Best use case
Academic Presentation Generation is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
## Overview
Teams using Academic Presentation Generation should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/pptx-generation/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How Academic Presentation Generation Compares
| Feature / Agent | Academic Presentation Generation | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
## Overview
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Academic Presentation Generation ## Overview Create publication-quality academic presentations (.pptx) for group meetings, thesis defenses, conference talks, and posters. ## Templates ### Group Meeting (10-15 slides) 1. Title slide (project name, date, presenter) 2. Background / Context (1-2 slides) 3. This Week's Progress (3-5 slides) 4. Results & Figures (2-3 slides) 5. Challenges / Questions (1 slide) 6. Next Steps (1 slide) ### Thesis Defense (30-50 slides) 1. Title (name, committee, date) 2. Outline 3. Background & Significance (5-8 slides, establishing expertise) 4. Specific Aims / Research Questions (1-2 slides) 5. Aim 1: Methods → Results → Summary (8-12 slides) 6. Aim 2: Methods → Results → Summary (8-12 slides) 7. Aim 3 (if applicable) 8. Integrated Discussion (2-3 slides) 9. Conclusions & Impact (1-2 slides) 10. Future Directions (1-2 slides) 11. Acknowledgments 12. Backup slides (for committee questions) ### Conference Talk (12-20 slides, 10-15 min) 1. Title (grab attention) 2. The Problem (why should the audience care?) 3. Key Question (one sentence) 4. Our Approach (why this method?) 5. Key Results (3-5 slides, one finding per slide) 6. So What? (implications, impact) 7. Acknowledgments ## Design Principles - **One message per slide**: if you need two messages, use two slides - **Visual hierarchy**: title → key message → supporting data → source - **Minimal text**: bullet points, not paragraphs. The speaker IS the narrative. - **Figure-first**: lead with the figure, explain verbally - **Consistent styling**: same fonts, colors, and layout throughout ## Technical Implementation - Use python-pptx for programmatic generation - Template-based: define slide layouts, then populate with content - Support custom color themes and institutional branding - Export as .pptx (editable) and .pdf (final)
Related Skills
Academic Literature Search — 学术文献检索与引用管理
Use this skill when the user asks to search for academic papers, retrieve literature, generate citations, format references, or any task involving PubMed, bioRxiv, arXiv, or academic reference management. Trigger keywords: "搜文献", "检索", "找论文", "参考文献", "引用", "citation", "search papers", "PubMed", "bioRxiv", "arXiv", "GB/T 7714", "PMID", "DOI", "批量引用".
Academic Writing
## Overview
Scientific Diagram Generation
AI-powered scientific illustration generation using Gemini Image models. Creates publication-quality mechanism diagrams, pathway illustrations, and scientific figures.
hypothesis-generation
Structured hypothesis formulation from observations. Use when you have experimental observations or data and need to formulate testable hypotheses with predictions, propose mechanisms, and design experiments to test them. Follows scientific method framework. For open-ended ideation use scientific-brainstorming; for automated LLM-driven hypothesis testing on datasets use hypogenic.
hot3d
HOT3D (Hand-Object 3D Dataset) by Meta Facebook - multi-view egocentric hand and object 3D tracking for Aria/Quest smart glasses. State-of-the-art multi-view 3D hand pose, object pose, and hand-object interaction tracking. Supports visualization with 3D joint projections, meshes, and skeletal overlays on video frames.
handtracking
Real-time hand detection in egocentric videos using victordibia/handtracking. Outputs bounding boxes for hands, specifically trained on EgoHands dataset. Supports video input/output with labeled hand boxes. Lightweight and fast for egocentric view applications.
hands-3d-pose
High-quality 3D hand pose estimation for egocentric videos from ECCV 2024 (ap229997/hands). Provides 3D joint keypoints and skeleton visualization projected to 2D. Optimized for daily egocentric activities with state-of-the-art accuracy. Outputs hand skeleton overlays on video frames.
hand-tracking-toolkit
Facebook Research Hand Tracking Challenge Toolkit - evaluation and visualization tools for 3D hand tracking. Supports loading HOT3D data, computing metrics (PA-MPJPE, AUC, etc.), visualizing 3D pose projections, and generating tracking evaluation reports. Essential for benchmarking hand tracking algorithms.
egohos-segmentation
Egocentric Hand-Object Segmentation (EgoHOS) - pixel-level hand and object segmentation in egocentric videos. Outputs fine-grained segmentation masks with hand regions highlighted. Specialized for hand-object interaction scenarios with pixel-accurate masks. Ideal for detailed interaction analysis.
zinc-database
Access ZINC (230M+ purchasable compounds). Search by ZINC ID/SMILES, similarity searches, 3D-ready structures for docking, analog discovery, for virtual screening and drug discovery.
torchdrug
PyTorch-native graph neural networks for molecules and proteins. Use when building custom GNN architectures for drug discovery, protein modeling, or knowledge graph reasoning. Best for custom model development, protein property prediction, retrosynthesis. For pre-trained models and diverse featurizers use deepchem; for benchmark datasets use pytdc.
torch-geometric
Graph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for geometric deep learning.