MD To Office Agent Skill

by claude-office-skills

3k tokens

context cost

the whole folder, loaded on every use

files

instructions only

copies elsewhere

how many repositories repackaged it

353

stars on the repo

on the repository, not the skill itself

Install

one command, takes just this skill from the repository

npx skills add https://github.com/claude-office-skills/skills --skill md-to-office

The instruction itself

32 sections, as written by the author

Markdown to Office Skill

Overview

This skill enables conversion from Markdown to various Office formats using Pandoc - the universal document converter. Convert your Markdown files to professional Word documents, PowerPoint presentations, PDFs, and more while preserving formatting and structure.

How to Use

Provide the Markdown content or file
Specify the target format (docx, pptx, pdf, etc.)
Optionally provide a reference template for styling
I'll convert using Pandoc with optimal settings

Example prompts:

"Convert this README.md to a professional Word document"
"Turn my markdown notes into a PowerPoint presentation"
"Generate a PDF from this markdown with custom styling"
"Create a Word doc from this markdown using company template"

Domain Knowledge

Pandoc Fundamentals

# Basic conversion
pandoc input.md -o output.docx
pandoc input.md -o output.pdf
pandoc input.md -o output.pptx

# With template
pandoc input.md --reference-doc=template.docx -o output.docx

# Multiple inputs
pandoc ch1.md ch2.md ch3.md -o book.docx

Supported Conversions

| From | To | Command |

|------|-----|---------|

| Markdown | Word | pandoc in.md -o out.docx |

| Markdown | PDF | pandoc in.md -o out.pdf |

| Markdown | PowerPoint | pandoc in.md -o out.pptx |

| Markdown | HTML | pandoc in.md -o out.html |

| Markdown | LaTeX | pandoc in.md -o out.tex |

| Markdown | EPUB | pandoc in.md -o out.epub |

Markdown to Word (.docx)

Basic Conversion

pandoc document.md -o document.docx

With Template (Reference Doc)

# First create a template by converting sample
pandoc sample.md -o reference.docx

# Edit reference.docx styles in Word, then use it
pandoc input.md --reference-doc=reference.docx -o output.docx

With Table of Contents

pandoc document.md --toc --toc-depth=3 -o document.docx

With Metadata

pandoc document.md \
  --metadata title="My Report" \
  --metadata author="John Doe" \
  --metadata date="2024-01-15" \
  -o document.docx

Markdown to PDF

Via LaTeX (Best Quality)

# Requires LaTeX installation
pandoc document.md -o document.pdf

# With custom settings
pandoc document.md \
  --pdf-engine=xelatex \
  -V geometry:margin=1in \
  -V fontsize=12pt \
  -o document.pdf

Via HTML/wkhtmltopdf

pandoc document.md \
  --pdf-engine=wkhtmltopdf \
  --css=style.css \
  -o document.pdf

PDF Options

pandoc document.md \
  -V papersize:a4 \
  -V geometry:margin=2cm \
  -V fontfamily:libertinus \
  -V colorlinks:true \
  --toc \
  -o document.pdf

Markdown to PowerPoint (.pptx)

Basic Conversion

pandoc slides.md -o presentation.pptx

Markdown Structure for Slides

---
title: Presentation Title
author: Author Name
date: January 2024
---

# Section Header (creates section divider)

## Slide Title

- Bullet point 1
- Bullet point 2
  - Sub-bullet

## Another Slide

Content here

::: notes
Speaker notes go here (not visible in slides)
:::

## Slide with Image

![Description](image.png){width=80%}

## Two Column Slide

:::::::::::::: {.columns}
::: {.column width="50%"}
Left column content
:::

::: {.column width="50%"}
Right column content
:::
::::::::::::::

With Template

# Use corporate PowerPoint template
pandoc slides.md --reference-doc=template.pptx -o presentation.pptx

YAML Frontmatter

Add metadata at the top of your Markdown:

---
title: "Document Title"
author: "Author Name"
date: "2024-01-15"
abstract: "Brief description"
toc: true
toc-depth: 2
numbersections: true
geometry: margin=1in
fontsize: 11pt
documentclass: report
---

# First Chapter
...

Python Integration

import subprocess
import os

def md_to_docx(input_path, output_path, template=None):
    """Convert Markdown to Word document."""
    cmd = ['pandoc', input_path, '-o', output_path]
    
    if template:
        cmd.extend(['--reference-doc', template])
    
    subprocess.run(cmd, check=True)
    return output_path

def md_to_pdf(input_path, output_path, **options):
    """Convert Markdown to PDF with options."""
    cmd = ['pandoc', input_path, '-o', output_path]
    
    if options.get('toc'):
        cmd.append('--toc')
    
    if options.get('margin'):
        cmd.extend(['-V', f"geometry:margin={options['margin']}"])
    
    subprocess.run(cmd, check=True)
    return output_path

def md_to_pptx(input_path, output_path, template=None):
    """Convert Markdown to PowerPoint."""
    cmd = ['pandoc', input_path, '-o', output_path]
    
    if template:
        cmd.extend(['--reference-doc', template])
    
    subprocess.run(cmd, check=True)
    return output_path

pypandoc (Python Wrapper)

import pypandoc

# Simple conversion
output = pypandoc.convert_file('input.md', 'docx', outputfile='output.docx')

# With options
output = pypandoc.convert_file(
    'input.md', 
    'docx',
    outputfile='output.docx',
    extra_args=['--toc', '--reference-doc=template.docx']
)

# From string
md_content = "# Hello\n\nThis is markdown."
output = pypandoc.convert_text(md_content, 'docx', format='md', outputfile='output.docx')

Best Practices

Use Templates: Create a reference document for consistent branding
Structure Headers: Use consistent heading levels (## for slides, # for sections)
Test Incrementally: Convert small sections first to verify formatting
Include Metadata: Use YAML frontmatter for document properties
Handle Images: Use relative paths and specify dimensions

Common Patterns

Batch Conversion

import subprocess
from pathlib import Path

def batch_convert(input_dir, output_format, output_dir=None):
    """Convert all markdown files in a directory."""
    input_path = Path(input_dir)
    output_path = Path(output_dir) if output_dir else input_path
    
    for md_file in input_path.glob('*.md'):
        output_file = output_path / md_file.with_suffix(f'.{output_format}').name
        subprocess.run([
            'pandoc', str(md_file), '-o', str(output_file)
        ], check=True)
        print(f"Converted: {md_file.name} -> {output_file.name}")

batch_convert('./docs', 'docx', './output')

Report Generator

def generate_report(title, sections, output_path, template=None):
    """Generate Word report from structured data."""
    
    # Build markdown
    md_content = f"""---
title: "{title}"
date: "{datetime.now().strftime('%B %d, %Y')}"
---

"""
    for section_title, content in sections.items():
        md_content += f"# {section_title}\n\n{content}\n\n"
    
    # Write temp file
    with open('temp_report.md', 'w') as f:
        f.write(md_content)
    
    # Convert
    cmd = ['pandoc', 'temp_report.md', '-o', output_path, '--toc']
    if template:
        cmd.extend(['--reference-doc', template])
    
    subprocess.run(cmd, check=True)
    os.remove('temp_report.md')

Examples

Example 1: Technical Documentation

import subprocess

# Create comprehensive markdown
doc = """---
title: "API Documentation"
author: "Dev Team"
date: "2024-01-15"
toc: true
toc-depth: 2
---

# Introduction

This document describes the REST API for our service.

## Authentication

All API requests require an API key in the header:

Authorization: Bearer YOUR_API_KEY


## Endpoints

### GET /users

Retrieve all users.

**Response:**

| Field | Type | Description |
|-------|------|-------------|
| id | integer | User ID |
| name | string | Full name |
| email | string | Email address |

### POST /users

Create a new user.

**Request Body:**

{

"name": "John Doe",

"email": "[email protected]"

}


## Error Codes

| Code | Meaning |
|------|---------|
| 400 | Bad Request |
| 401 | Unauthorized |
| 404 | Not Found |
| 500 | Server Error |
"""

# Save markdown
with open('api_docs.md', 'w') as f:
    f.write(doc)

# Convert to Word
subprocess.run([
    'pandoc', 'api_docs.md',
    '-o', 'api_documentation.docx',
    '--toc',
    '--reference-doc', 'company_template.docx'
], check=True)

# Convert to PDF
subprocess.run([
    'pandoc', 'api_docs.md',
    '-o', 'api_documentation.pdf',
    '--toc',
    '-V', 'geometry:margin=1in',
    '-V', 'fontsize=11pt'
], check=True)

Example 2: Presentation from Markdown

slides_md = """---
title: "Q4 Business Review"
author: "Sales Team"
date: "January 2024"
---

# Overview

## Agenda

- Q4 Performance Summary
- Regional Highlights
- 2024 Outlook
- Q&A

# Q4 Performance

## Key Metrics

- Revenue: $12.5M (+15% YoY)
- New Customers: 250
- Retention Rate: 94%

## Regional Performance

:::::::::::::: {.columns}
::: {.column width="50%"}
**North America**

- Revenue: $6.2M
- Growth: +18%
:::

::: {.column width="50%"}
**Europe**

- Revenue: $4.1M
- Growth: +12%
:::
::::::::::::::

# 2024 Outlook

## Strategic Priorities

1. Expand APAC presence
2. Launch new product line
3. Improve customer onboarding

## Revenue Targets

| Quarter | Target |
|---------|--------|
| Q1 | $13M |
| Q2 | $14M |
| Q3 | $15M |
| Q4 | $16M |

# Thank You

## Questions?

Contact: [email protected]
"""

with open('presentation.md', 'w') as f:
    f.write(slides_md)

subprocess.run([
    'pandoc', 'presentation.md',
    '-o', 'q4_review.pptx',
    '--reference-doc', 'company_slides.pptx'
], check=True)

Limitations

Complex Word formatting may not convert perfectly
PDF conversion requires LaTeX or wkhtmltopdf
PowerPoint animations not supported
Some advanced tables may need manual adjustment
Image positioning can be tricky

Installation

# macOS
brew install pandoc

# Ubuntu/Debian
sudo apt-get install pandoc

# Windows
choco install pandoc

# Python wrapper
pip install pypandoc

Resources

Other skills for the same job

different authors, same section of the catalogue

Protocolsio Integration

by christophacham

×4

Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.

16k tokens

Tailored Resume Generator

by frostant

×4

Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances

3k tokens

Excalidraw Diagram Generator

by github

vendor ×3

Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.

Build and distribute Expo development clients locally or via TestFlight

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.

16k tokens

Benchling Integration

by christophacham

×3

Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.

Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.

24k tokens

How to use it

Copy the folder

Take claude-office-skills/md-to-office from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.

Install what it needs

The instructions reference pip, brew, apt. Without those the skill loads but fails at the first command.