Univer Node Backend logo

Univer Node Backend

Organization
dream-num
univer-node-backend

Run Univer Sheets, Docs, Slides, Bases, Boards, or PDFs in Node.js without browser UI. Use for server-side or backend Univer, OSS Sheets or Docs Node presets, Pro product Facades and collaboration, JSON snapshot processing, formula or Base child-process workers, or automated unit manipulation with @univerjs/rpc-node.

Overview

Publisherdream-num
Repositoryskills
Skill nameuniver-node-backend
Stars
79
Forks
7
Bundled files
4
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 4 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by dream-num on GitHub. Read the source before you install it.

Installation

Install the Univer Node Backend AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/dream-num/skills/tree/main/skills/univer-node-backend
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/dream-num/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/univer-node-backend .claude/skills/univer-node-backend
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Univer Node Backend in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Univer Node Backend on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Univer Node Backend is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Univer Node.js Backend

Run Univer without browser UI for data, document, presentation, Base, Board, and PDF automation.

Compatibility: Synced to the current Univer and Univer Pro source baseline, 1.0.0-beta.0. Keep every @univerjs/* and @univerjs-pro/* package on exactly the same version. The public OSS headless runtime supports Node.js >=18.17.0; developing the current Univer source checkout requires Node.js >=22.18 and pnpm >=10.

Public setup: Prefer createUniver with @univerjs/preset-sheets-node-core or @univerjs/preset-docs-node-core when either OSS preset fits. createUniverOnNode is the name of an example-local helper in the Univer repositories, not an exported npm API. The other four product hosts currently use manual Pro plugin stacks.

Choose the product path

Package existence, headless model/Facade support, browser rendering, and a maintained preset are separate facts:

ProductCurrent Node pathVerified current example boundary
SheetsOSS UniverSheetsNodeCorePreset; manual Pro stack for licensed featuresLocal OSS workbooks; the Pro example loads a collaborative Sheet
DocsOSS UniverDocsNodeCorePreset; manual Pro stack for licensed Docs featuresLocal document model through the OSS preset; the Pro example loads a collaborative Doc
SlidesManual @univerjs-pro/slides stack and @univerjs-pro/slides/facadeThe current Pro example loads a collaborative Slide
BasesManual @univerjs-pro/bases stack and @univerjs-pro/bases/facade; the current example pairs a Node formula workerThe current Pro example loads a collaborative Base
BoardsManual @univerjs-pro/boards stack and @univerjs-pro/boards/facadeThe current Pro example can call local createBoard(...) or load a collaborative Board
PDFsManual @univerjs-pro/pdfs stack and @univerjs-pro/pdfs/facadeThe current Pro example loads a collaborative PDF and edits its model

Slides, Bases, Boards, and PDFs have no unified Node preset in the checked source. Their current Node examples register runtime/model plugins and Facade side effects without *-ui plugins or CSS. A registered render engine satisfies model dependencies in some examples; it does not establish browser canvas rendering, screenshots, print, or exchange-client support. Read the Node plugin registry and Pro Node.js integration before composing one of these hosts.

Quick Start

1. Install the current Node preset

bash
npm install @univerjs/core@1.0.0-beta.0 @univerjs/presets@1.0.0-beta.0 @univerjs/preset-sheets-node-core@1.0.0-beta.0 rxjs@^7.8.2

2. Create and process a workbook

ts
import { LocaleType } from '@univerjs/core';
import { UniverSheetsNodeCorePreset } from '@univerjs/preset-sheets-node-core';
import UniverSheetsNodeCoreEnUS from '@univerjs/preset-sheets-node-core/locales/en-US';
import { createUniver } from '@univerjs/presets';

const { univer, univerAPI } = createUniver({
  locale: LocaleType.EN_US,
  locales: {
    [LocaleType.EN_US]: UniverSheetsNodeCoreEnUS,
  },
  presets: [UniverSheetsNodeCorePreset()],
});

try {
  const workbook = univerAPI.createWorkbook({});
  const sheet = workbook.getActiveSheet();

  sheet.getRange('A1').setValue(123);
  sheet.getRange('B1').setValue('=SUM(A1) * 6');
  await univerAPI.getFormula().onCalculationResultApplied();

  console.log(sheet.getRange('B1').getValue()); // 738
  console.log(workbook.save());
} finally {
  univer.dispose();
}

The preset registers the core Sheets, formula, data-validation, filter, hyperlink, drawing, sort, and thread-comment plugins plus their Node-safe Facade extensions.

Formula Worker

Pass a built JavaScript worker path to the preset. @univerjs/rpc-node uses node:child_process.fork(), not a browser Worker.

ts
// main.ts (ESM)
import { fileURLToPath } from 'node:url';
import { LocaleType } from '@univerjs/core';
import { UniverSheetsNodeCorePreset } from '@univerjs/preset-sheets-node-core';
import UniverSheetsNodeCoreEnUS from '@univerjs/preset-sheets-node-core/locales/en-US';
import { createUniver } from '@univerjs/presets';

const workerSrc = fileURLToPath(new URL('./formula-worker.js', import.meta.url));
const { univer, univerAPI } = createUniver({
  locale: LocaleType.EN_US,
  locales: {
    [LocaleType.EN_US]: UniverSheetsNodeCoreEnUS,
  },
  presets: [UniverSheetsNodeCorePreset({ workerSrc })],
});
ts
// formula-worker.ts; compile it to formula-worker.js before running main.ts
import { LocaleType } from '@univerjs/core';
import { UniverSheetsNodeCoreWorkerPreset } from '@univerjs/preset-sheets-node-core/worker';
import { createUniver } from '@univerjs/presets';

createUniver({
  locale: LocaleType.EN_US,
  presets: [UniverSheetsNodeCoreWorkerPreset()],
});

The worker preset includes UniverRPCNodeWorkerPlugin and UniverRemoteSheetsFormulaPlugin. Do not replace the latter with the main-thread UniverSheetsFormulaPlugin.

Node-Specific Rules

ConcernBrowserNode.js
SetupBrowser preset or manual UI pluginsSheets/Docs Node preset, or a source-verified manual Pro product stack
UIUniverUIPlugin, *-ui, CSSOmit
RPC mainUniverRPCMainThreadPlugin with workerURLUniverRPCNodeMainPlugin with workerSrc
RPC workerUniverRPCWorkerThreadPluginUniverRPCNodeWorkerPlugin
Formula worker bridgeUniverRemoteSheetsFormulaPluginUniverRemoteSheetsFormulaPlugin
ThemeRuntime theme and CSS required for UINot needed for data-only processing

Facade imports

The Sheets Node preset loads its documented Facade side effects. The Docs Node preset loads only the formula Facade; import @univerjs/docs/facade before calling createDocument(...). With manual registration, import the Facade entry for every API surface used and exclude @univerjs/ui/facade and *-ui/facade. Read the Node plugin registry before assembling a manual plugin or Facade list.

Pro on Node.js

For the six-product Pro Node matrix, exact runtime/Facade stacks, formula and Base workers, model-only chart/shape boundaries, and collaboration, read Pro Node.js integration.

References

  • Node plugin registry — six-product support matrix, current preset contents, manual plugins, Facade allowlist, worker pairing, and browser-only exclusions
  • Node common tasks — batch reports, JSON snapshots, formula barriers, custom functions, events, and resource cleanup
  • Pro Node.js integration — exact six-product Pro stacks, formula/Base workers, collaboration socket adapter, license handling, and current headless limitations

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Univer Node Backend AI skill do?

Run Univer Sheets, Docs, Slides, Bases, Boards, or PDFs in Node.js without browser UI. Use for server-side or backend Univer, OSS Sheets or Docs Node presets, Pro product Facades and collaboration, JSON snapshot processing, formula or Base child-process workers, or automated unit manipulation with @univerjs/rpc-node.

Why use Univer Node Backend on TypingMind?

Because you install it once and use it with any model. Univer Node Backend is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Univer Node Backend in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/dream-num/skills/tree/main/skills/univer-node-backend. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Univer Node Backend?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Univer Node Backend?

As many as you like. As long as a model supports skills, you can use Univer Node Backend with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Univer Node Backend AI skill free?

Yes. It is published on GitHub by dream-num under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇