export-pptx

Export research project findings to a presentation (.pptx) with key findings, figures, and conclusions. Use when user says "导出 PPT", "/export pptx", "做个汇报", "生成 PPT", "export to PowerPoint", "make a presentation from results", or wants slides from project results. Builds on pptx-generation skill.

42 stars

byZaoqu-Liu

View on GitHub Installation ↓

Best use case

export-pptx is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Teams using export-pptx 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

$curl -o ~/.claude/skills/export-pptx/SKILL.md --create-dirs "https://raw.githubusercontent.com/Zaoqu-Liu/ScienceClaw/main/skills/export-pptx/SKILL.md"

Manual Installation

Download SKILL.md from GitHub
Place it in .claude/skills/export-pptx/SKILL.md inside your project
Restart your AI agent — it will auto-discover the skill

How export-pptx Compares

Feature / Agent	export-pptx	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?

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

# Export Project to Presentation (.pptx)

Auto-generate a presentation from a ScienceClaw project's reports and figures. Uses the pptx-generation skill's code templates and themes.

## When to Use

- User says "/export pptx", "导出 PPT", "做个汇报", "生成 PPT"
- User completed a research analysis and wants slides for group meeting or conference
- User wants to present findings to collaborators

## Workflow

1. **Identify the project directory** from ACTIVE_PROJECT.md or most recent project
2. **Read the main report** from `reports/` — extract key findings, section headers, conclusions
3. **Collect figures** from `figures/` — each significant figure gets its own slide
4. **Read METHODS.md** if present — create a methods slide
5. **Generate .pptx** using the pptx-generation skill's helper functions
6. **Save** to `reports/<project_name>_presentation.pptx`

## Slide Structure (auto-generated)

| Slide | Content |
|-------|---------|
| 1 | Title slide (project name, date, "ScienceClaw Analysis") |
| 2 | Background / Research Question (from report intro) |
| 3-N | Key Findings (one per slide, with figure if available) |
| N+1 | Methods Summary (from METHODS.md) |
| N+2 | Conclusions (from report summary/conclusion section) |
| N+3 | References (top 10 cited papers) |

## Key Extraction Logic

From the report markdown, extract:
- **Title**: First `# ` heading
- **Background**: First section text (before second `## `)
- **Key findings**: Lines containing statistical results (p-values, HR, AUC, fold change, correlation coefficients)
- **Conclusions**: Section titled "Summary", "Conclusion", "总结", or "结论"
- **References**: Lines matching `[N] Author...` or numbered reference patterns

## Theme

Use the NPG theme from pptx-generation skill by default:
- Primary: `(0x3C, 0x54, 0x88)` — dark blue
- Accent: `(0xE6, 0x4B, 0x35)` — red
- Light background: `(0xEE, 0xF0, 0xF5)`

## Execution

Combine ALL steps into a single `bash` call:

```bash
pip install -q python-pptx Pillow 2>/dev/null && python3 << 'PPTXEOF'
# Use helpers from pptx-generation skill
# Read project directory
# Extract key findings from report
# Build slides
# Save to reports/
PPTXEOF
```

Refer to the `pptx-generation` skill for the full helper function library (title_slide, content_slide, figure_slide, table_slide, etc.).

## Output

- `reports/<project_name>_presentation.pptx`
- Report the slide count and file path to the user

Related Skills

pptx-posters

from Zaoqu-Liu/ScienceClaw

Create research posters using HTML/CSS that can be exported to PDF or PPTX. Use this skill ONLY when the user explicitly requests PowerPoint/PPTX poster format. For standard research posters, use latex-posters instead. This skill provides modern web-based poster design with responsive layouts and easy visual integration.

pptx-generation

from Zaoqu-Liu/ScienceClaw

Generate academic PowerPoint presentations (.pptx) using python-pptx. Use this skill for making PPT, slides, presentations, 生成PPT, 做PPT, 写PPT, 幻灯片. Provides complete helper functions and templates. Preferred over scientific-slides and frontend-slides for all PPTX generation.

export-latex

from Zaoqu-Liu/ScienceClaw

Export research project findings to a LaTeX manuscript draft with figures, references, and methods. Supports Nature, Cell, Lancet, and generic article formats. Use when user says "导出 LaTeX", "/export latex", "写论文初稿", "export to LaTeX", "generate manuscript", or wants a paper draft from project results. Builds on venue-templates skill.

export-docx

from Zaoqu-Liu/ScienceClaw

Export research project reports to Word (.docx) format with embedded figures and formatted references. Use when user says "导出 Word", "/export word", "转 docx", "生成 Word 报告", "export to Word", or wants a Word document from project results.

zinc-database

from Zaoqu-Liu/ScienceClaw

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

from Zaoqu-Liu/ScienceClaw

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

from Zaoqu-Liu/ScienceClaw

## Overview

scientific-visualization

from Zaoqu-Liu/ScienceClaw

## Overview

venue-templates

from Zaoqu-Liu/ScienceClaw

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.

vaex

from Zaoqu-Liu/ScienceClaw

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

from Zaoqu-Liu/ScienceClaw

Access USPTO APIs for patent/trademark searches, examination history (PEDS), assignments, citations, office actions, TSDR, for IP analysis and prior art searches.

uniprot-database

from Zaoqu-Liu/ScienceClaw

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.