Claude Skill

docx

Extract text from Microsoft Word documents

LLM Mart · 0 points · 17 43 0

Virus-scanned Reviewed automatically before listing.

Full trust report

Download axoviq-ai-synthadoc-synthadoc_skills_docx-8dee0ee.zip · 1 KB

axoviq-ai/synthadoc 1226 123 forks AGPL-3.0 Updated 5d ago

Part of axoviq-ai/synthadoc — 10 skills

Install

skills CLI npx skills add https://github.com/axoviq-ai/synthadoc/tree/main/synthadoc/skills/docx

Claude Code claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install axoviq-ai-synthadoc@llmmart

Git git clone https://github.com/axoviq-ai/synthadoc.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole axoviq-ai/synthadoc collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

DOCX Skill

Extracts paragraph text from .docx files using python-docx.

Setup

pip install python-docx

Standalone usage

import asyncio
from synthadoc.skills.docx.scripts.main import DocxSkill

skill = DocxSkill()

async def main():
    result = await skill.extract("/path/to/document.docx")
    print(result.text)      # all paragraphs joined as plain text

asyncio.run(main())

When this skill is used

Source path ends with .docx
User intent contains: word document, docx

Files (synthadoc)

scripts

main.py 905 B

# SPDX-License-Identifier: AGPL-3.0-or-later
# Copyright (C) 2026 Paul Chen / axoviq.com
from docx import Document
from synthadoc.skills.base import BaseSkill, ExtractedContent, SkillMeta


class DocxSkill(BaseSkill):
    meta = SkillMeta(name="docx", description="Extract text from Word documents",
                     extensions=[".docx"])

    async def extract(self, source: str) -> ExtractedContent:
        try:
            doc = Document(source)
        except Exception as exc:
            raise ValueError(
                f"Cannot read '{source}' as a Word document: {exc}. "
                "Ensure the file is a valid .docx (Office Open XML) document."
            ) from exc
        text = "\n".join(p.text for p in doc.paragraphs if p.text.strip())
        return ExtractedContent(text=text, source_path=source,
                                metadata={"paragraphs": len(doc.paragraphs)})

__init__.py 0 B

requirements.txt 12 B
```
python-docx
```

SKILL.md 827 B

---
name: docx
version: "1.0"
description: Extract text from Microsoft Word documents
entry:
  script: scripts/main.py
  class: DocxSkill
triggers:
  extensions:
    - ".docx"
  intents:
    - "word document"
    - "docx"
requires:
  - python-docx
author: axoviq.com
license: AGPL-3.0-or-later
---

# DOCX Skill

Extracts paragraph text from `.docx` files using `python-docx`.

## Setup

```bash
pip install python-docx
```

## Standalone usage

```python
import asyncio
from synthadoc.skills.docx.scripts.main import DocxSkill

skill = DocxSkill()

async def main():
    result = await skill.extract("/path/to/document.docx")
    print(result.text)      # all paragraphs joined as plain text

asyncio.run(main())
```

## When this skill is used

- Source path ends with `.docx`
- User intent contains: `word document`, `docx`