ScienceClaw Presentations — Joey's PPT Templates
Joey's reference for all presentation work. Use this skill when creating academic presentations.
Best use case
ScienceClaw Presentations — Joey's PPT Templates is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Joey's reference for all presentation work. Use this skill when creating academic presentations.
Teams using ScienceClaw Presentations — Joey's PPT Templates 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/scienceclaw-presentations/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How ScienceClaw Presentations — Joey's PPT Templates Compares
| Feature / Agent | ScienceClaw Presentations — Joey's PPT Templates | 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?
Joey's reference for all presentation work. Use this skill when creating academic presentations.
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
# ScienceClaw Presentations — Joey's PPT Templates
Joey's reference for all presentation work. Use this skill when creating academic presentations.
---
## Templates
### Group Meeting
- **Use**: Informal lab meeting / group meeting
- **Sections**: Title, Background, Methods, Results, Next Steps, Questions
- **Style**: Clean, minimal, data-focused
- **Slide count**: 10-15
- **Tone**: Conversational but structured
### Thesis Defense
- **Use**: PhD/Master thesis defense
- **Sections**: Title, Committee, Background, Aims, Methods, Results (by aim), Discussion, Conclusions, Future Work, Acknowledgments, Questions
- **Style**: Formal, comprehensive, narrative arc
- **Slide count**: 30-50
- **Tone**: Authoritative, builds from problem to contribution
### Conference Talk
- **Use**: Conference oral presentation (10-15 min)
- **Sections**: Title, Motivation, Key Question, Approach, Results (3-5 key), Impact, Acknowledgments
- **Style**: Punchy, one-message-per-slide, builds to climax
- **Slide count**: 12-20
- **Tone**: Engaging, clear takeaways, audience-first
### Poster
- **Use**: Academic poster (48x36 inches typical)
- **Sections**: Title/Authors, Background, Methods, Results, Conclusions, References, QR Code
- **Style**: Visual hierarchy, scannable at 2 meters
- **Slide count**: 1 (poster layout)
- **Tone**: Concise, conversation-starter
---
## Slide Design Principles
1. **One message per slide**. If a slide needs two points, it needs two slides.
2. **Build narrative tension**. Motivation → Question → Approach → Discovery → Impact.
3. **Visuals over text**. A figure with a one-line title beats three bullet points.
4. **Audience calibration**. Group meeting: peers who know the jargon. Conference: mixed audience. Defense: experts who will probe.
5. **Timing**: ~1 minute per slide for talks, ~2 minutes per poster section for conversations.
---
## python-pptx Code Patterns
When generating .pptx files via the Compute Server:
```python
from pptx import Presentation
from pptx.util import Inches, Pt
from pptx.enum.text import PP_ALIGN
prs = Presentation()
prs.slide_width = Inches(13.333)
prs.slide_height = Inches(7.5)
# Title slide
slide = prs.slides.add_slide(prs.slide_layouts[0])
slide.shapes.title.text = "Title Here"
slide.placeholders[1].text = "Author | Affiliation | Date"
# Content slide with figure
slide = prs.slides.add_slide(prs.slide_layouts[5]) # blank
slide.shapes.add_picture("figure.png", Inches(1), Inches(1.5), width=Inches(11))
prs.save("output.pptx")
```
---
## Reference Formatting
Presentations should cite key references in footer text (Author et al., Year) with full references on the last slide. Use Vancouver/numbered style for dense slides, Author-Year for sparse slides.Related Skills
venue-templates
Access comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.
ScienceClaw Aesthetics — Publication-Quality Figure Standards
Rachel's aesthetic reference for all visualization work. Use this skill when generating any scientific figure.
svg-ui-templates
Generate professional SVG UI panels for structured information display. Use when presenting lists, task checklists, pipeline/dependency status diagrams, or rich-text report layouts as SVG images. Covers four templates - list-panel, checklist-panel, pipeline-status, richtext-layout. Style is professional, business-oriented, academic-grade with Material Design color palette.
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.
zarr-python
Chunked N-D arrays for cloud storage. Compressed arrays, parallel I/O, S3/GCS integration, NumPy/Dask/Xarray compatible, for large-scale scientific computing pipelines.
Academic Writing
## Overview
scientific-visualization
## Overview
vaex
Use this skill for processing and analyzing large tabular datasets (billions of rows) that exceed available RAM. Vaex excels at out-of-core DataFrame operations, lazy evaluation, fast aggregations, efficient visualization of big data, and machine learning on large datasets. Apply when users need to work with large CSV/HDF5/Arrow/Parquet files, perform fast statistics on massive datasets, create visualizations of big data, or build ML pipelines that do not fit in memory.
uspto-database
Access USPTO APIs for patent/trademark searches, examination history (PEDS), assignments, citations, office actions, TSDR, for IP analysis and prior art searches.
uniprot-database
Direct REST API access to UniProt. Protein searches, FASTA retrieval, ID mapping, Swiss-Prot/TrEMBL. For Python workflows with multiple databases, prefer bioservices (unified interface to 40+ services). Use this for direct HTTP/REST work or UniProt-specific control.
umap-learn
UMAP dimensionality reduction. Fast nonlinear manifold learning for 2D/3D visualization, clustering preprocessing (HDBSCAN), supervised/parametric UMAP, for high-dimensional data.
treatment-plans
Generate concise (3-4 page), focused medical treatment plans in LaTeX/PDF format for all clinical specialties. Supports general medical treatment, rehabilitation therapy, mental health care, chronic disease management, perioperative care, and pain management. Includes SMART goal frameworks, evidence-based interventions with minimal text citations, regulatory compliance (HIPAA), and professional formatting. Prioritizes brevity and clinical actionability.