Skip to content
Analytics Engineering
Start free
Open-source installation

Install the Analytics Engineering Toolkit.

The source and releases are public today. Clone the repository and install the toolkit for Cursor, VS Code, or Google Antigravity. A one-click marketplace listing is still pending.

View the repositoryLatest release

Requirements: Git and Python 3. Read the repository files before running installation commands.

Agent Skills hosts

Install the skills in Claude Code, Codex, Gemini CLI, OpenCode, and other compatible agents.

This option installs the toolkit's 25 skills without the Cursor-specific hooks, commands, or agents.

npx skills add analyticsengineering/ae-toolkit

Use the Cursor, VS Code, or Antigravity install when you need the toolkit's enforced shell, warehouse, and published-model gates.

Cursor

Install as a local plugin.

Cursor currently loads locally developed plugins from its local plugins directory. Install a real directory rather than a symlink.

git clone https://github.com/analyticsengineering/ae-toolkit.git
cd ae-toolkit
mkdir -p ~/.cursor/plugins/local
rsync -a --exclude '.git' ./ ~/.cursor/plugins/local/analytics-engineering-toolkit/
  1. 01

    Restart Cursor or run Developer: Reload Window.

  2. 02

    Open Customize and confirm Analytics Engineering Toolkit appears.

  3. 03

    Review and enable only the components and scopes you intend to use.

Cursor documents local plugin behavior in its Plugins guide. Teams and Enterprise administrators may disable local plugin imports.

First local workflow

/ae-review-sql Review models/marts/fct_orders.sql. Mode: Work. Expected grain: one row per order. Do not execute queries.
VS Code and Antigravity

Generate and install the matching host layout.

The installer merges toolkit files into the target workspace, rewrites hook commands to absolute paths, and verifies that a destructive command is denied.

VS Code

python3 scripts/build_targets.py
python3 scripts/install_target.py --host vscode --workspace /path/to/your/repo

Google Antigravity

python3 scripts/build_targets.py
python3 scripts/install_target.py --host antigravity --workspace /path/to/your/repo

Add --dry-run to preview the workspace changes before installation.

Featured workflows

Start with six common analytics tasks.

  • /ae-review-sqlAvailable locally
    Workflow 01

    Review SQL

    Check correctness, grain, joins, performance, and production risk.

  • /ae-profile-dataAvailable locally
    Workflow 02

    Profile data

    Compute and interpret a local CSV, JSON, or JSONL profile.

  • /ae-review-modelAvailable locally
    Workflow 03

    Review a data model

    Assess or propose a model from business and source evidence.

  • /ae-dbt-healthAvailable locally
    Workflow 04

    Check dbt health

    Inspect a real dbt project without blindly executing dbt.

  • /ae-requirementsAvailable locally
    Workflow 05

    Clarify requirements

    Turn an ambiguous request into definitions and acceptance criteria.

  • /ae-explainAvailable locally
    Workflow 06

    Explain data code

    Explain selected SQL, Python, dbt, YAML, or pipeline code.

Connected integration

Local workflows work without the planned remote service.

Connected course hints and authoritative grading remain planned. The public toolkit does not claim those services are available.

  • /ae-hintComing later
    Workflow 01

    Connected course hints

    Requires a course service that is not available today.

  • /ae-gradeComing later
    Workflow 02

    Connected grading

    Requires an authoritative course service that is not available today.

Take the skill diagnostic