive tools, see references/mental-models.md.

Applying the frameworks

The Ladder of Causation

Use this to categorize the complexity of a user's question and determine if causal tools are required.

  1. Association (Observation): "What is?" (Handled by standard statistics/deep learning).
  2. Intervention (Action): "What if I do X?" (Requires causal models and the do(x) operator).
  3. Counterfactuals (Retrospection): "What if I had done X instead?" (Requires structural causal models).
The General Methodology for Causal Inference

Use this four-step procedure for tackling any causal problem.

  1. Define the causal problem and target quantities.
  2. Assume the causal relationships (via diagrams).
  3. Identify if the target can be computed from observed data given the assumptions.
  4. Estimate the identified quantity from the data.
The Back-door Criterion

Use this graphical rule to select a sufficient set of covariates for adjustment.

  1. Ensure no element in the adjustment set is a descendant of the treatment.
  2. Ensure the set blocks all "back-door" paths from treatment to outcome.

For the full catalog, including Do-calculus and Selection Diagrams, see references/frameworks.md.

Show full SKILL.md (319 more words)Show less

Anti-patterns he pushes against

  • Answering Causal Questions with Data Alone: Attempting to derive causal conclusions without articulating causal assumptions.
  • Scaling LLMs to Achieve AGI: Believing that scaling model-blind architectures will yield true intelligence.
  • Blindly Applying Propensity Scores: Assuming propensity scores always reduce bias without mapping the causal structure (e.g., the M-graph).
  • Hiding Assumptions Under the Rug: Keeping assumptions implicit to avoid criticism, which hinders scientific progress.

For the full catalog with rationale and quotes, see references/anti-patterns.md.

Heuristics and rules of thumb

  • The Associational Test: If a concept can be defined entirely by a joint distribution, it is associational; if not, it is causal.
  • Missing Links Encode Assumptions: Look to the missing arrows in a graph to find the testable claims.
  • No Guesswork in Covariates: Never guess which variables to control for; map the causal relationships first.
  • Translate Intuition into Math: Formalize intuition into mathematics to amplify it.

See references/heuristics.md for the full list with attribution.

How to use this skill in conversation

When a user asks about the impact of an action, the cause of an event, or the capabilities of AI, channel Pearl's insistence on explicit causal models.

  • If they are trying to solve a causal problem with purely statistical tools (like deep learning or standard regression), point out the "Demarcation Line" and explain why probability calculus is insufficient.
  • If they are confused about which variables to control for, introduce the "Back-door Criterion" and ask them to define their causal graph.
  • Frame AI limitations using the "Ladder of Causation," explaining that LLMs operate at Level 1 (Association) while true reasoning requires Levels 2 and 3.
  • Avoid impersonation. Do not pretend to be Judea Pearl. Instead, say things like, "Judea Pearl's framework suggests..." or "Applying the rules of do-calculus here reveals..."

Generated with mimeo. If this material contributes to published work, please cite Kassis, T. (2026). "mimeo: Compiling Public Expert Corpora into Agent Skills and Testing What Transfers." arXiv:2609.00453.

© K-Dense-AI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 9 other files (references) in output/judea-pearl of K-Dense-AI/mimeo.

  • SKILL.md
  • AGENTS.md
  • avatar.png
  • references/anti-patterns.md
  • references/frameworks.md
  • references/heuristics.md
  • references/mental-models.md
  • references/principles.md
  • references/quotes.md
  • references/sources.md

Open the folder on GitHubat commit a4cea18

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders. This page covers the copy in K-Dense-AI/mimeo, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Judea Pearl next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Judea Pearl compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Judea Pearl this skillK-Dense-AI/mimeo282—~1.7kAutomated safety check: PassMIT
Causalai-analyst-lab/ai-analyst304—~1.8kAutomated safety check: PassMIT
Fin Experiment Designcsmar432/finai-research109—~4.2kAutomated safety check: PassMIT
Academic Paper Verifybrycewang-stanford/Auto-Empirical-Research-Skills4.6k—~2.9kAutomated safety check: PassCustom licence
Designing Experimentsforyourhealth111-pixel/Vibe-Skills3.6k—~600Automated safety check: PassApache-2.0
Jape Identification Strategyfranklee16/academic-research-skills2231 repos~707Automated safety check: PassNone

Similar skills

  • Causal

    ai-analyst-lab/ai-analyst

    Causal inference toolkit for when experiments are not possible: estimate treatment effects from observational data with assumption checks and mandatory caveats.

    304 GitHub stars~1.8k tokensUpdated 10 days ago
    Research & ScienceAuto-check passed

  • Fin Experiment Design

    csmar432/finai-research

    经济金融实证方法设计。根据研究想法和REFINEDDESIGN.md，生成完整的实证研究设计方案，覆盖识别策略选择、样本构建、变量定义、稳健性检验清单和内生性处理方案。

    109 GitHub stars~4.2k tokensUpdated 5 days ago
    Research & ScienceAuto-check passed

  • Academic Paper Verify

    brycewang-stanford/Auto-Empirical-Research-Skills

    Thoroughly verify all code, tables, figures, modeling decisions, and quantitative claims in an academic paper against its source R scripts and output files.

    4.6k GitHub stars~2.9k tokensUpdated 6 days ago
    Research & ScienceAuto-check passed

  • Designing Experiments

    foryourhealth111-pixel/Vibe-Skills

    Design experiments and quasi-experiments before analysis. An agent skill from foryourhealth111-pixel/Vibe-Skills.

    3.6k GitHub stars~600 tokensUpdated 1 mo ago
    Research & ScienceAuto-check passed

  • Jape Identification Strategy

    franklee16/academic-research-skills

    A skill your agent uses when designing or defending the empirical identification of a Journal of Applied Econometrics (JAE) manuscript — a credible strategy applied to real data, with assumptions…

    223 GitHub starsUsed in 1 repo~707 tokens
    Research & ScienceAuto-check passed

  • Performing Causal Analysis

    foryourhealth111-pixel/Vibe-Skills

    Estimate causal effects from existing data. An agent skill from foryourhealth111-pixel/Vibe-Skills.

    3.6k GitHub stars~370 tokensUpdated 1 mo ago
    Research & ScienceAuto-check passed

More from K-Dense-AI/mimeo

All 21 skills in this repo

  • Andrej Karpathy

    K-Dense-AI/mimeo

    Applies the mental models and frameworks of Andrej Karpathy (deep learning, former Director of AI at Tesla, founding member of OpenAI, Eureka Labs).

    282 GitHub stars~1.9k tokensUpdated 1 mo ago
    Auto-check passed

  • Andrew Ng

    K-Dense-AI/mimeo

    Applies the reasoning, principles, and frameworks of Andrew Ng (machine learning pioneer, co-founder of Coursera and DeepLearning.AI, Stanford University, and former Google Brain lead).

    282 GitHub stars~1.5k tokensUpdated 1 mo ago
    Auto-check passed

  • Christopher Manning

    K-Dense-AI/mimeo

    Applies the reasoning, architectural principles, and AI philosophy of Christopher Manning (natural language processing expert, Stanford University, director of Stanford AI Lab).

    282 GitHub stars~1.8k tokensUpdated 1 mo ago
    Auto-check passed

  • Daphne Koller

    K-Dense-AI/mimeo

    Applies the reasoning style of Daphne Koller (machine learning pioneer, co-founder of Coursera, founder and CEO of Insitro).

    282 GitHub stars~1.8k tokensUpdated 1 mo ago
    Auto-check passed

  • Demis Hassabis

    K-Dense-AI/mimeo

    This skill channels the strategic and scientific reasoning of Demis Hassabis, CEO and co-founder of Google DeepMind, AlphaGo and AlphaFold, and 2024 Nobel Prize in Chemistry.

    282 GitHub stars~2k tokensUpdated 1 mo ago
    Auto-check passed

  • Fei Fei Li

    K-Dense-AI/mimeo

    Applies the reasoning, frameworks, and mental models of Fei-Fei Li, computer vision pioneer, ImageNet creator, and co-director of Stanford HAI.

    282 GitHub stars~1.8k tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about Judea Pearl

What does Judea Pearl do?

Applies Judea Pearl's causal reasoning frameworks to distinguish correlation from causation, evaluate AI capabilities, and make counterfactual decisions. Judea Pearl is an agent skill from K-Dense-AI/mimeo. Applies Judea Pearl's causal reasoning frameworks to distinguish correlation from causation, evaluate AI capabilities, and make counterfactual decisions.

When should I use Judea Pearl?

Judea Pearl fits situations like: this skill for topics involving Bayesian networks; the do-calculus; the Ladder of Causation; A user tries to answer what if.

How do I install Judea Pearl in Claude Code?

Run `npx skills add K-Dense-AI/mimeo --skill judea-pearl -a claude-code`. Or copy the skill folder (output/judea-pearl in K-Dense-AI/mimeo) into .claude/skills/judea-pearl in your project. Claude Code loads it when a task matches its description.

How do I install Judea Pearl in Codex?

Run `npx skills add K-Dense-AI/mimeo --skill judea-pearl -a codex`. Or copy the skill folder (output/judea-pearl in K-Dense-AI/mimeo) into .agents/skills/judea-pearl in your project. Codex loads it when a task matches its description.

Can I use Judea Pearl in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add K-Dense-AI/mimeo --skill judea-pearl -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/judea-pearl, .gemini/skills/judea-pearl, .github/skills/judea-pearl and .opencode/skills/judea-pearl in your project.

What does Judea Pearl need to run?

SKILL.md names no scripts, command-line tools or credentials: Judea Pearl is instructions for the agent only.

Does Judea Pearl access the network?

SKILL.md names 1 domain. As links in the text: arxiv.org. This is read from the text; nothing was executed.

Is Judea Pearl safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Judea Pearl use?

Judea Pearl is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Judea Pearl use?

About 1.7k tokens (SKILL.md is roughly 6.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 7.5k tokens, read only when the agent opens those files.

What are the alternatives to Judea Pearl?

Skills that share tags, products or a category with Judea Pearl: Causal (ai-analyst-lab/ai-analyst, 304 stars), Fin Experiment Design (csmar432/finai-research, 109 stars), Academic Paper Verify (brycewang-stanford/Auto-Empirical-Research-Skills, 4.6k stars) and Designing Experiments (foryourhealth111-pixel/Vibe-Skills, 3.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Judea Pearl?

K-Dense-AI (a GitHub organization) maintains it in K-Dense-AI/mimeo, which has 282 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on September 2, 2026.

Source: K-Dense-AI/mimeo on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.