dream-num/dsh-univer-office 预览 preview

dream-num/dsh-univer-office

在DeepSeek Harness中预览、创建、编辑办公表格、文档及演示文稿。由Univer驱动。

Project Overview项目介绍

This is a native plugin built exclusively for DeepSeek Harness (DSH), designed to integrate the full Univer Office environment directly into DSH’s runtime. It enables DSH agents to create and edit a wide range of office content, including spreadsheets, documents, presentations, relational tables, and canvases. It also supports isolated worktrees and versioned changes for multi-agent collaboration. It supports import and export for all common office formats like .xlsx, .docx, and .pptx, and every change made by the agent is tracked so users can preview, approve, or discard changes directly within the DSH conversation.

After installation, users simply describe their desired office outcome in natural language, and the agent handles all steps of content creation, editing, and validation automatically. Users can follow the agent’s progress in real time directly through the DSH conversation interface, and review the final output before approving any changes. Once approved, the finished content can be exported as a standard office file that can be opened and edited in any mainstream office application like Microsoft Office or WPS Office. It is ideal for DSH users who need AI assistance for office content creation, data analysis, report writing, and presentation development.

The plugin requires Node.js version 22.19.0 or higher to run, and it is released under the open-source Apache-2.0 license, so it is free to use and modify. By default, it collects anonymous usage telemetry, but this can be disabled via a configuration setting or the DO_NOT_TRACK=1 environment variable, and telemetry never collects sensitive data like file content or file paths. No extra reverse proxy configuration is needed for remote deployments, as all access inherits DSH’s existing authentication mechanism to keep user data secure. Uninstallation can be done via a single command line: dsh plugin --profile web remove dsh-univer-office.

这是专为DeepSeek Harness(DSH)开发的原生插件,将Univer Office办公环境完整集成进DSH运行时,让DSH中的智能体能够创建、编辑电子表格、文本文档、演示文稿、关系表、画布等多种办公内容,支持多智能体协作下的隔离工作树和版本化变更管理,还能导入导出常见的.xlsx、.docx、.pptx等办公格式,所有修改都能在对话中由用户预览、批准或放弃。

安装完成后,用户只需要用自然语言描述想要的办公成果,智能体就会自动完成内容创建、编辑和验证工作,用户可以在对话中实时跟进进度,最终成果可以导出为标准办公格式,供用户在WPS、微软Office等常见软件中打开编辑。这个插件适合需要让智能体协助完成办公内容创作、数据分析、报告生成、方案演示等工作的DSH用户使用。

该插件要求Node.js版本不低于22.19.0,默认开启匿名使用数据统计,可通过设置环境变量或配置项关闭,遥测不会收集任何文件内容或路径信息。项目采用Apache-2.0开源许可,无使用成本,部署后不需要额外配置反向代理,所有访问都继承DSH原有身份验证机制,保障数据安全。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 no risk signal found未发现风险信号
  • This site's static screen found no obvious risk signal (stars, license, activity, manifest)本站静态筛查没发现明显风险信号(星标、许可证、更新活跃度、清单完整度)
DSH walks through these 9 checksDSH 会逐条核对这 9 项

Compatibility兼容性

  • DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
  • External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时(Electron / Python / Docker 等)是否齐备
  • Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突:命令名、skill / tool 重名、端口占用、重复 MCP 注册

Security安全性

  • Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致,是否归档或长期停更
  • Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
  • curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
  • Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
  • Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需(filesystem / network / shell / clipboard)
  • Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限,以及卸载与回滚方式

Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照,不能替代安全审计。

Or use CLI install (for developers)或使用命令行安装(适合开发者)

CLI Install命令行安装

dsh plugin --profile web add dsh-univer-office

把 dream-num/dsh-univer-office 加入你的 DSH 配置(web profile)即可启用。

READMEREADME

Univer × DeepSeek

DSH × Univer Office

Give DeepSeek Harness a real office environment.

Univer Office Plugin brings spreadsheets, docs, slides, canvases, relational tables, and more into one runtime — with connected data, validation, versioned changes, and isolated worktrees for multi-agent collaboration.

English · 简体中文

npm Node.js License

dsh-univer-office is the Univer office plugin for DeepSeek Harness (DSH). Tell the agent what you need and it can create or edit spreadsheets, documents, presentations, multidimensional tables, and canvases, or work with existing Excel, Word, and PowerPoint files. Every change is verified and stays in the conversation for you to preview, approve, or discard.

After installation, describe the result you want in natural language. The agent handles creation, editing, and verification while you follow the work live and review the result in the conversation. Deliver spreadsheets as Excel (.xlsx), documents as Word (.docx), and presentations as PowerPoint (.pptx) files when needed.

See it in action

Play the DSH × Univer Office demo

The agent created this spreadsheet from a natural-language request, then added conditional formatting and a chart in the same conversation. The result can be previewed, revised, merged into the current version, or discarded in place.

Reviewing a spreadsheet with conditional formatting and a chart in DSH

Deliver a standard Excel file: after review, ask the agent to export the spreadsheet as .xlsx so it can be opened and edited in Excel, WPS Office, and other compatible office applications.

See the complete workflow from request to review

1. Describe the task in natural language

Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要,完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →

← 上一个 Prev dsh-synapse 下一个 Next chatgpt-gemini-timeline →