Skip to content
Skill

Causal inference

Bengio's causal inference for AI: Interventional reasoning, counterfactuals, and System 2 deep learning

Install
Scripts
None
Platforms
Claude Code, Codex, Cursor
GitHub stars
72
Last commit
18 days ago
License
MIT
Listing updated
today

When your agent uses it

Bengio's causal inference for AI: Interventional reasoning, counterfactuals, and System 2 deep learning. World models with causal structure.

From the skill's SKILL.md. Your agent reads this description to decide when to load the skill.

What it can access

From a static check of its 1 file (7 KB) on GitHub on 17 November 2026. Nothing was run. Read the files before you install a skill: it can tell your agent to run anything its tools allow.

Install

Copy the skill folder to ~/.claude/skills/causal-inference to use it in all your projects:

tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/plurigrid/asi.git "$tmp" &&
mkdir -p ~/.claude/skills &&
rm -rf ~/.claude/skills/causal-inference &&
cp -R "$tmp/ies/music-topos/.codex/skills/causal-inference" ~/.claude/skills/causal-inference &&
rm -rf "$tmp"

For one project only, put the folder in .claude/skills/causal-inference inside it instead.

Claude Code docs on skills

Copy the skill folder to ~/.agents/skills/causal-inference to use it in every repository:

tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/plurigrid/asi.git "$tmp" &&
mkdir -p ~/.agents/skills &&
rm -rf ~/.agents/skills/causal-inference &&
cp -R "$tmp/ies/music-topos/.codex/skills/causal-inference" ~/.agents/skills/causal-inference &&
rm -rf "$tmp"

For one repository only, put the folder in .agents/skills/causal-inference inside it instead.

Codex docs on skills

Copy the skill folder to ~/.cursor/skills/causal-inference to use it in every project:

tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/plurigrid/asi.git "$tmp" &&
mkdir -p ~/.cursor/skills &&
rm -rf ~/.cursor/skills/causal-inference &&
cp -R "$tmp/ies/music-topos/.codex/skills/causal-inference" ~/.cursor/skills/causal-inference &&
rm -rf "$tmp"

For one project only, put the folder in .cursor/skills/causal-inference inside it instead.

Cursor docs on skills

Run in a terminal (add --scope workspace to install it for the current workspace only):

gemini skills install https://github.com/plurigrid/asi.git --path ies/music-topos/.codex/skills/causal-inference

Or copy the folder to ~/.gemini/skills/causal-inference yourself.

Gemini CLI docs on skills

For GitHub Copilot in VS Code, copy the skill folder to ~/.copilot/skills/causal-inference:

tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/plurigrid/asi.git "$tmp" &&
mkdir -p ~/.copilot/skills &&
rm -rf ~/.copilot/skills/causal-inference &&
cp -R "$tmp/ies/music-topos/.codex/skills/causal-inference" ~/.copilot/skills/causal-inference &&
rm -rf "$tmp"

For one project only, put the folder in .github/skills/causal-inference inside it instead.

VS Code docs on skills

Get the folder:

git clone --depth 1 https://github.com/plurigrid/asi.git

Then copy asi/ies/music-topos/.codex/skills/causal-inference into your agent's skills folder as causal-inference. Agents that support SKILL.md read one folder per skill.

The SKILL.md format

Causal inference FAQ

How do I install Causal inference in Claude Code?

Copy the skill folder from GitHub to ~/.claude/skills/causal-inference to use it in all your projects, or to .claude/skills/causal-inference in one project.

Does Causal inference run scripts?

No. It is instructions only, with no scripts. This comes from a static check of the files on GitHub; nothing was run. Read the files before you install it.

Which AI agents can use Causal inference?

Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose. Each reads skills in the SKILL.md format from its own folder; the install steps on this page list them.

More from plurigrid/asi

  1. Org-agenda-like transient views for ASI skill orchestration via nbb/squint + Emacs hydra

    • Open source
    • 72 GitHub stars
  2. Connect and stream from OpenBCI Cyton/Daisy via USB dongle, including first-time radio channel pairing

    • Open source
    • 72 GitHub stars
  3. Hypothesis-Test Loops via REPL for Exploratory Abductive Inference with Gay.jl colors

    • Open source
    • 72 GitHub stars
  4. Layer 4 Learning and Pattern Extraction for Cognitive Surrogate Systems

    • Open source
    • 72 GitHub stars
  5. Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration

    • Open source
    • 72 GitHub stars
  6. Automated code review for pull requests using specialized review patterns

    • Open source
    • 72 GitHub stars
    • Developer tools