Token导航 LogoToken导航

Agent Skill · 研究检索

metabase-modular-embedding-to-modular-embedding-sdk-upgrade(metabase modular embedding TO modular embedding SDK upgrade 搜索)

用于搭建或维护带检索增强的 RAG 工作流,适合让 Agent 处理知识库问答、向量检索、来源引用和事实核查。它可以辅助整理数据接入、Embedding、向量库、召回参数和回答生成流程。使用时需要确认数据来源、更新频率、召回阈值和引用展示方式,避免把未命中的资料或过期内容包装成确定事实。

metabase-modular-embedding-to-modular-embedding-sdk-upgrade 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为接触敏感数据;许可证信息还不明确,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 47,393。

总安装 734周安装 30GitHub Stars 12下载 238核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:metabase-modular-embedding-to-modular-embedding-sdk-upgrade(metabase modular embedding TO modular embedding SDK upgrade 搜索)
来源仓库:https://github.com/metabase/agent-skills
仓库路径:skills/metabase-modular-embedding-to-modular-embedding-sdk-upgrade
安装命令:
npx skills add https://github.com/metabase/agent-skills --skill metabase-modular-embedding-to-modular-embedding-sdk-upgrade
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

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

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

用于搭建或维护带检索增强的 RAG 工作流,支持知识库问答和向量检索。适合处理数据接入、Embedding 生成、召回参数调整和回答引用展示。通过 npx skills add 命令从指定 GitHub 仓库安装并使用。需确认数据来源、更新频率和召回阈值,避免将未命中内容包装成确定事实。

建议结合实际业务需求设置合理的检索策略。

来源仓库内路径:skills/metabase-modular-embedding-to-modular-embedding-sdk-upgrade

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/metabase/agent-skills --skill metabase-modular…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

metabase-modular-embedding-to-modular-embedding-sdk-upgrade 怎么安装?

在终端执行 npx skills add https://github.com/metabase/agent-skills --skill metabase-modular-embedding…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

metabase-modular-embedding-to-modular-embedding-sdk-upgrade 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

metabase-modular-embedding-to-modular-embedding-sdk-upgrade 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

metabase-modular-embedding-to-modular-embedding-sdk-upgrade 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

metabase-modular-embedding-to-modular-embedding-sdk-upgrade 用的人多吗?

公开数据是累计安装 734 次,近一周安装 30 次,下载 238 次,GitHub 12 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

metabase-modular-embedding-to-modular-embedding-sdk-upgrade 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
metabase-modular-embedding-to-modular-embedding-sdk-upgrade

metabase modular embedding TO modular embedding SDK upgrade 搜索 · 本页

73412接触敏感数据未明确有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

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

  1. 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.

平台分布

Codex

38.66%
按下载量换算92

Claude

32.75%
按下载量换算78

Cursor

17%
按下载量换算40

Gemini CLI

8.28%
按下载量换算20

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills