# Build brief — a focused alternative to MagicSlides

> **Verdict:** Partly, if you narrow it · **Buildability:** 45/100 · **Category:** Presentations
> **Source:** https://www.canitbevibecoded.com/magicslides
> Independent editorial assessment from Can It Be Vibe Coded? Not affiliated with, endorsed by, or derived from MagicSlides. Verify current pricing and capabilities before acting.

## Context

**MagicSlides** — Turn a topic, article or YouTube video into a slide deck with AI. It currently costs $29/mo.

An LLM that turns a topic or URL into an outline and renders a PPTX/PDF is a focused build. What MagicSlides actually sells is the template library, the export fidelity, and the distribution: a Google Slides add-on and a browser extension already installed by millions. You can rebuild the core loop; you can't rebuild the polish or the install base overnight.

This brief describes a focused, single-operator replacement for the part of MagicSlides that is genuinely reproducible. It is deliberately narrower than the product it replaces, and it says so in writing. Build the useful core; do not pretend to have rebuilt the rest.

## What you are building

Prompt an LLM for a slide outline from a topic, article URL or YouTube transcript, map it to a template, and export a PPTX and PDF.

- Generate slide outlines and layouts from structured content you supply.
- A responsive interface with real empty, loading, success, and error states.

## Requirements

### Functional

- A slide/PPTX renderer.
- A template system.
- Optional YouTube transcript fetch.

### Data and integrations

- LLM API key.
- Optional image API key.

Each of these needs a real account, credential, or quota. Set them up before writing feature code.

### Non-functional

- Accessibility: semantic markup, labelled controls, visible focus, and reduced-motion support.
- Security: server-side secrets, validated input, and no credentials in the client bundle.
- Reliability: retries with backoff on external calls, and a clear failure state when a provider is down.
- Portability: the operator can export their data and leave without losing it.

## Implementation brief

Build me an AI presentation generator to replace MagicSlides, in an empty repo.

Stack (no alternatives): a Node.js + TypeScript CLI. Use pptxgenjs for PPTX output
and LibreOffice headless (soffice --headless --convert-to pdf) for the PDF. Do not
build a web app.

Core loop:
- `deck new "<topic>"` OR `deck new --url <article-url>` OR `deck new --yt <youtube-url>`.
- For --url, fetch and strip the page to text; for --yt, pull the transcript via the
  youtube-transcript package; for a bare topic, skip fetching.
- Send that text to an LLM (key in .env) and ask for structured JSON: a deck title,
  then per slide a title, 3-5 bullets, and speaker notes.
- Render the JSON with pptxgenjs using one of five layouts: title, bullets,
  two-column, section-break, quote.
- Write ./decks/<slug>/deck.pptx, deck.pdf, and the raw slides.json.

Details:
- One theme file (fonts, colors, logo) so every deck is consistent; no per-deck design.
- `deck redo <n>` regenerates a single slide by number, leaving the rest untouched.
- Decks are plain files on disk, git-friendly and hand-editable. No database.
- Secrets (LLM key, optional image API key) live in .env; ship .env.example.
- No accounts, no telemetry; the only network calls are the LLM, the optional image
  API, and the URL/YouTube fetch.
- Out of scope: a web editor, a Google Slides add-on, a browser extension, hosted
  share links, collaboration. Editing the PPTX in Keynote/PowerPoint is the editor.
- README: keys, the three input modes, export commands, and how to add a layout.

## Delivery standard

- Inspect the repository first, then write a short implementation plan before writing code.
- Deliver the smallest complete end-to-end workflow first; every primary control must work against persisted data.
- Use real validation and storage; never substitute fake dashboards, decorative controls, hard-coded success states, or mock integrations.
- Include responsive layouts plus genuine empty, loading, success, validation, and failure states.
- Keep secrets server-side in environment variables, provide .env.example, and never commit credentials or user data.
- Add structured logs around every external call and return actionable errors without leaking sensitive details.
- Write unit tests for the core logic and one automated test of the main user journey.
- Finish with a README covering setup, architecture, data location, backups, tests, deployment, and known limitations.

## Acceptance criteria

- [ ] A clean install starts the app using only the README and .env.example.
- [ ] The primary journey works from first visit through saved result, reload, edit, export, and deletion where applicable.
- [ ] Invalid input, missing configuration, provider failure, and an empty database each have a usable state.
- [ ] The interface works at 390px and 1440px, is keyboard navigable, and shows visible focus on every control.
- [ ] Tests, type checking, linting, and a production build all pass with no ignored failures.
- [ ] No part of the interface implies a live integration, security guarantee, or scale capability that was not actually built and verified.

## Non-goals

Do not build these, and do not claim to have replaced them:

- 70+ polished templates and design presets.
- One-click Google Slides add-on and browser extension.
- Reliable PPTX/PDF export fidelity.
- Hosted sharing and no-watermark output.
- Team and API tiers.

## What you still own after launch

- Secure credentials, rotate secrets, and handle provider rate limits.
- Run migrations, backups, restores, and dependency updates.
- Test the critical journey after every model, API, or hosting change.
- Monitor failures and fix the edge cases a first prompt will miss.
- Maintain every third-party integration as APIs and OAuth rules change.

## Risk

**Operational risk.** The code is achievable; dependable data, integrations, and ongoing operations are the real cost.

Editorial confidence in this assessment: medium. No reviewed project implementation is linked yet.

## Prior art

Working open-source software you can read, fork, or borrow from before starting:

- [Slidev](https://github.com/slidevjs/slidev) — Open-source Markdown/HTML slide deck framework, a strong base for a generator
- [Marp](https://github.com/marp-team/marp) — Markdown-to-slides ecosystem with PPTX/PDF export

---

Generated by [Can It Be Vibe Coded?](https://www.canitbevibecoded.com) · Full report: https://www.canitbevibecoded.com/magicslides
