agentleFS
claude-office-skillsclaude-office-skills/skills/ai-slides/SKILL.md

ai-slides

Skill433 starsChanged 9 months agoMITView on GitHub

Generate complete presentations with AI - from outline to polished slides

  • Installs packages

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    One Idea Per Slide: Keep focused

    line 297

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

AI Slides Skill

Overview

This skill enables AI-powered presentation generation. Provide a topic or outline, and get a complete, polished presentation with proper structure, content, and formatting.

How to Use

  1. Provide a topic, outline, or rough notes
  2. Specify audience and presentation length
  3. I'll generate a complete presentation

Example prompts:

  • "Create a 10-slide presentation about machine learning"
  • "Generate a pitch deck for a SaaS startup"
  • "Build training slides on cybersecurity basics"
  • "Make a quarterly review presentation from this data"

Domain Knowledge

Presentation Structure

# Effective presentation structure
structure:
  - title_slide:
      title: "Clear, compelling title"
      subtitle: "Context or tagline"
      author: "Presenter name"
  
  - agenda:
      items: 3-5 main topics
  
  - introduction:
      hook: "Attention-grabbing opening"
      context: "Why this matters"
  
  - main_content:
      sections: 3-5 key points
      each_section:
        - heading
        - 3-5 bullets or visual
        - supporting data
  
  - conclusion:
      summary: "Key takeaways"
      call_to_action: "What to do next"
  
  - closing:
      thank_you: true
      contact_info: true
      qa_prompt: true

Content Generation Pattern

def generate_presentation(topic, audience, slide_count=10):
    """AI-powered presentation generation."""
    
    # 1. Generate outline
    outline = generate_outline(topic, slide_count)
    
    # 2. Expand each section
    slides = []
    for section in outline:
        slide_content = expand_section(section, audience)
        slides.append(slide_content)
    
    # 3. Add visuals suggestions
    for slide in slides:
        slide['visuals'] = suggest_visuals(slide['content'])
    
    # 4. Format as Marp markdown
    presentation = format_as_marp(slides)
    
    return presentation

def generate_outline(topic, count):
    """Generate presentation outline."""
    # Typical structure
    outline = [
        {'type': 'title', 'title': topic},
        {'type': 'agenda'},
        # Main content (60% of slides)
        # ... content slides
        {'type': 'summary'},
        {'type': 'closing'}
    ]
    return outline

Marp Output

def format_as_marp(slides):
    """Convert slides to Marp markdown."""
    
    marp = """---
marp: true
theme: gaia
paginate: true
---

"""
    
    for slide in slides:
        if slide['type'] == 'title':
            marp += f"""<!-- _class: lead -->

# {slide['title']}

{slide.get('subtitle', '')}

---

"""
        elif slide['type'] == 'content':
            marp += f"""# {slide['heading']}

"""
            for point in slide['points']:
                marp += f"- {point}\n"
            marp += "\n---\n\n"
    
    return marp

Example: Generate Tech Talk

topic = "Introduction to Docker"
audience = "Developers new to containers"
slides = 10

# Generated presentation
presentation = """---
marp: true
theme: gaia
paginate: true
---

<!-- _class: lead -->

# Introduction to Docker

Containerization Made Simple

---

# Agenda

1. What is Docker?
2. Core Concepts
3. Getting Started
4. Best Practices
5. Demo

---

# What is Docker?

- Container platform for packaging applications
- Lightweight alternative to VMs
- "Build once, run anywhere"
- 15M+ developers, 7M+ applications

---

# Why Containers?

| VMs | Containers |
|-----|------------|
| GB size | MB size |
| Minutes to start | Seconds to start |
| Full OS | Shared kernel |

---

# Core Concepts

- **Image**: Blueprint/template
- **Container**: Running instance
- **Dockerfile**: Build instructions
- **Registry**: Image storage (Docker Hub)

---

# Getting Started

```bash
# Pull an image
docker pull nginx

# Run a container
docker run -p 8080:80 nginx

# List containers
docker ps

Your First Dockerfile

FROM node:18
WORKDIR /app
COPY package*.json ./
RUN npm install
COPY . .
EXPOSE 3000
CMD ["npm", "start"]

Best Practices

  • Use official base images
  • Minimize layers
  • Don't run as root
  • Use .dockerignore
  • Multi-stage builds

Summary

✅ Docker simplifies deployment ✅ Containers are lightweight & fast ✅ Easy to get started ✅ Industry standard


<!-- _class: lead -->

Questions?

Resources: docs.docker.com """


## Best Practices

1. **Know Your Audience**: Tailor complexity and examples
2. **One Idea Per Slide**: Keep focused
3. **6x6 Rule**: Max 6 bullets, 6 words each
4. **Visual First**: Suggest images/diagrams
5. **Strong Opening/Closing**: Hook and call-to-action

## Resources

- [Marp](https://marp.app/) - Markdown presentations
- [Slidev](https://sli.dev/) - Vue-powered slides
- [reveal.js](https://revealjs.com/) - HTML presentations

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.