Agent skill

officecli

Create, analyze, proofread, and modify Office documents (.docx, .xlsx, .pptx) using the officecli CLI tool. Use when the user wants to create, inspect, check formatting, find issues, add charts, or modify Office documents.

Sylinkogithub.com/SylinkoGitHub ↗
claude-codeNOASSERTION
Install
npx skills add Sylinko/Everywhere --skill OfficeCLI --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 1
SKILL.md size: 24 KB
Bundled scripts: none
Path: src/Everywhere.Core/Assets/Skills/OfficeCLI/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 6,206
Language: C#
Read our review of the source →

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

Review
written from the skill's own SKILL.md · Aug 5, 2026

What it does

Officecli is an AI-friendly CLI for .docx, .xlsx, .pptx that lets you create blank documents, view documents in multiple modes (outline, stats, issues, text, annotated, html), get nodes, query with CSS-like selectors, validate against OpenXML, and perform editing via commands like set, add, and marks. It includes a Quick Start with concrete examples for Word, Excel, and PPTX, and guidance for running in a resident mode where a file is kept in memory across commands.

How it works

The skill instructs using the built-in officecli tool (or the OfficeCLI tool in the chat window if unavailable) and requires using the exact commands. It emphasizes a read flow (L1) then DOM edit (L2) then raw XML (L3), and encourages adding --json for structured outputs. It provides command patterns for creating files (e.g., officecli create <file>), viewing with officecli view <file> <mode>, getting nodes (officecli get <file> <path> --depth N), querying (officecli query <file> <selector>), and performing edits with officecli set, officecli add, and advanced features like officecli watch for live HTML previews. It also details performance notes for a resident mode and how to flush changes via save/close around non-officecli processes.

When to use it

Use when the user wants to create, inspect, check formatting, find issues, add charts, or modify Office documents. The tool supports creating, viewing in multiple modes, extracting content, validating against OpenXML, and performing edits or additions to document components.

What it can touch

The skill references the following commands and file types: officecli executable, file paths like report.docx, slides.pptx, data.xlsx, and operations create, view, get, query, validate, set, add, watch, open, close, save. It notes the ability to pass --json for structured outputs and mentions specific modes and props without enumerating hidden internals.

Caveats

It notes a Resident Mode with 60s idle timeout on first access and a separate option to opt out via OFFICECLI_NO_AUTO_RESIDENT=1. It specifies saving and flushing behavior, and that reads like get/query/view/dump reflect latest edits, with explicit save or close before non-officecli programs read files. It mentions help guidance for property names and command syntax, and instruction to use officecli help to avoid guesswork.

From the SKILL.md

# officecli AI-friendly CLI for .docx, .xlsx, .pptx. Single binary, no dependencies, no Office installation needed. ## Usage `officecli` is a built-in tool. If it's unavailable or not exist, please instruct the user to open the `OfficeCLI` tool in the chat window. The tool allows you to call `officecli` directly without having to install or locate the executable. For any of the commands in the following instructions, do not use any other tools; you MUST use the exact tool and pass the `commandLine` parameter to execute them. --- ## Strategy **L1 (read) → L2 (DOM edit) → L3 (raw XML)**. Always prefer higher layers. Add `--json` for structured output. **Before doc work, check Specialized Skills** (bottom of this file). Fundraising decks, academic papers, financial models, dashboards, and Morph animations need their own skill loaded first — `load_skill` once, then proceed. --- ## Help System (IMPORTANT) **When unsure about property names, value formats, or command syntax, ALWAYS run help instead of guessing.** One help query beats guess-fail-retry loops. `officecli help` ≡ `officecli --help`, and `officecli <cmd> --help` ≡ `officecli help <cmd>` — same content. ```bash officecli help

What's inside
Steps it walks through
  1. Usage
  2. Strategy
  3. Help System (IMPORTANT)
  4. Performance: Resident Mode
  5. Quick Start
  6. L1: Create, Read & Inspect
  7. view modes
  8. get
  9. Stable ID Addressing
  10. query
  11. Watch & Interactive Selection
  12. get <file> selected — read what the user clicked
  13. Key properties
  14. Marks — edit proposals waiting for review
Commands it runs
officecli help                       # All commands + global options + schema entry points
officecli help docx                  # List all docx elements
officecli help docx paragraph        # Full schema: properties, aliases, examples, readbacks
officecli help docx set paragraph    # Verb-filtered: only props usable with `set`
officecli help docx paragraph --json # Structured schema (machine-readable)
officecli open report.docx    # explicitly keep in memory
officecli set report.docx ... # no file I/O overhead
officecli close report.docx   # save and release
officecli create slides.pptx
officecli add slides.pptx / --type slide --prop title="Q4 Report" --prop background=1A1A2E
About this skill
What does the officecli skill do?

Create, analyze, proofread, and modify Office documents (.docx, .xlsx, .pptx) using the officecli CLI tool. Use when the user wants to create, inspect, check formatting, find issues, add charts, or modify Office documents.

How do I install it?

Run `npx skills add Sylinko/Everywhere --skill OfficeCLI --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From Sylinko/Everywhere, a repository with 6,206 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going