Install the "docx-official" agent skill from https://github.com/XiaomiMiMo/MiMo-Code/tree/main/packages/cli/src/skill/builtin/.bundle/docx-official into .claude/skills/docx-official/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "docx-official", then confirm the skill loads.
Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
skills CLI
$ npx skills add XiaomiMiMo/MiMo-Code --skill docx-official -a codex
Project install goes to .agents/skills/; add -g for ~/.codex/skills/.
Install the "docx-official" agent skill from https://github.com/XiaomiMiMo/MiMo-Code/tree/main/packages/cli/src/skill/builtin/.bundle/docx-official into .agents/skills/docx-official/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "docx-official", then confirm the skill loads.
Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
skills CLI
$ npx skills add XiaomiMiMo/MiMo-Code --skill docx-official -a cursor
Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.
Install the "docx-official" agent skill from https://github.com/XiaomiMiMo/MiMo-Code/tree/main/packages/cli/src/skill/builtin/.bundle/docx-official into .cursor/skills/docx-official/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "docx-official", then confirm the skill loads.
Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
skills CLI
$ npx skills add XiaomiMiMo/MiMo-Code --skill docx-official -a gemini-cli
Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.
Install the "docx-official" agent skill from https://github.com/XiaomiMiMo/MiMo-Code/tree/main/packages/cli/src/skill/builtin/.bundle/docx-official into .gemini/skills/docx-official/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "docx-official", then confirm the skill loads.
Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
skills CLI
$ npx skills add XiaomiMiMo/MiMo-Code --skill docx-official -a github-copilot
Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.
Install the "docx-official" agent skill from https://github.com/XiaomiMiMo/MiMo-Code/tree/main/packages/cli/src/skill/builtin/.bundle/docx-official into .github/skills/docx-official/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "docx-official", then confirm the skill loads.
GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
skills CLI
$ npx skills add XiaomiMiMo/MiMo-Code --skill docx-official -a opencode
OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
Install the "docx-official" agent skill from https://github.com/XiaomiMiMo/MiMo-Code/tree/main/packages/cli/src/skill/builtin/.bundle/docx-official into .opencode/skills/docx-official/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "docx-official", then confirm the skill loads.
OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
Skill name
docx-official
GitHub stars
14k
Token cost
~2.4k tokens
SKILL.md length
910 words
Files
14 (incl. scripts)
Skills in repo
22
Repo updated
First seen
Licence
Apache-2.0
At a glance
Produces, edits and reads Microsoft Word files through python-docx and lxml, with a decision table for picking the lightest workflow for a given task.
Works in 7 steps: Rely on named styles. Use Heading 1,… → One idea per paragraph. Long paragraphs… → Structure first, prose second. Draft the… → …
Drafting a report, contract or letter as a new Word document
SKILL.md covers Decision matrix, One-time environment setup, Common commands and Authoring principles, plus 5 more sections
Runs Python scripts from its folder; calls uv, python3 and soffice
What it does
Built from scratch against the ECMA-376 / ISO/IEC 29500 specification rather than a proprietary library, the skill picks one of several paths depending on the job: authoring from scratch with python-docx when there is no source file, in-place placeholder replacement when a template just needs filling, an explode-edit-XML-reassemble workflow for deep structural changes, or a dedicated extraction pipeline when only text or metadata is needed. A LibreOffice-based script can render a PDF preview for QA.
Every script carries inline PEP 723 dependency metadata so uv run resolves python-docx and lxml automatically, and a bundled runtime variable lets the skill skip package installation entirely when one is preconfigured. Mixed tasks are expected to follow read, then plan, then edit or create, then validate, in that order.
When your agent uses it
Drafting a report, contract or letter as a new Word document
Filling an existing Word template while keeping its styling
Making a deep structural edit to a .docx that in-place editing cannot reach
Extracting text, structure or metadata from a Word file
Example prompts
“Fill this RFP template with our company details, keeping its styles intact.”
“Extract all the headings and tables from this .docx into plain text.”
“Restructure this document with new sections using the explode and reassemble workflow.”
“Render a PDF preview of this draft so I can check the layout.”
Requirements
Python with python-docx and lxml (resolved automatically by uv run)
LibreOffice, optional, for PDF previews
Workflow steps
7 steps, taken from the first numbered list in SKILL.md.
1Rely on named styles. Use Heading 1, Heading 2, Normal, Title, Quote, List Bullet, List Number, Caption. They are what makes Word's ToC…
2One idea per paragraph. Long paragraphs are fine; run-on paragraphs are not. Break at logical boundaries.
3Structure first, prose second. Draft the heading tree, then write inside it. Reviewers scan headings before words.
4Tables for tabular data only. Do not use tables to fake multi-column layouts — export to PDF and users see the borders through the layout.
5Line length is set by page margins, not by hard breaks. Never insert manual line breaks to control wrapping.
6Use fields, not literal text, for things that change — page numbers, dates, ToC, cross-references. python-docx supports field codes via…
7Every image needs alt text — accessibility, and Word screams at you in review mode when it's missing.
What it can do on your machine
Read from SKILL.md and the folder at commit 6babeb0. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 8 files in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
uv
python3
soffice
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
ecma-international.org
peps.python.org
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
DOCX Toolkit loads about 2.4k tokens when it runs. Until then it costs about 156 tokens; SKILL.md has 910 words of instructions outside code blocks.
Always· name and description, kept in context so the agent knows when to use it
~156
When it runs· the whole SKILL.md, loaded when a task matches
~2.4k
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
Download SKILL.mdSave it as .claude/skills/docx-official/SKILL.md (or your agent's skills folder). This skill also uses 13 other files; get the full folder from GitHub.
name
docx-official
description
Use this skill whenever a Microsoft Word (.docx) file is being produced, opened, transformed, or read. That includes: drafting reports, letters, contracts, RFPs, technical documents, or any long-form written deliverable; extracting text or structure from an existing Word file; filling a Word template with values; converting Word to PDF or plain text; splitting or merging documents; inspecting styles, headings, sections, tables, images, comments, or tracked changes. Trigger on mentions of 'Word doc', 'DOCX', 'Office document', a filename ending in .docx, or requests like 'turn this into a Word report'.
license
Apache-2.0 — see LICENSE for terms and third-party attributions
DOCX Skill
An Apache-2.0 toolkit for producing, editing, and reading Microsoft Word (.docx) files. Written from scratch against the public ECMA-376 / ISO/IEC 29500 specification and built on permissively-licensed tooling (python-docx MIT, lxml BSD-3-Clause, optional external binaries pandoc and soffice) so it can be reused in commercial projects without restriction.
Decision matrix
Situation
Path
Read first
No source file — build a document from a prompt / data
If the task mixes several of these, do them in this order: read → plan → edit/create → validate.
One-time environment setup
Bundled runtime: when the MIMO_PYTHON environment variable is set, skip uv/python3 and pip installs entirely — run every command below with uv run replaced by "$MIMO_PYTHON" (e.g. "$MIMO_PYTHON" scripts/extract_text.py input.docx). This skill's Python dependencies are preinstalled in that interpreter; pip console scripts are unavailable, so always go through "$MIMO_PYTHON" -m <module>. A bundled LibreOffice is exposed as MIMO_SOFFICE and picked up automatically by the scripts here.
All scripts include PEP 723 inline metadata, so uv run resolves dependencies automatically — no manual install step needed. Just run:
Alternatively, if this skill lives in a persistent workspace you can uv init a project, uv add python-docx lxml, and run scripts with uv run scripts/... from the project root — this gives you a lockfile and reproducible environment.
All scripts here use the standard library plus python-docx. No proprietary dependencies.
Common commands
bash
# 1. Extract plain text (best for "what does this file say?" questions)
uv run scripts/extract_text.py input.docx > input.txt
# 2. Explode a .docx into readable XML for structural surgery
uv run scripts/explode.py input.docx exploded/
# 3. Assemble an exploded directory into a fresh .docx
uv run scripts/assemble.py exploded/ output.docx
# 4. Render a .docx as PDF (used for visual QA)
uv run scripts/render_pdf.py output.docx # writes output.pdf next to it
# 5. Well-formedness check (ZIP integrity + parseable XML + python-docx open)
uv run scripts/audit.py output.docx
# 6. Accept every tracked change without needing Word/LibreOffice
uv run scripts/resolve_revisions.py reviewed.docx clean.docx
# 7. Add a comment to an exploded directory
uv run scripts/annotate.py exploded/ "Please check" --author "Reviewer" --anchor "text"
Every script is a small, self-contained Python file. Read the top of the file for full CLI options.
Authoring principles
Word is a flowing document format, not a slide surface. Users expect it to look like something a human wrote in Word — not a design tool trying to reinvent typography. Keep that in mind:
Rely on named styles. Use Heading 1, Heading 2, Normal, Title, Quote, List Bullet, List Number, Caption. They are what makes Word's ToC, navigation pane, and cross-references work.
One idea per paragraph. Long paragraphs are fine; run-on paragraphs are not. Break at logical boundaries.
Structure first, prose second. Draft the heading tree, then write inside it. Reviewers scan headings before words.
Tables for tabular data only. Do not use tables to fake multi-column layouts — export to PDF and users see the borders through the layout.
Line length is set by page margins, not by hard breaks. Never insert manual line breaks to control wrapping.
Use fields, not literal text, for things that change — page numbers, dates, ToC, cross-references. python-docx supports field codes via low-level XML (see edit.md).
Every image needs alt text — accessibility, and Word screams at you in review mode when it's missing.
Typography defaults (safe starting point)
Element
Font
Size
Weight
Notes
Title
Calibri Light
28pt
Bold
Centered or left, one line
Heading 1
Calibri Light
18pt
Bold
Space before 12pt
Heading 2
Calibri Light
14pt
Bold
Space before 10pt
Heading 3
Calibri
12pt
Bold
Space before 6pt
Body
Calibri
11pt
Regular
Line spacing 1.15, space after 6pt
Caption
Calibri
9pt
Italic
Muted gray #595959
Code / mono
Consolas
10pt
Regular
Left-aligned, no first-line indent
Change the palette for the topic — muted navy #1F3A5F for legal/finance, warm charcoal #2E2A26 for editorial. Avoid pure #000000 for body text; #1F1F1F reads softer on print.
Show full SKILL.md (352 more words)Show less
Page setup (A4 vs Letter)
Ask the user which one to use. If you cannot ask, default to the region implied by the language (Chinese/European → A4, US English → Letter). Margins:
Size
Width × Height
Standard margins (T/B/L/R)
A4
21.0 × 29.7 cm
2.54 / 2.54 / 3.18 / 3.18 cm
Letter
8.5 × 11.0 in
1.00 / 1.00 / 1.25 / 1.25 in
QA checklist — always run before declaring done
Assume something is wrong. Word files fail silently: a broken relationship, an unclosed <w:p>, a missing style — Word will still open the file but strip content or throw a "content had problems" warning. Verify explicitly.
Open cleanly — no repair prompt.bash
uv run python -c "import docx; docx.Document('output.docx')" # loads without exceptions
Text integrity — no placeholder residue.bash
uv run scripts/extract_text.py output.docx | grep -Ei "TODO|TBD|\{\{|lorem|xxxx"
Grep must return nothing.
Visual sanity — render a PDF, open the first and last pages, scan for:
Widowed headings alone at the bottom of a page.
Tables split awkwardly across pages.
Images pushed to their own page because they exceeded content width.
Style hygiene — every heading uses a real style, not just bold+large text:bash
uv run python -c "
import docx; d = docx.Document('output.docx')
for p in d.paragraphs:
if p.text and p.style.name == 'Normal' and p.runs and p.runs[0].bold:
print('possible fake heading:', p.text[:80])"
If any of these fail, fix and re-run — don't paper over.
What is out of scope
.doc (legacy Word 97-2003) — this skill only targets .docx (Office Open XML). Convert .doc to .docx with LibreOffice first: soffice --headless --convert-to docx old.doc.
Live collaborative editing — the Word online API is a separate concern; here we produce and modify files.
Macros / VBA — do not generate .docm files. If the user asks for automation, offer a Python script that regenerates the doc instead.
Where each detail lives
Creating from scratch: create.md — headings, paragraphs, styles, tables, images, page setup, headers/footers, tables of contents.
Editing / templating: edit.md — placeholder replacement, section swap, raw XML surgery, tracked changes, comments.
DOCX Toolkit next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
Creates, reads, edits and templates Word .docx files with python-docx scripts, including tracked changes, comments, tables of contents and health checks.
Lets one MiMoCode process drive another, headless with JSON events or interactively through tmux, to test behavior and visual regressions with parseable evidence.
Builds, edits, cleans, recalculates and reads Excel workbooks and CSV files with openpyxl and pandas, plus LibreOffice for recalculation and PDF export.
Hands coding work to the Claude Code CLI from the terminal in print, interactive tmux or background mode, only when you explicitly ask for Claude Code.
Produces, edits and reads Microsoft Word files through python-docx and lxml, with a decision table for picking the lightest workflow for a given task. Built from scratch against the ECMA-376 / ISO/IEC 29500 specification rather than a proprietary library, the skill picks one of several paths depending on the job: authoring from scratch with python-docx when there is no source file, in-place placeholder replacement when a template just needs filling, an explode-edit-XML-reassemble workflow for deep structural changes, or a dedicated extraction pipeline when only text or metadata is needed. A LibreOffice-based script can render a PDF preview for QA.
When should I use DOCX Toolkit?
DOCX Toolkit fits situations like: drafting a report, contract or letter as a new Word document; filling an existing Word template while keeping its styling; making a deep structural edit to a .docx that in-place editing cannot reach; extracting text, structure or metadata from a Word file.
How do I install DOCX Toolkit in Claude Code?
Run `npx skills add XiaomiMiMo/MiMo-Code --skill docx-official -a claude-code`. Or copy the skill folder (packages/cli/src/skill/builtin/.bundle/docx-official in XiaomiMiMo/MiMo-Code) into .claude/skills/docx-official in your project. Claude Code loads it when a task matches its description.
How do I install DOCX Toolkit in Codex?
Run `npx skills add XiaomiMiMo/MiMo-Code --skill docx-official -a codex`. Or copy the skill folder (packages/cli/src/skill/builtin/.bundle/docx-official in XiaomiMiMo/MiMo-Code) into .agents/skills/docx-official in your project. Codex loads it when a task matches its description.
Can I use DOCX Toolkit in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add XiaomiMiMo/MiMo-Code --skill docx-official -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/docx-official, .gemini/skills/docx-official, .github/skills/docx-official and .opencode/skills/docx-official in your project.
What does DOCX Toolkit need to run?
Going by SKILL.md and its folder, DOCX Toolkit needs Python for the scripts in its folder and the command-line tools its instructions call (uv, python3 and soffice). Our summary lists: Python with python-docx and lxml (resolved automatically by uv run); LibreOffice, optional, for PDF previews.
Does DOCX Toolkit access the network?
SKILL.md names 2 domains. As links in the text: ecma-international.org and peps.python.org. This is read from the text; nothing was executed.
Is DOCX Toolkit safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does DOCX Toolkit use?
DOCX Toolkit is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does DOCX Toolkit use?
About 2.4k tokens (SKILL.md is roughly 9.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to DOCX Toolkit?
Skills that share tags, products or a category with DOCX Toolkit: DOCX Creation and Editing (anthropics/skills, 180k stars), Office File Process (xstongxue/best-skills, 2.9k stars), Huashu Markdown Publishing Pipeline (alchaincyf/huashu-md-html, 908 stars) and Word DOCX Toolkit (NousResearch/hermes-agent, 252k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains DOCX Toolkit?
XiaomiMiMo (a GitHub organization) maintains it in XiaomiMiMo/MiMo-Code, which has 13,601 GitHub stars. The repository holds 22 skills in this directory. The repository was last updated on October 3, 2026.
Source: XiaomiMiMo/MiMo-Code on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.
