Agent skill

Word Read Write

by aipoch in aipoch/medical-research-skills

Create and read Microsoft Word (.docx) documents. An agent skill from aipoch/medical-research-skills.

MITAuto-check passedDocuments & Office

Install Word Read Write

skills CLI
$ npx skills add aipoch/medical-research-skills --skill word-read-write -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install aipoch/medical-research-skills word-read-write --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/aipoch/medical-research-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/scientific-skills/Other/word-read-write .claude/skills/word-read-write && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
word-read-write
GitHub stars
2k
Token cost
~3.1k tokens
SKILL.md length
813 words
Files
65 (incl. scripts)
Skills in repo
567
Repo updated
First seen
Licence
MIT

At a glance

Create and read Microsoft Word (.docx) documents. An agent skill from aipoch/medical-research-skills.

  • Works in 2 steps: Create a .docx (Node.js) → Read/extract .docx text with Pandoc
  • You need to generate reports/letters/templates as .docx
  • SKILL.md covers When to Use, Key Features, Dependencies and Example Usage, plus 8 more sections
  • Runs Python scripts from its folder; calls npm, node and pandoc

What it does

Word Read Write is an agent skill from aipoch/medical-research-skills. Create and read Microsoft Word (.docx) documents. Use this skill when you need to generate reports/letters/templates as .docx or extract readable text from existing .docx files.

Its SKILL.md is about 3.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 69 other files, including scripts (for example `POLISH_CHANGELOG.md`, `eval_report_word-read-write_result.json` and `scripts/accept_changes.py`).

It sits in Documents & Office, covering Word documents. It works with Microsoft Word, Pandoc, Node.js and python-docx. The repository describes itself as: Hundreds of agent skills for medical research, including protocol design, data analysis, evidence insights, and academic writing. The licence is MIT.

When your agent uses it

  • You need to generate reports/letters/templates as .docx
  • Extract readable text from existing .docx files

Example prompts

  • “/word-read-write”

Requirements

  • Python 3
  • Node.js

Workflow steps

2 steps, taken from the step headings in SKILL.md.

  1. Create a .docx (Node.js)
  2. Read/extract .docx text with Pandoc

What it can do on your machine

Read from SKILL.md and the folder at commit 686e09d. 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 13 files in scripts/ (Python, from the files we listed), which the agent can run.

    Shell commands in SKILL.md call:

    • npm
    • node
    • pandoc

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npm, which can reach the network depending on how they are called.

    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

Word Read Write loads about 3.1k tokens when it runs. Until then it costs about 48 tokens; SKILL.md has 813 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~48
When it runs · the whole SKILL.md, loaded when a task matches
~3.1k

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.

SKILL.md

The full file from aipoch/medical-research-skills at commit 686e09d, republished under its MIT licence (© aipoch). 813 words, ~3,127 tokens.

Download SKILL.mdSave it as .claude/skills/word-read-write/SKILL.md (or your agent's skills folder). This skill also uses 64 other files; get the full folder from GitHub.
name
word-read-write
description
Create and read Microsoft Word (.docx) documents. Use this skill when you need to generate reports/letters/templates as .docx or extract readable text from existing .docx files.
license
MIT
author
AIPOCH

Source: https://github.com/aipoch/medical-research-skills

When to Use

  • Generate Word reports (e.g., weekly status, audit summaries) from structured data in Node.js.
  • Produce standardized memos/letters/templates with consistent page size, margins, headings, and tables.
  • Export documents that must render reliably across Microsoft Word and Google Docs (tables, shading, widths).
  • Insert images, headers/footers, page numbers, page breaks, and a table of contents programmatically.
  • Extract text from existing .docx files for indexing, review, or conversion to Markdown.

Key Features

  • Create .docx documents using the docx (docx-js) library.
  • Explicit page setup (US Letter vs A4), margins, and landscape handling.
  • Style control (default font, overriding built-in Heading styles for TOC compatibility).
  • Proper list generation (bullets/numbering via numbering config, not Unicode characters).
  • Robust table rendering rules (DXA widths, column widths + cell widths, shading, borders, padding).
  • Images with required metadata and transformations.
  • Page breaks, headers/footers, and page numbering.
  • Table of contents generation based on Word heading levels.
  • Read/extract .docx content via Pandoc conversion.

Dependencies

  • Node.js: >= 18
  • docx: ^9.0.0
  • pandoc: >= 2.0 (CLI tool for extracting/converting .docx content)

Example Usage

1) Create a .docx (Node.js)

Install

bash
npm i docx

create-doc.js

javascript
const fs = require("fs");
const {
  Document,
  Packer,
  Paragraph,
  TextRun,
  Table,
  TableRow,
  TableCell,
  ImageRun,
  Header,
  Footer,
  AlignmentType,
  BorderStyle,
  WidthType,
  ShadingType,
  PageOrientation,
  PageNumber,
  PageBreak,
  TableOfContents,
  HeadingLevel,
  LevelFormat,
} = require("docx");

const US_LETTER = { width: 12240, height: 15840 }; // DXA (1440 = 1 inch)
const MARGINS_1IN = { top: 1440, right: 1440, bottom: 1440, left: 1440 };
const CONTENT_WIDTH = US_LETTER.width - MARGINS_1IN.left - MARGINS_1IN.right; // 9360

const border = { style: BorderStyle.SINGLE, size: 1, color: "CCCCCC" };
const borders = { top: border, bottom: border, left: border, right: border };

const doc = new Document({
  styles: {
    default: {
      document: {
        run: { font: "Arial", size: 24 }, // 12pt
      },
    },
    paragraphStyles: [
      // Use exact IDs to override built-in Word heading styles
      {
        id: "Heading1",
        name: "Heading 1",
        basedOn: "Normal",
        next: "Normal",
        quickFormat: true,
        run: { size: 32, bold: true, font: "Arial" },
        paragraph: { spacing: { before: 240, after: 240 }, outlineLevel: 0 },
      },
      {
        id: "Heading2",
        name: "Heading 2",
        basedOn: "Normal",
        next: "Normal",
        quickFormat: true,
        run: { size: 28, bold: true, font: "Arial" },
        paragraph: { spacing: { before: 180, after: 180 }, outlineLevel: 1 },
      },
    ],
  },

  numbering: {
    config: [
      {
        reference: "bullets",
        levels: [
          {
            level: 0,
            format: LevelFormat.BULLET,
            text: "•",
            alignment: AlignmentType.LEFT,
            style: { paragraph: { indent: { left: 720, hanging: 360 } } },
          },
        ],
      },
      {
        reference: "numbers",
        levels: [
          {
            level: 0,
            format: LevelFormat.DECIMAL,
            text: "%1.",
            alignment: AlignmentType.LEFT,
            style: { paragraph: { indent: { left: 720, hanging: 360 } } },
          },
        ],
      },
    ],
  },

  sections: [
    {
      properties: {
        page: {
          size: {
            width: US_LETTER.width,
            height: US_LETTER.height,
            // For landscape: pass portrait dimensions and set orientation; docx swaps internally.
            // orientation: PageOrientation.LANDSCAPE,
          },
          margin: MARGINS_1IN,
        },
      },

      headers: {
        default: new Header({
          children: [new Paragraph({ children: [new TextRun("Sample Header")] })],
        }),
      },

      footers: {
        default: new Footer({
          children: [
            new Paragraph({
              children: [
                new TextRun("Page "),
                new TextRun({ children: [PageNumber.CURRENT] }),
              ],
            }),
          ],
        }),
      },

      children: [
        new Paragraph({
          heading: HeadingLevel.HEADING_1,
          children: [new TextRun("DOCX Creation Example")],
        }),

        new TableOfContents("Table of Contents", {
          hyperlink: true,
          headingStyleRange: "1-3",
        }),

        new Paragraph({
          heading: HeadingLevel.HEADING_2,
          children: [new TextRun("Lists")],
        }),

        new Paragraph({
          numbering: { reference: "bullets", level: 0 },
          children: [new TextRun("Bullet item")],
        }),
        new Paragraph({
          numbering: { reference: "numbers", level: 0 },
          children: [new TextRun("Numbered item")],
        }),

        new Paragraph({
          heading: HeadingLevel.HEADING_2,
          children: [new TextRun("Table")],
        }),

        new Table({
          width: { size: CONTENT_WIDTH, type: WidthType.DXA },
          columnWidths: [CONTENT_WIDTH / 2, CONTENT_WIDTH / 2],
          rows: [
            new TableRow({
              children: [
                new TableCell({
                  borders,
                  width: { size: CONTENT_WIDTH / 2, type: WidthType.DXA },
                  shading: { fill: "D5E8F0", type: ShadingType.CLEAR },
                  margins: { top: 80, bottom: 80, left: 120, right: 120 },
                  children: [new Paragraph("Left cell")],
                }),
                new TableCell({
                  borders,
                  width: { size: CONTENT_WIDTH / 2, type: WidthType.DXA },
                  shading: { fill: "FFFFFF", type: ShadingType.CLEAR },
                  margins: { top: 80, bottom: 80, left: 120, right: 120 },
                  children: [new Paragraph("Right cell")],
                }),
              ],
            }),
          ],
        }),

        new Paragraph({
          heading: HeadingLevel.HEADING_2,
          children: [new TextRun("Image")],
        }),

        new Paragraph({
          children: [
            new ImageRun({
              type: "png",
              data: fs.readFileSync("./image.png"),
              transformation: { width: 200, height: 150 },
              altText: { title: "Title", description: "Desc", name: "Name" },
            }),
          ],
        }),

        new Paragraph({ children: [new PageBreak()] }),

        new Paragraph({
          heading: HeadingLevel.HEADING_2,
          children: [new TextRun("New Page Section")],
        }),

        // Do not use "\n" inside TextRun; create separate Paragraphs instead.
        new Paragraph({ children: [new TextRun("This is on a new page.")] }),
      ],
    },
  ],
});

(async () => {
  const buffer = await Packer.toBuffer(doc);
  fs.writeFileSync("output.docx", buffer);
  console.log("Wrote output.docx");
})();

Run

bash
node create-doc.js
2) Read/extract .docx text with Pandoc
bash
pandoc document.docx -o output.md

Implementation Details

  • DOCX structure: .docx is a ZIP archive containing XML parts; libraries generate the required XML and package it.
  • Page sizing (DXA):
    • Word uses DXA units where 1440 DXA = 1 inch.
    • docx-js defaults to A4; for US documents set US Letter explicitly: 12240 x 15840.
    • With 1" margins, content width is 12240 - 1440 - 1440 = 9360 DXA.
  • Landscape orientation:
    • docx-js swaps width/height internally for landscape.
    • Provide portrait dimensions and set orientation: PageOrientation.LANDSCAPE.
  • Headings and TOC:
    • TOC generation requires paragraphs using HeadingLevel.*.
    • To override built-in heading appearance, use exact style IDs: "Heading1", "Heading2", etc.
    • Include outlineLevel (H1 = 0, H2 = 1, ...), otherwise TOC may not pick up headings.
  • Paragraphs vs newlines:
    • Do not embed \n in runs to simulate line breaks; create separate Paragraph elements.
  • Lists:
    • Do not manually insert Unicode bullet characters as plain text.
    • Use numbering.config with LevelFormat.BULLET / LevelFormat.DECIMAL.
    • Numbering continuity depends on reference: same reference continues; different reference restarts.
  • Tables (critical rendering rules):
    • Always use WidthType.DXA (percent widths can break in Google Docs).
    • Set table width and columnWidths; the sum of columnWidths must equal table width.
    • Set each cell width to match its corresponding column width (required for consistent rendering).
    • Cell margins are internal padding and do not add to width; they reduce usable content area.
    • For shading, prefer ShadingType.CLEAR to avoid unexpected black backgrounds.
  • Images:
    • ImageRun requires a valid type (e.g., png, jpg) and altText fields.
  • Page breaks:
    • PageBreak must be inside a Paragraph (or use pageBreakBefore: true).

When Not to Use

  • Do not proceed when required input files, identifiers, parameters, or context are missing — ask the user to provide them first.
  • Do not assume capabilities beyond this skill's declared scope when the user requests external operations or inferences.
  • Do not proceed without user confirmation when overwriting existing results, executing high-cost batch operations, or expanding task scope.
Show full SKILL.md (333 more words)Show less

Required Inputs

FieldRequiredFormat/SourceExampleIf Missing
User task descriptionYesTextResearch question, writing goal, analysis objectiveStop and ask user to provide
Primary input materialDepends on taskText, file path, ID, table, or literaturePMID, PDF, CSV, DOCX, keywords, etc.Specify which material type is missing
Output preferenceNoTextLanguage, format, target journal, templateUse skill default format

Output Contract

  • Primary output: Structured result or target file aligned with this skill's objective.
  • Optional output: Intermediate check notes, issue list, supplementary suggestions, or generated file paths.
  • Format requirement: Unless the user specifies otherwise, prefer stable, reviewable Markdown or JSON; if the skill's bundled script requires a fixed format, use that format.
  • If partially complete: Must explicitly mark as PARTIAL and state which steps are completed and which remain.

Failure Handling

  • Missing critical input: Explicitly state which fields, files, or identifiers are missing and pause.
  • Script, template, or resource execution failure: Report the failing step, likely cause, and recovery suggestions — do not silently degrade.
  • Partial completion only: Return the verified portion first, then list remaining blockers and suggested next steps.

User Checkpoints

  • Before executing batch processing, overwriting files, long-running searches, or multi-stage generation, confirm scope and output format with the user.
  • Before proceeding when a key judgment is ambiguous, evidence is insufficient, or the workflow is entering the next stage, confirm with the user.

Input Validation

This skill accepts requests that match the documented purpose of word-read-write and include enough context to complete the workflow safely.

Do not continue the workflow when the request is out of scope, missing a critical input, or would require unsupported assumptions. Instead respond:

word-read-write only handles its documented workflow. Please provide the missing required inputs or switch to a more suitable skill.

Quick Validation

  • Check that key scripts, templates, or reference file paths this skill depends on exist.
  • Check that the final output contains the core fields, sections, or files specified for this task.
  • Check that results clearly mark assumptions, limitations, and incomplete items.

© aipoch, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 64 other files (scripts) in scientific-skills/Other/word-read-write of aipoch/medical-research-skills.

  • SKILL.md
  • POLISH_CHANGELOG.md
  • eval_report_word-read-write_result.json
  • scripts/accept_changes.py
  • scripts/comment.py
  • scripts/office/helpers/merge_runs.py
  • scripts/office/helpers/simplify_redlines.py
  • scripts/office/pack.py
  • scripts/office/schemas/ISO-IEC29500-4_2016/dml-chart.xsd
  • scripts/office/schemas/ISO-IEC29500-4_2016/dml-chartDrawing.xsd
  • scripts/office/schemas/ISO-IEC29500-4_2016/dml-diagram.xsd
  • scripts/office/schemas/ISO-IEC29500-4_2016/dml-lockedCanvas.xsd
  • scripts/office/schemas/ISO-IEC29500-4_2016/dml-main.xsd
  • scripts/office/schemas/ISO-IEC29500-4_2016/dml-picture.xsd
  • scripts/office/schemas/ISO-IEC29500-4_2016/dml-spreadsheetDrawing.xsd
  • scripts/office/schemas/ISO-IEC29500-4_2016/dml-wordprocessingDrawing.xsd
  • … and 49 more

Open the folder on GitHubat commit 686e09d

Compare with similar skills

Word Read Write 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.

Word Read Write compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Word Read Write this skillaipoch/medical-research-skills2k—~3.1kAutomated safety check: PassMIT
DOCX ToolkitXiaomiMiMo/MiMo-Code14k—~2.4kAutomated safety check: PassApache-2.0
DOCXmateaix/mateclaw1.1k—~4.1kAutomated safety check: PassProprietary
DOCX Creation and Editinganthropics/skills180k6 repos~1.7kAutomated safety check: PassProprietary
WordIgorWarzocha/Opencode-Workflows122—~647Automated safety check: PassNone
Office File Processxstongxue/best-skills3k—~1.8kAutomated safety check: PassProprietary

Similar skills

  • DOCX Toolkit

    XiaomiMiMo/MiMo-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.

    14k GitHub stars~2.4k tokensUpdated 5 days ago
    Documents & OfficeAuto-check passed
  • DOCX

    mateaix/mateclaw

    A skill your agent uses whenever the user wants to create, read, edit, or manipulate Word documents (.docx files).

    1.1k GitHub stars~4.1k tokensUpdated 3 days ago
    Documents & OfficeAuto-check passed
  • DOCX Creation and Editing

    anthropics/skills

    Official

    Creates, edits and reviews Word documents: new files with docx-js, edits through the underlying XML, plus tracked changes, comments and conversions.

    180k GitHub starsUsed in 6 repos~1.7k tokens
    Documents & OfficeAuto-check passed
  • Word

    IgorWarzocha/Opencode-Workflows

    Handle Word document (.docx) creation, editing, and analysis with high-fidelity visual review.

    122 GitHub stars~647 tokensUpdated 8 mo ago
    Documents & OfficeAuto-check passed
  • Office File Process

    xstongxue/best-skills

    处理 Office 文档的一站式 skill:Word(.doc/.docx/.dotx)、Excel(.xls/.xlsx/.xlsm/.csv)、PowerPoint(.ppt/.pptx/.potx) 的创建、读取、编辑、提取、转换、校验。触发:『读取 word 文档』『提取 excel 内容』『看 ppt 讲了什么』、.doc 老格式打不开、生成/编辑 Word…

    3k GitHub stars~1.8k tokensUpdated 25 days ago
    Documents & OfficeAuto-check passed
  • Brand DOCX

    ferdinandobons/brand-docs

    Brand-aware Word engine. An agent skill from ferdinandobons/brand-docs.

    272 GitHub stars~3.8k tokensUpdated 3 mo ago
    Documents & OfficeAuto-check passed

More from aipoch/medical-research-skills

All 567 skills in this repo
  • Academic Poster Generator

    aipoch/medical-research-skills

    Complete workflow for generating academic research posters from PDF literature; use when you need to extract paper content from PDFs and produce a LaTeX-based poster…

    2k GitHub stars~2.2k tokensUpdated 21 days ago
    Auto-check passed
  • Diagnostic Study Quality Assessment Quadas

    aipoch/medical-research-skills

    Analyzes clinical diagnostic accuracy studies for bias using the QUADAS-2 tool.

    2k GitHub stars~1.4k tokensUpdated 21 days ago
    Auto-check passed
  • Exploratory Data Analysis

    aipoch/medical-research-skills

    Perform comprehensive exploratory data analysis on scientific data files across 200+ file formats.

    2k GitHub stars~3.7k tokensUpdated 21 days ago
    Auto-check passed
  • Iso Certification

    aipoch/medical-research-skills

    A toolkit for preparing ISO 13485:2016 certification documentation for medical device QMS.

    2k GitHub stars~1.8k tokensUpdated 21 days ago
    Auto-check passed
  • Journal Skills

    aipoch/medical-research-skills

    Recommends target journals for manuscript submission by analyzing the paper topic/abstract and the journal distribution of similar PubMed literature; use when users ask for journal…

    2k GitHub stars~1.7k tokensUpdated 21 days ago
    Auto-check passed
  • Latex Posters

    aipoch/medical-research-skills

    Creates academic-poster writing packages for LaTeX using beamerposter, tikzposter, or baposter.

    2k GitHub stars~1.3k tokensUpdated 21 days ago
    Auto-check passed

Questions about Word Read Write

What does Word Read Write do?

Create and read Microsoft Word (.docx) documents. An agent skill from aipoch/medical-research-skills. Word Read Write is an agent skill from aipoch/medical-research-skills.docx) documents.

When should I use Word Read Write?

Word Read Write fits situations like: you need to generate reports/letters/templates as .docx; extract readable text from existing .docx files.

How do I install Word Read Write in Claude Code?

Run `npx skills add aipoch/medical-research-skills --skill word-read-write -a claude-code`. Or copy the skill folder (scientific-skills/Other/word-read-write in aipoch/medical-research-skills) into .claude/skills/word-read-write in your project. Claude Code loads it when a task matches its description.

How do I install Word Read Write in Codex?

Run `npx skills add aipoch/medical-research-skills --skill word-read-write -a codex`. Or copy the skill folder (scientific-skills/Other/word-read-write in aipoch/medical-research-skills) into .agents/skills/word-read-write in your project. Codex loads it when a task matches its description.

Can I use Word Read Write 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 aipoch/medical-research-skills --skill word-read-write -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/word-read-write, .gemini/skills/word-read-write, .github/skills/word-read-write and .opencode/skills/word-read-write in your project.

What does Word Read Write need to run?

Going by SKILL.md and its folder, Word Read Write needs Python for the scripts in its folder and the command-line tools its instructions call (npm, node and pandoc). Our summary lists: Python 3; Node.js.

Does Word Read Write access the network?

SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Word Read Write 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 Word Read Write use?

Word Read Write is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Word Read Write use?

About 3.1k tokens (SKILL.md is roughly 13k 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 Word Read Write?

Skills that share tags, products or a category with Word Read Write: DOCX Toolkit (XiaomiMiMo/MiMo-Code, 14k stars), DOCX (mateaix/mateclaw, 1.1k stars), DOCX Creation and Editing (anthropics/skills, 180k stars) and Word (IgorWarzocha/Opencode-Workflows, 122 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Word Read Write?

aipoch (a GitHub organization) maintains it in aipoch/medical-research-skills, which has 1,974 GitHub stars. The repository holds 567 skills in this directory. The repository was last updated on September 17, 2026.

Source: aipoch/medical-research-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.