MCPInstall

metabase-modular-embedding-to-modular-embedding-sdk-upgrade

Migrates a React project from Metabase Modular embedding (embed.js web components) to the Modular embedding SDK (@metabase/embedding-sdk-react). Use when the user wants to switch from embed.js web components to React SDK components (MetabaseProvider). This is not a version upgrade — it changes the embedding technology.

Installs
354
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/metabase/agent-skills --skill metabase-modular-embedding-to-modular-embedding-sdk-upgrade
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads metabase-modular-embedding-to-modular-embedding-sdk-upgrade automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

Execution contract

Follow the workflow steps in order — do not skip any step. Create the checklist first, then execute each step and explicitly mark it done with evidence. Each step's output feeds into the next, so skipping steps produces wrong migrations.

If you cannot complete a step due to missing info or tool failure, you must:

  1. record the step as ❌ blocked,
  2. explain exactly what is missing / what failed,
  3. stop (do not proceed to later steps).

Required output structure

Your response should contain these sections in this order:

  1. Step 0: Prerequisites Check
  2. Step 0.1: Migration Plan Checklist
  3. Step 1: Project Scan
  4. Step 2: Target SDK API
  5. Step 3: Migration Mapping
  6. Step 4: Applied Code Changes
  7. Step 5: Typecheck Validation
  8. Step 6: Final Summary

Each step section should end with a status line:

  • Status: ✅ complete or Status: ❌ blocked

Evidence requirements

  • Step 0: React detected (dependency + version), Metabase instance version, target SDK version, package manager.
  • Step 1: every file with Modular embedding usage (web components, metabaseConfig, embed.js script tag), with matching grep lines.
  • Step 2: confirm d.ts loaded in context. List exported components, their props, and the MetabaseProvider config type.
  • Step 3: the structured migration mapping — every web component → React component with prop conversions, auth config mapping, and embed.js removal plan.
  • Step 4: per file — what was changed and exact diffs applied.
  • Step 5: the exact typecheck command run and error summary if any remain.

Credential safety

This migration touches code that may contain API keys, JWTs, or auth configuration values (e.g., window.metabaseConfig). Rules:

  • Never output literal secret values — if you encounter a hardcoded API key, token, or secret in the code, reference it by variable name or file location (e.g., "the key in config.js:12"), never echo the value itself
  • In code diffs and summaries, use variable references — not the resolved values
  • If you find hardcoded secrets, flag them to the user and recommend moving them to environment variables as part of the migration

Performance

The workflow is designed as a pipeline:

Round 1 (grep+glob+pkg) ──► Round 2 (prepare.sh) ──► Round 3 (read-sources.sh) ──► Step 3 (mapping, inline)
                                                                                          │
                                                                                    Step 4 per-file:
                                                                                     ├── Convert FileA
                                                                                     ├── Convert FileB
                                                                                     └── Convert FileC
                                                                                           │
                                                                                     Step 5 (typecheck) ──► Step 6

In Claude Code, use parallel tool calls or run_in_background: true for sub-agents.

Do not parse repo branches, commits, PRs, or issues — they're noisy and irrelevant.

Tool-call round budget for Steps 1+2

Steps 1+2 must complete in 3 tool-call rounds.

Round 1 — discovery (all concurrent, single message):

  • Grep for metabase-dashboard, metabase-question, metabase-browser in *.{jsx,tsx,js,ts} files
  • Grep for window.metabaseConfig
  • Grep for /app/embed.js (to find the script tag)
  • Read package.json (to confirm React dependency and detect package manager)
  • Glob for lock files (yarn.lock, pnpm-lock.yaml, package-lock.json)
  • npm view @metabase/embedding-sdk-react version (if target not specified by user)

All tool calls in one message.

Round 2 — prepare.sh + fetch docs (concurrent):

bash <skill-path>/scripts/prepare.sh {TARGET_VERSION}

Downloads the target SDK npm package and extracts it. Outputs SDK_TMPDIR and d.ts availability.

In the same message, fetch llms-embedding-full.txt for the target version (see "Allowed documentation sources" for URL format).

Round 3 — read-sources.sh (single Bash call):

bash <skill-path>/scripts/read-sources.sh {SDK_TMPDIR}

Dumps the target SDK's d.ts type definitions to stdout.

After Round 3, output Step 1 Results + Step 2 Results + Step 3 Migration Mapping with zero additional tool calls. Produce Step 3 inline right after the data is loaded.

Scope

This skill converts Modular embedding (web-components-based) used inside a React app to the Modular embedding SDK (@metabase/embedding-sdk-react). The project must already be a React application with Modular embedding web components in JSX/TSX files.

If the project is not React-based, this skill does not apply. If the project uses iframes instead of web components, use the metabase-full-app-to-modular-embedding-upgrade skill instead.

What this skill handles

  • Replacing <metabase-dashboard>, <metabase-question>, <metabase-browser> web components in JSX/TSX with their SDK React equivalents
  • Installing the @metabase/embedding-sdk-react npm package
  • Adding <MetabaseProvider> at the appropriate level in the React component tree
  • Converting window.metabaseConfig to MetabaseProvider config props
  • Removing the embed.js <script> tag (typically in index.html or the HTML entry point)
  • Removing the window.metabaseConfig assignment
  • Converting HTML attribute naming (kebab-case) to React prop naming (camelCase)

What this skill does not handle

  • Non-React projects using Modular embedding web components in plain HTML/templates

Allowed documentation sources

Fetch the version-specific llms-embedding-full.txt using this URL:

https://www.metabase.com/docs/v0.{VERSION}/llms-embedding-full.txt

The version in the URL uses the format v0.58 (normalize: strip leading v or 0., drop patch — e.g., 0.58.1 → 58 → URL uses v0.58). This single file contains all embedding documentation for that version, optimized for LLM consumption.

Other constraints:

  • No GitHub PRs/issues or npm pages
  • Do not follow changelog links to GitHub or guess URLs

Detecting versions

Do all version detection in Round 1.

  • Metabase instance version: grep for Docker image tags (metabase/metabase:v, metabase/metabase-enterprise:v), METABASE_VERSION, or version references in env files. If undetected, AskUserQuestion.
  • Target SDK version:
    • If user specifies, use it.
    • Otherwise, use the Metabase instance version to determine the matching SDK version (they use the same version scheme: Metabase v0.58 → SDK 0.58.x). Run npm view @metabase/embedding-sdk-react version to find the latest matching version.
  • Package manager: detect from lock files e.g. yarn.lock → yarn, pnpm-lock.yaml → pnpm, package-lock.json → npm.

Pre-workflow steps

Migration Plan Checklist

Create a checklist to track progress. In Claude Code, use TaskCreate/TaskUpdate tools:

  • Step 0: Prerequisites check
  • Step 1: Scan Modular embedding usage
  • Step 2: Fetch target SDK API
  • Step 3: Build migration mapping
  • Step 4: Apply code changes (one sub-task per file)
  • Step 5: Typecheck and fix
  • Step 6: Final summary

Workflow

Step 0: Prerequisites check

Verify before starting:

  1. React dependency: check package.json for react in dependencies or devDependencies. If not present, mark ❌ blocked — this skill only applies to React projects.
  2. Web components in JSX/TSX: confirm the grep results from Round 1 show <metabase-* usage in .jsx, .tsx, .js, or .ts files (not only in plain HTML). If web components are only in plain HTML files, mark ❌ blocked — this skill requires web components to already be used inside React.
  3. Metabase instance version: detect or ask user (see "Detecting versions" section above).
  4. Target SDK version: determine as described in "Detecting versions".
  5. Package manager: detect from lock files.

Step 1: Scan Modular embedding usage

Step 1 happens in Round 1 — grep only, no file reading.

Grep for these patterns (all in parallel):

  • <metabase-dashboard in *.{jsx,tsx,js,ts} files — dashboard web components
  • <metabase-question in *.{jsx,tsx,js,ts} files — question web components
  • <metabase-browser in *.{jsx,tsx,js,ts} files — collection browser web components
  • window.metabaseConfig — global config assignment (may be in index.html or a JS/TS file)
  • /app/embed.js — the embed.js script tag (typically in index.html)

This returns file paths + matching lines. Do not read project files yet — that happens in Step 4.

Output: a file list grouped by category:

Web components (JSX/TSX):
  - src/pages/Dashboard.tsx:15 — <metabase-dashboard dashboard-id="123">
  - src/pages/Analytics.tsx:22 — <metabase-question question-id="456">
Config:
  - public/index.html:8 — window.metabaseConfig = { ... }
Script tag:
  - public/index.html:12 — <script defer src="...embed.js"></script>

Step 2: Fetch target SDK API

Run prepare.sh in Round 2 (see round budget). Then read-sources.sh in Round 3 to load the d.ts into context.

If d.ts is available, extract from it:

  • All exported React components (e.g., MetabaseProvider, dashboard/question/collection components)
  • Their prop types (resolved to concrete types, not just alias names)
  • The MetabaseProvider config type (what fields it accepts)
  • The auth config type

The embedding docs (llms-embedding-full.txt) fetched in Round 2 provide supplementary reference for component usage, configuration options, and migration guidance. Use them alongside the d.ts for a complete picture.

If d.ts is not available (SDK versions before 0.52.0 do not ship a single index.d.ts), use the embedding docs as the primary API reference instead. If neither d.ts nor docs are available, mark Step 2 ❌ blocked.

Step 3: Build migration mapping (after Steps 1–2 are ✅ complete)

Scope: only map components and config actually found in Step 1's scan.

Produce a mapping that covers:

Component mapping

For each web component found in Step 1, identify the SDK React equivalent from the d.ts. Map attributes to props:

## Migration Mapping

### <metabase-dashboard> → {SDK dashboard component from d.ts}
- `dashboard-id` → `dashboardId` (camelCase)
- `with-title` → `withTitle` (boolean prop)
- `drills` → check d.ts for equivalent prop name
- Other attributes → map to corresponding React props from d.ts

### <metabase-question> → {SDK question component from d.ts}
- `question-id` → `questionId` (camelCase)
- Other attributes → map from d.ts

### <metabase-browser> → {SDK collection component from d.ts}
- `initial-collection` → check d.ts for prop name
- Other attributes → map from d.ts

For each mapping, resolve the target prop type to its concrete type. If an attribute has no SDK equivalent, note it as "dropped (not supported in SDK)" or "requires alternative approach".

Auth config mapping

Map window.metabaseConfig fields to MetabaseProvider config:

### Auth & Config
- window.metabaseConfig.instanceUrl → config.metabaseInstanceUrl (check d.ts for exact field name)
- window.metabaseConfig.jwtProviderUri → authConfig.jwtProviderUri or authConfig.authProviderUri or config.authProviderUri (check d.ts — the field was renamed from `jwtProviderUri` to `authProviderUri` in some versions)
- window.metabaseConfig.locale → locale prop or config field (check d.ts)

The d.ts is the authoritative source for field names — do not guess. If a window.metabaseConfig field has no equivalent in the SDK config type, note it.

MetabaseProvider placement

Determine where to add <MetabaseProvider>:

  • Find the highest common ancestor component that contains all Modular embedding web components
  • Typically this is the app root (App.tsx, App.jsx, or equivalent)
  • The provider must wrap all SDK components but should not unnecessarily wrap the entire app if components are isolated to a subtree

Removal plan

  • embed.js <script> tag: identify file and exact code to remove
  • window.metabaseConfig assignment: identify file and exact code to remove

Step 4: Apply code changes

Before per-file work:

  1. Install the SDK package:
    {package-manager} add @metabase/embedding-sdk-react@{TARGET_VERSION}
    
  2. Remove the embed.js <script> tag
  3. Remove the window.metabaseConfig assignment
  4. Add <MetabaseProvider> wrapper at the determined location with the migrated config

Per-file task (for each file containing web components):

  1. Read the file — first time file content is loaded.
  2. Match mapping entries — which web components are in this file, what are their current attributes?
  3. Convert each web component:
    • Replace the web component tag with the SDK React component
    • Convert HTML attributes (kebab-case) to React props (camelCase)
    • Convert string attribute values to appropriate JS types (e.g., "false" → {false}, "123" → {123})
    • Add the import statement for the SDK component
  4. Report — output what was changed.

Parallelization strategy:

  • ≤ 10 files: process all in the main agent.
  • > 10 files: batch into 3–5 sub-agents. Each receives its file paths and the full migration mapping.

Type conversion rules

When converting HTML attribute values to React props:

  • String "true" / "false" → boolean {true} / {false}
  • Numeric strings "123" → number {123}
  • Template expressions already in JSX (e.g., {dashboardId}) → keep as-is
  • Static string IDs → keep as strings if the d.ts prop type accepts strings, otherwise convert

Step 5: Typecheck validation

  1. Run typecheck — npm run typecheck, tsc --noEmit, or the project's equivalent.
  2. Analyze errors — categorize SDK-related errors by root cause.
  3. Look up expected types — search the installed node_modules/@metabase/embedding-sdk-react/dist/index.d.ts for each failing symbol.
  4. Fix in batch — apply all fixes before re-running typecheck.
  5. Verify — re-run typecheck. If errors remain after 3 rounds, mark ❌ blocked.

If the project does not use TypeScript, manually review each change against the d.ts to verify prop names and types match. Mark Step 5 ✅ with a note that validation was manual.

Step 6: Output summary

Organize into these sections:

1. Changes applied — list every file modified and a one-line description of each change.

2. Component mapping — table showing each old web component → new React component:

| File | Old | New | Props Changed |
|---|---|---|---|
| src/Dashboard.tsx | <metabase-dashboard dashboard-id="1"> | <InteractiveDashboard dashboardId={1} /> | dashboard-id → dashboardId |

3. Auth migration — how window.metabaseConfig was converted to MetabaseProvider config.

4. Removed artifacts — embed.js script tag, window.metabaseConfig, any dead code.

5. New capabilities — SDK features now available that weren't in Modular embedding (e.g., React hooks, typed callbacks, sub-components like InteractiveQuestion.FilterBar). Keep brief.

6. Instance requirements — minimum Metabase instance version needed. The Metabase instance version must match the SDK version (e.g., SDK 0.58.x requires Metabase v0.58+).

Retry policy

Doc fetching:

  • If fetching llms-embedding-full.txt returns 404, verify the Metabase version number and retry. If still failing, proceed without docs (d.ts is the primary source).

npm pack:

  • If npm pack fails for the target version, it likely doesn't exist on npm. Mark as ❌ blocked and inform the user.

npm install:

  • If package installation fails due to peer dependency conflicts, try with --legacy-peer-deps (npm) or equivalent. Report the conflict to the user.

FAQ

What does the metabase-modular-embedding-to-modular-embedding-sdk-upgrade skill do?

Migrates a React project from Metabase Modular embedding (embed.js web components) to the Modular embedding SDK (@metabase/embedding-sdk-react). Use when the user wants to switch from embed.js web components to React SDK components (MetabaseProvider). This is not a version upgrade — it changes the embedding technology.

How do I install metabase-modular-embedding-to-modular-embedding-sdk-upgrade?

Run npx skills add https://github.com/metabase/agent-skills --skill metabase-modular-embedding-to-modular-embedding-sdk-upgrade in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/metabase-modular-embedding-to-modular-embedding-sdk-upgrade/ (personal) or .claude/skills/metabase-modular-embedding-to-modular-embedding-sdk-upgrade/ (project).

Which AI agents can use metabase-modular-embedding-to-modular-embedding-sdk-upgrade?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is metabase-modular-embedding-to-modular-embedding-sdk-upgrade safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains metabase-modular-embedding-to-modular-embedding-sdk-upgrade?

It is published by metabase in metabase/agent-skills. It has 354 recorded installs.

More from metabase/agent-skills

View all →

rde

metabase/agent-skills

Expert data engineering with Metabase at the center of any company's stack: explore and profile raw warehouse tables, build clean tables as Metabase transforms pinned by transform tests, build the semantic layer (models, metrics, measures, segments, metadata), design dashboards, answer questions with checked numbers, reconcile against a reference, change delivered definitions safely. Use for data work, not one mb command (metabase-cli): "make sense of my data", "model this raw schema", "set up analytics for X", "build a data model", "define MRR / active customers officially", "build a semantic layer", "go from raw tables to a dashboard", "does this number match finance", "our numbers look wrong", "two cards disagree", "test this transform", "why does this transform get case X wrong", "make Metabot answer questions about X", "explain this table", "change this definition", "build a data app", "donor retention", "event attendance", "quarterly board report", "be my data engineer / anal

Data & Databases949 installs

rde-data-apps

metabase/agent-skills

Build or change a Metabase data app on an rde machine: settles what the metabase-data-apps skill needs from the local setup (the remote-sync repository, the Metabase URL, the API key rde stores, how the app reaches Metabase), makes sure everything the app reads is Library content already synced into that repository, confirms every sync step with the user, and hands the build to it. Use only when an app is asked for explicitly: "build me an app for X", "create a data app", "make an internal tool / portal in Metabase", "add a page / a form / a filter to my data app". A dashboard, a question, or a metric is not an app; those stay with the rde skill.

Backend & APIs877 installs

metabase-cli

metabase/agent-skills

Drive a Metabase instance from the terminal via the mb CLI: auth profiles, databases and schemas, schema sync and field-values rescan, tables, fields, cards (questions, models, metrics) run as JSON/CSV/XLSX, dashboards and dashcards, collections and their tree, snippets, segments, measures, transforms and transform-jobs, settings, search, git-sync. Use for any Metabase operation from the terminal: "log into metabase", "what profiles do I have", "list cards", "run card 42 as CSV", "create a transform", "list dashboards", "move a dashcard", "list collections", "what's in collection 4", "show the collection tree", "list snippets", "create a segment", "archive a measure", "search metabase for X", "import the latest changes", "add a directory to git sync", "set a setting", "what schemas are in this database", "trigger a sync", "rescan field values", or any mb . Whole data jobs go to rde.

Data & Databases784 installs

metabase-database-metadata

metabase/agent-skills

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 @metabase/database-metadata, or when reasoning about a project's schema (columns, types, FK relationships) through the .metadata/databases folder.

Data & Databases564 installs

metabase-representation-format

metabase/agent-skills

Understands the Metabase Representation Format — a YAML-based serialization format for Metabase content (collections, cards, dashboards, documents, segments, measures, snippets, transforms, actions, and data apps). Use when the user needs to create, edit, understand, or validate Metabase representation YAML files, or when working with Metabase serialization/deserialization (serdes). Covers entity schemas, MBQL and native queries, visualization settings, parameters, and folder structure.

AI & Agents535 installs

metabase-semantic-checker

metabase/agent-skills

Open the skill to read its SKILL.md instructions.

AI & Agents432 installs

Popular ai & agents skills

View category →

google-agents-cli-publish

google/agents-cli

This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).

AI & Agents513.9K installs

google-agents-cli-eval

google/agents-cli

This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).

AI & Agents513.5K installs

skill-creator

anthropics/skills

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

OfficialAI & Agents416.4K installs

codex-pet

prime-skills/runcomfy-agent-skills

Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.

AI & Agents402.1K installs

full-output-enforcement

leonxlnx/taste-skill

Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.

AI & Agents401K installs

executing-plans

obra/superpowers

Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available

AI & Agents245.7K installs