Officecli Skills logo

Officecli Skills

Community
mingchen666
officecli-skills

Unified OfficeCLI skill for creating, reading, and editing Office files. Use for any .docx, .pptx, or .xlsx task, including Word documents, PowerPoint decks, Excel workbooks, academic papers, pitch decks, financial models, dashboards, and fillable Word forms. This is the only top-level OfficeCLI skill; route to the specific reference files under references/ as needed.

Overview

Publishermingchen666
RepositoryReviva
Skill nameofficecli-skills
Stars
293
Forks
31
Bundled files
9
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.

  • 9 bundled files

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

  • Open source

    Published by mingchen666 on GitHub. Read the source before you install it.

Installation

Install the Officecli Skills 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/mingchen666/Reviva/tree/main/electron/builtin-assets/skills/officecli-skills
  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/mingchen666/Reviva.git /tmp/Reviva
mkdir -p .claude/skills
cp -r /tmp/Reviva/electron/builtin-assets/skills/officecli-skills .claude/skills/officecli-skills
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Officecli Skills 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 Officecli Skills 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 Officecli Skills 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.

OfficeCLI

OfficeCLI is the unified Office skill for .docx, .pptx, and .xlsx work. It covers reading, creating, and editing Office files through Reviva's controlled tools and the local officecli runtime.

This is the top-level router skill. Do not load every reference file by default. Load only the reference files needed for the current task.

Runtime Setup

Use the shared Reviva OfficeCLI runtime:

  • Reviva on Windows prefers the bundled officecli binary.
  • If the bundled binary is missing or unavailable, Reviva falls back to system officecli from PATH.
  • Check availability in 设置 > 环境检测 > OfficeCLI.
  • Do not run install commands automatically unless the user explicitly asks.
  • When a property, path, enum, or element name is uncertain, ask officecli help <format> <element> --json before guessing.

Reference files may contain legacy standalone Setup sections copied from their original skills. Treat this section as authoritative inside Reviva.

Reference files may also keep their original YAML frontmatter names, such as officecli-docx or officecli-xlsx. Treat those names as source metadata only. The recommended top-level skill to bind is this unified officecli-skills skill.

Tool Pairing

Office work is a Skill + Tool pairing:

  • Skill: decides how to plan and structure the Office artifact.
  • Tool: decides whether the Agent may actually read, create, or edit files.

Expected tool pairing:

  • office_read: bottom-level precise reader for .docx, .pptx, .xlsx; general document reading should go through document_read when available.
  • office_write: create and edit .docx, .pptx, .xlsx; write capability and should be explicitly enabled.

If office_write is unavailable, plan the work and explain what would be changed, but do not claim the file was created or edited.

Routing

Choose the smallest set of references that covers the request.

User intentReferences
General Word document, report, memo, letter, proposal, docx editingreferences/docx.md
Academic paper, thesis, citation style, bibliography, footnotes/endnotes, equations, cross-referencesreferences/docx.md + references/academic-paper.md
Fillable Word form, content controls, form fields, mail merge, protected form, contract/SOW templatereferences/word-form.md
General PowerPoint deck, slides, presentation, template, speaker notes, commentsreferences/pptx.md
Fundraising deck, investor deck, seed/Series A/B/C pitchreferences/pptx.md + references/pitch-deck.md
General Excel workbook, spreadsheet, tracker, CSV import, formulas, charts, pivot tablesreferences/xlsx.md
Financial model, 3-statement, DCF, LBO, SaaS unit economics, sensitivity/scenario analysisreferences/xlsx.md + references/financial-model.md
Excel dashboard, KPI dashboard, executive dashboard, CSV to dashboard, analytics dashboardreferences/xlsx.md + references/data-dashboard.md

Reverse routing rules:

  • Do not use pitch-deck for a generic board review, sales deck, all-hands, or product launch. Use pptx.
  • Do not use financial-model for a simple budget tracker, CSV dump, or operational KPI sheet. Use xlsx.
  • Do not use data-dashboard for a one-chart weekly report or simple formatted table. Use xlsx.
  • Do not use academic-paper for ordinary reports or memos. Use docx.
  • Do not use word-form for non-fillable documents. Use docx.

Standard Workflow

Existing Files

  1. Identify the file format from extension.
  2. Load only the necessary references.
  3. Read the file first with office_read(mode="overview"); do not edit blind.
  4. Read relevant text, outline, stats, issues, or images as needed.
  5. Plan the edits as structured actions.
  6. Execute through office_write only when write access is available.
  7. Re-read or inspect the result enough to summarize what changed.

New Files

  1. Identify target format and output path.
  2. Load the necessary references.
  3. Build a concise artifact plan: structure, layout, data model, or slide/page list.
  4. Execute creation through office_write(operation="create").
  5. Inspect the result with office_read or relevant OfficeCLI views.
  6. Return the output path and a short creation summary.

Safety

  • Default to creating a new output file instead of overwriting the source.
  • Never claim an edit happened unless office_write returned success.
  • Do not expose arbitrary officecli command execution as the product interface.
  • Prefer typed actions over raw XML.
  • raw-set is a last-resort bridge and should remain disabled unless the product explicitly enables a narrow, template-backed action.
  • For destructive actions like remove, require precise paths and keep the scope narrow.
  • Do not write outside authorized workspace paths.
  • Do not use cloud knowledge-base documents as local files; use kb_search for cloud knowledge.

Action Layers

Prefer these layers in order:

  1. High-level structured actions: add_heading, add_table, add_picture, add_chart, set_cell, set_range, add_slide, replace_text.
  2. Typed OfficeCLI primitives: add, clone, set, remove, query, get.
  3. Dotted properties inside typed primitives, such as font.color, pbdr.bottom, calc.fullCalcOnLoad.
  4. batch through office_write(useBatch=true) for many stable actions.
  5. raw_set through explicit allowRawXml=true and per-action confirm=true when typed actions cannot express the required OpenXML change.

Inside Reviva, office_write exposes common actions plus format shortcuts:

  • Word: paragraphs, headings, tables, pictures, comments, fields, headers, footers, form controls.
  • PowerPoint: slides, shapes, text boxes, pictures, charts, speaker notes, connectors.
  • Excel: sheets, cells, ranges, formulas, tables, charts, defined names.

For uncommon elements or uncertain props, call office_write(operation="help", format, element, verb) before creating actions.

Use useBatch=true when applying many stable actions, especially Excel formulas/ranges, PPT layout construction, and form field batches. The Agent may decide this per task. Avoid batch for exploratory edits where individual warning output is important.

Use raw_set only for documented OfficeCLI fallback cases such as SDT dropdown items, date formats, field cache patches, workbook activeTab, or targeted XML cleanup. The Agent may decide this when typed actions cannot express the change, but must set allowRawXml=true and confirm=true on each raw action. Prefer typed set when a dotted property exists. Reviva forces post-write issues/validate checks for batch and raw_set.

QA Expectations

Do not treat validate as proof of quality. Each format has different failure modes:

  • Word: heading hierarchy, TOC/footer fields, placeholder leakage, layout rhythm.
  • PowerPoint: overflow, dark-on-dark text, misalignment, missing alt text, missing speaker notes in pitch decks.
  • Excel: formula errors, stale cached values, ### overflow, chart title/series placeholders, cross-sheet formula quoting.
  • Word forms: missing SDT alias/tag, unlocked protected regions, broken field names, placeholder leakage.

Use the relevant reference file's QA section for format-specific checks.

Reference Files

The long-form rules live under references/:

  • references/docx.md
  • references/pptx.md
  • references/xlsx.md
  • references/academic-paper.md
  • references/pitch-deck.md
  • references/financial-model.md
  • references/data-dashboard.md
  • references/word-form.md

Read only what the task requires.

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 Officecli Skills AI skill do?

Unified OfficeCLI skill for creating, reading, and editing Office files. Use for any .docx, .pptx, or .xlsx task, including Word documents, PowerPoint decks, Excel workbooks, academic papers, pitch decks, financial models, dashboards, and fillable Word forms. This is the only top-level OfficeCLI skill; route to the specific reference files under references/ as needed.

Why use Officecli Skills on TypingMind?

Because you install it once and use it with any model. Officecli Skills 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 Officecli Skills in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mingchen666/Reviva/tree/main/electron/builtin-assets/skills/officecli-skills. 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 Officecli Skills?

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 Officecli Skills?

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

Is the Officecli Skills AI skill free?

It is published on GitHub by mingchen666. Check the repository for licensing terms. 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 👇