Academic Presentations

Produce slide decks (and optionally narrated demo videos) from research papers. The human drives all outline and visual decisions, the agent executes.

Pipeline

[1] Script Draft ──→ [2] Slide Generation ──→ [3] TTS Audio (optional) ──→ [4] Video Assembly (optional)
     Claude Code          nanobanana /edit     edge-tts / Kokoro / ElevenLabs       ffmpeg

Skip stages 3, 4 for slide-only output. User can enter at any stage.

Stage 1: Script / Outline

Input: paper + user-provided outline or slide plan Output: video-scripts.md or slide-outline.md, per-slide content with talking points

The agent drafts scripts based on the user's outline. The user owns the structure, agent does not decide slide count, order, or what to emphasize.

Stage 2: Slide Generation

Full reference: references/slide-generation.md

Tool: nanobanana (Gemini CLI extension)

Priority order (edit-first):

1. Has paper figure → nanobanana /edit to wrap into slide frame
2. Has existing slide → /edit to adapt
3. User-provided reference (e.g., from NotebookLM or PPTX the user made) → /edit to refine
4. Title slide from scratch → generate with academic style prompt
5. Content slide from scratch → generate with deck-style preamble

Key principle: prefer /edit on existing HQ paper figures over generating from scratch.

Deck style: create deck-style.md once per deck, prepend to all generate-from-scratch prompts. For /edit, style is inherited from the base image.

Example deck-style.md:

- Canvas: 1920x1080, white background
- Accent: #2563EB blue, text: #1e293b dark slate
- Clean sans-serif, flat design, no gradients/shadows
- Bottom bar: blue accent with white affiliation text

Stage 3: TTS Audio (optional)