metabase

Use when building, creating, or editing data apps that should query Metabase tables and metrics through generated schema files like metabase.data.ts or *.metabase.data.ts.

Scaffold a new Metabase data-app into the connected remote-sync repository's `data_apps/<app>/` directory from the `data-app-template`. Use when the user asks to start, create, scaffold, or set up a data-app from scratch.

Write TypeScript and JavaScript code following Metabase coding standards and best practices. Use when developing or refactoring TypeScript/JavaScript code.

Deciding where frontend code lives — tier model, move mechanics, extension points, side effects, naming, and the traps. Use when moving code between modules, carving new modules, fixing boundary violations, adding a barrel or an endpoint, or reviewing…

Review Clojure and ClojureScript code changes for compliance with Metabase coding standards, style violations, and code quality issues. Use when reviewing pull requests or diffs containing Clojure/ClojureScript code.

Guide Clojure and ClojureScript development using REPL-driven workflow, coding conventions, and best practices. Use when writing, developing, or refactoring Clojure/ClojureScript code.

Add product analytics events to track user interactions in the Metabase frontend

Review TypeScript and JavaScript code changes for compliance with Metabase coding standards, style violations, and code quality issues. Use when reviewing pull requests or diffs containing TypeScript/JavaScript code.

Add an end-to-end test that drives the built CLI against a real Metabase via docker compose. Use whenever the user asks to "add an e2e test for `<command>`", "wire `<noun> <verb>` into tests/e2e", "cover the new command end-to-end", or anything that creates a…

Add a Metabase API resource end-to-end — Zod schema in `packages/client/src/domain/`, methods in `packages/client/src/resources/`, list/get commands in `packages/cli/src/commands/<noun>/`, unit tests where logic warrants them, and a comprehensive e2e suite.…

Whole-repo architectural drift sweep. Spawns eight parallel read-only subagents, each focused on one axis across the entire codebase (not just the diff). Aggregates findings into a single severity-ranked report. Use periodically, before milestones, or on user…

Strict end-of-task review. Use before marking any non-trivial task done. Returns axis-by-axis pass/fail; any FAIL blocks completion. Trigger on user /review or end-of-task self-check.

Foundations for driving Metabase from the terminal with the `mb` CLI — authentication and named profiles, the flag/output/`--json` conventions every command shares, JSON body input, command discovery via `--help` (add `--json` for machine-readable schemas),…

Build Metabase dashboards via the `mb` CLI — lay out dashcards on the 24-column grid (`{col,row,size_x,size_y}` math, per-chart default sizes) and turn cards into a filterable, cross-linked app. Covers wiring filters to cards (parameters +…

Guided, end-to-end data work through the `mb` CLI — investigate a raw database, build clean analysis-ready tables, define reusable segments/measures/metrics, answer questions, and build dashboards. Detects where the data is, holds the shared conventions for…

Author and edit Metabase documents via `mb` — the TipTap (ProseMirror) JSON body shape, the node-type inventory (paragraphs, headings, lists, plus the Metabase-custom `cardEmbed` / `smartLink` / `flexContainer` / `resizeNode`), the per-node-type `_id`…

A Metabase AI-governance coach, covering the *controls and rollout* side of AI: who may use Metabot, what it can see, what it costs, where the model runs, and the audit trail. Use this skill whenever the user wants to roll out AI analytics safely, control who…

A Metabase AI-readiness coach, covering the *data groundwork* that makes AI answers trustworthy: modeling with Transforms, table and field metadata, the Glossary, saved Metrics, and marking canonical content. Use this skill whenever the user wants to check if…

A spaced repetition learning coach for Metabase. Use this skill whenever the user wants to: learn Metabase, start a Metabase training session, do a Metabase review, practice Metabase concepts, check what they should study today, get quizzed on Metabase, run…

Drive a Metabase instance from the terminal via the `mb` CLI. Authenticate with named profiles; inspect databases (list, get, full metadata rollup, schemas, tables in a schema) and trigger manual schema sync / field-values rescan; inspect tables, fields;…

Understands the Metabase Database Metadata Format — a YAML-based on-disk representation of databases, tables, and fields synced from a Metabase instance. Use when the user needs to read, edit, or understand metadata files produced by…

Runs the Metabase semantic checker against a tree of Representation Format YAML files to verify that all references resolve — cross-entity references (collection_id, dashboard_id, parent_id, parameter source cards, snippet references, transform tags, etc.)…

Understands the Metabase Representation Format — a YAML-based serialization format for Metabase content (collections, cards, dashboards, documents, segments, measures, snippets, transforms). Use when the user needs to create, edit, understand, or validate…

Implements JWT SSO authentication for Metabase embedding in a project. Supports all embedding types that use SSO — Modular embedding (embed.js web components), Modular embedding SDK (@metabase/embedding-sdk-react), and Full app embedding (iframe-based).…

Reference material for Metabase reproduction — REPL recipes, API patterns, domain quirks (pivot tables, serialization, H2 tips), edge case handling, and MCP tools table. Invoke at Phase 4 start.

Write a failing test for a reproduced Metabase bug. Invoked from the /repro workflow when status is REPRODUCED. Determines test type (Clojure/Jest/Cypress), finds the right test file, writes a minimal failing test, runs it, and saves a patch.

Set up and run a local Metabase instance. Downloads the JAR (if Java 21+ is available) or runs via Docker. Also handles stopping running instances.

Read these instructions before using Metabase MCP tools. Setup is needed to connect to Metabase instances via the built-in MCP server.

Set up and run a local Metabase instance. Downloads the JAR (if Java 21+ is available) or runs via Docker. Also handles stopping running instances.