A command-line tool for creating, inspecting, checking, importing, exporting, and reviewing Univer files, including spreadsheets, documents, slides, databases, and canvases.

It helps automate file authoring, inspect models, embed different file types, use isolated worktrees, capture screenshots, verify results, and hand files to viewers.

It gives developers a terminal-based way to work with complex .univer files and review their contents without relying only on a graphical editor.

univer-cli — Skill for Claude Code and Codex by dream-num: A command-line tool for creating, inspecting, checking, importing, exporting…

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add skills/dream-num/skills/univer-cli

Any agent

npx skills add dream-num/skills --skill univer-cli

Clone the repo

git clone --depth 1 https://github.com/dream-num/skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/dream-num/skills/univer-cli.svg)](https://agentmods.dev/skills/dream-num/skills/univer-cli)

Your own site

<a href="https://agentmods.dev/skills/dream-num/skills/univer-cli"><img src="https://agentmods.dev/badge/skills/dream-num/skills/univer-cli.svg" alt="Measured on agentmods" height="20"></a>

Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,026 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00057	$0.01026
Opus 5	$0.00028	$0.00513
Sonnet 5	$0.00011	$0.00205
Haiku 4.5	$0.00006	$0.00103

Measured 5d ago against content hash e5357bb0512d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

univer-cli scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/univer-cli/SKILL.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Univer CLI

Terminal-native authoring and inspection for multi-Unit .univer files. The CLI provides isolated worktrees, version-matched Facade guidance, model readback, and browser review.

Install:

npm install -g univer-cli
univer doctor

Keep the CLI current

Use these commands to compare the installed CLI with the latest public release:

univer --version
npm view univer-cli@latest version --registry=https://registry.npmjs.org/

When a newer version is available, complete the current Univer task before updating:

univer update
univer doctor --json
univer skills get core

If univer update reports that the shared daemon must stop, rerun it with --force after confirming that stopping the daemon is safe. Reload core and the target Unit Skill after every update.

Start here

This file is the discovery entry, not the operational guide. Before using Univer commands for a task, load the complete core Skill from the installed CLI:

univer skills get core          # shared model, workflow, evidence, and handoff
univer skills get core --full   # include direct references and templates

Runtime Skills ship with the CLI so their commands and Facade APIs match the installed version.

Core Model

A .univer path is the authoritative multi-Unit target. Always address the file explicitly.
A Unit is a top-level Sheet, Doc, Slide, Base, or Board identified by unitId; sheet names, pages, tables, ranges, shapes, and records live inside that Unit.
trunk is the reviewed main line. A worktree is an isolated scope for agent changes; there is no implicit current worktree.
Command success is not correctness evidence. Read back the target model, verify task-specific assertions, and inspect rendered output when appearance matters.

Use public CLI and Facade surfaces. The worktree commit path is the durable write boundary, and merge remains an explicit review decision.

Unit Skills

After core, load the Skill matching the target top-level Unit before authoring:

Read the full file on GitHub · 126 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

5d ago First seen · 126 lines · 57 tokens per session scan A e5357bb0512d

Subscribe to this mod's changes

univer-cli is a skill published in the GitHub repository dream-num/skills (65 stars, last pushed 3d ago), licensed Apache-2.0. It adds 57 tokens to every session and 1,026 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Documents Spreadsheets agent-skills ai-agent claude-code claude-code-skills openai-codex spreadsheet

add-excel

Adds Excel Online (Business) connector to a Power Apps code app. Use when reading or writing Excel workbook data from OneDrive or SharePoint.

microsoft/power-platform-skills · 33 tokens

csv-to-sif

Export a project's FF&E product-library CSV as dealer-system SIF. Use to produce a .sif schedule; use sif-to-csv for the reverse direction.

AlpacaLabsLLC/skills-for-architects · 38 tokens

product-data-cleanup

Clean a local FF&E CSV schedule by normalizing casing, dimensions, units, language, materials, and formatting. Use when asked to clean, fix, or standardize product data.

AlpacaLabsLLC/skills-for-architects · 42 tokens

product-data-import

Generate a formatted FF&E specification schedule from notes, CSV, or pasted lists and optionally save it to the project's 33-column CSV library. Use when asked to import products or build a schedule.

AlpacaLabsLLC/skills-for-architects · 43 tokens

sif-to-csv

Parse a SIF (Standard Interchange Format) input into a readable preview and optionally append canonical product rows to the project's CSV library. Use when asked to convert or inspect SIF dealer data. For the reverse direction use /as:csv-to-sif.

AlpacaLabsLLC/skills-for-architects · 58 tokens

pm-feedback

Классифицирует пользовательский фидбек (Excel/CSV/текст) по 6 категориям, делает sentiment-анализ, кластеризацию тем, анализ трендов, триангуляцию по источникам, расчёт NPS и извлечение персон. На выходе — Top-10 болей с рекомендациями к действию. User-invoked only — do NOT auto-trigger. Triggers on /pm-feedback…

serejaris/personal-corp-os · 132 tokens