How I built a free, open-source library of AI slide-deck prompts

Description and use

The author built a library of 120+ AI slide‑deck prompts that reliably produce high‑quality, consistent decks, saving time and improving workflow.

Problem

Creating consistent, high-quality slide decks required rewriting the same prompt repeatedly, leading to unpredictable results.

Outcome

The library consistently produces high‑quality slide decks across multiple use cases, saving time and ensuring visual coherence.

Workflow

• 1. Identify common deck types and visual styles.
• 2. Draft prompts that specify slide count, content, color, font, and tone.
• 3. Test prompts in an AI image model to verify output quality.
• 4. Refine prompts based on results, adding preview images.
• 5. Publish the prompts in a free, MIT‑licensed GitHub repository.
• 6. Encourage community contributions via pull requests.

Evidence

Every time I needed a deck, I'd open an AI image model and rewrite the same "make me a pitch deck" prompt from scratch — and the output was hit-or-miss.

Source

I started saving the prompts that reliably produced good slides, and eventually organized 120+ of them by use case (pitch, QBR, research, sales, education) and visual style (minimal, dark, corporate, editorial).

Source

Why it works: it names every slide's job (problem, solution, TAM/SAM/SOM, traction, ask) and locks one accent color + one font, so the 10 slides read as a system instead of 10 unrelated images.

Source

How to use: copy any prompt → paste into your image model or SurgePix → generate → then edit (swap a chart, retitle a slide, recolor all 12 to match) rather than regenerating and hoping.

Source