Convert HTML/Markdown to PowerPoint presentations using Marp
npx skills add https://github.com/claude-office-skills/skills --skill html-to-ppt
This skill enables conversion from Markdown or HTML to professional PowerPoint presentations using Marp (Markdown Presentation Ecosystem). Create beautiful, consistent slides using simple Markdown syntax with CSS-based themes.
Example prompts:
Marp uses a simple syntax where --- separates slides:
---
marp: true
theme: default
---
# Slide 1 Title
Content for first slide
---
# Slide 2 Title
Content for second slide
# Convert to PowerPoint
marp slides.md -o presentation.pptx
# Convert to PDF
marp slides.md -o presentation.pdf
# Convert to HTML
marp slides.md -o presentation.html
# With specific theme
marp slides.md --theme gaia -o presentation.pptx
---
marp: true
---
# Title
- Bullet point 1
- Bullet point 2
- Bullet point 3
---
marp: true
theme: gaia
class: lead
---
# Presentation Title
## Subtitle
Author Name
Date
---
marp: true
theme: default # default, gaia, uncover
size: 16:9 # 4:3, 16:9, or custom
paginate: true # Show page numbers
header: 'Company Name' # Header text
footer: 'Confidential' # Footer text
backgroundColor: #fff
backgroundImage: url('bg.png')
---
---
marp: true
theme: default # Clean, minimal
---
---
marp: true
theme: gaia # Colorful, modern
---
---
marp: true
theme: uncover # Bold, presentation-focused
---
---
marp: true
theme: gaia
class: lead # Centered title slide
---
---
marp: true
theme: gaia
class: invert # Inverted colors
---
# Heading 1
## Heading 2
**Bold text** and *italic text*
`inline code`
> Blockquote for emphasis
- Unordered item
- Another item
- Nested item
1. Ordered item
2. Second item
1. Nested numbered
# Code Example
\`\`\`python
def hello():
print("Hello, World!")
\`\`\`
| Feature | Status |
|---------|--------|
| Tables | ✅ |
| Charts | ✅ |
| Images | ✅ |




---
marp: true
backgroundImage: url('background.jpg')
---
# Slide with Background
---
marp: true
style: |
.columns {
display: grid;
grid-template-columns: repeat(2, 1fr);
gap: 1rem;
}
---
# Two Column Layout
<div class="columns">
<div>
## Left Column
- Point 1
- Point 2
</div>
<div>
## Right Column
- Point A
- Point B
</div>
</div>
---
marp: true
theme: gaia
class: gaia
---
<!--
_backgroundImage: linear-gradient(to right, #4a90a4, #4a90a4 50%, white 50%)
-->
<div class="columns">
<div style="color: white;">
# Dark Side
</div>
<div>
# Light Side
</div>
</div>
---
marp: true
---
<!--
_backgroundColor: #123
_color: white
_paginate: false
-->
# Special Slide
---
marp: true
---
<style scoped>
h1 {
color: red;
}
</style>
# This Title is Red
import subprocess
import tempfile
import os
def markdown_to_pptx(md_content, output_path, theme='default'):
"""Convert Markdown to PowerPoint using Marp."""
# Add marp directive if not present
if '---\nmarp: true' not in md_content:
md_content = f"---\nmarp: true\ntheme: {theme}\n---\n\n" + md_content
# Write to temp file
with tempfile.NamedTemporaryFile(mode='w', suffix='.md', delete=False) as f:
f.write(md_content)
temp_path = f.name
try:
# Convert using marp
subprocess.run([
'marp', temp_path, '-o', output_path
], check=True)
return output_path
finally:
os.unlink(temp_path)
# Usage
md = """
# Welcome
Introduction slide
---
# Agenda
- Topic 1
- Topic 2
- Topic 3
"""
markdown_to_pptx(md, 'presentation.pptx')
const { marpCli } = require('@marp-team/marp-cli');
// Convert file
marpCli(['slides.md', '-o', 'output.pptx']).then(exitCode => {
console.log('Done:', exitCode);
});
def create_presentation(title, sections, output_path, theme='gaia'):
"""Generate presentation from structured data."""
md_content = f"""---
marp: true
theme: {theme}
paginate: true
---
<!-- _class: lead -->
# {title}
{sections.get('subtitle', '')}
{sections.get('author', '')}
"""
for section in sections.get('slides', []):
md_content += f"""---
# {section['title']}
"""
for point in section.get('points', []):
md_content += f"- {point}\n"
if section.get('notes'):
md_content += f"\n<!-- Notes: {section['notes']} -->\n"
md_content += """---
<!-- _class: lead -->
# Thank You!
Questions?
"""
return markdown_to_pptx(md_content, output_path, theme)
def generate_report_slides(data_list, template, output_dir):
"""Generate multiple presentations from data."""
import os
for data in data_list:
content = template.format(**data)
output_path = os.path.join(output_dir, f"{data['name']}_report.pptx")
markdown_to_pptx(content, output_path)
---
marp: true
theme: gaia
class: lead
paginate: true
---
# API Documentation
## REST API Best Practices
Engineering Team
January 2024
---
# Agenda
1. Authentication
2. Endpoints Overview
3. Error Handling
4. Rate Limiting
5. Examples
---
# Authentication
All requests require an API key:
Authorization: Bearer YOUR_API_KEY
- Keys expire after 90 days
- Store securely, never commit to git
- Rotate regularly
---
# Endpoints Overview
| Method | Endpoint | Description |
|--------|----------|-------------|
| GET | /users | List all users |
| POST | /users | Create user |
| GET | /users/:id | Get user details |
| PUT | /users/:id | Update user |
| DELETE | /users/:id | Delete user |
---
# Error Handling
{
"error": {
"code": "VALIDATION_ERROR",
"message": "Invalid email format",
"details": ["email must be valid"]
}
}
---
<!-- _class: lead -->
# Questions?
[email protected]
def create_pitch_deck(company_data):
"""Generate investor pitch deck."""
md = f"""---
marp: true
theme: uncover
paginate: true
---
<!-- _class: lead -->
<!-- _backgroundColor: #2d3748 -->
<!-- _color: white -->
# {company_data['name']}
{company_data['tagline']}
---
# The Problem
{company_data['problem_statement']}
**Market Pain Points:**
"""
for pain in company_data['pain_points']:
md += f"- {pain}\n"
md += f"""
---
# Our Solution
{company_data['solution']}
})
---
# Market Opportunity
- **TAM:** {company_data['tam']}
- **SAM:** {company_data['sam']}
- **SOM:** {company_data['som']}
---
# Traction
| Metric | Value |
|--------|-------|
| Monthly Revenue | {company_data['mrr']} |
| Customers | {company_data['customers']} |
| Growth Rate | {company_data['growth']} |
---
# The Ask
**Seeking:** {company_data['funding_ask']}
**Use of Funds:**
- Product Development: 40%
- Sales & Marketing: 35%
- Operations: 25%
---
<!-- _class: lead -->
# Let's Build the Future Together
{company_data['contact']}
"""
return md
# Generate deck
pitch_data = {
'name': 'TechStartup Inc',
'tagline': 'AI-Powered Document Processing',
'problem_statement': 'Businesses waste 20% of time on manual document work',
'pain_points': ['Manual data entry', 'Error-prone processes', 'Slow turnaround'],
'solution': 'Automated document processing with 99.5% accuracy',
'tam': '$50B',
'sam': '$10B',
'som': '$500M',
'mrr': '$100K',
'customers': '50',
'growth': '20% MoM',
'funding_ask': '$5M Series A',
'contact': '[email protected]'
}
md_content = create_pitch_deck(pitch_data)
markdown_to_pptx(md_content, 'pitch_deck.pptx', theme='uncover')
# Using npm
npm install -g @marp-team/marp-cli
# Using Homebrew
brew install marp-cli
# Verify installation
marp --version
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.
Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances
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.
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.
Take claude-office-skills/html-to-ppt from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
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.
The instructions reference npm, brew.
Without those the skill loads but fails at the first command.