Paper Web

Source: https://github.com/aipoch/medical-research-skills

Paper2All: Academic Paper Conversion Pipeline

When to Use

• Use this skill when the request matches its documented task boundary.
• Use it when the user can provide the required inputs and expects a structured deliverable.
• Prefer this skill for repeatable, checklist-driven execution rather than open-ended brainstorming.

Key Features

• Scope-focused workflow aligned to: Use this skill when converting academic papers to promotional and presentation formats, including interactive websites (Paper2Web), presentation videos (Paper2Video), and conference posters (Paper2Poster). This skill is suitable for paper dissemination, conference preparation, creating explorable academic homepages, generating video abstracts, or producing printable posters from LaTeX or PDF source.
• Documentation-first workflow with no packaged script requirement.
• Reference material available in references/ for task-specific guidance.
• Structured execution path designed to keep outputs consistent and reviewable.

Dependencies

See ## Prerequisites above for related details.

• Python: 3.10+. Repository baseline for current packaged skills.
• Third-party packages: not explicitly version-pinned in this skill package. Add pinned versions if this skill needs stricter environment control.

Example Usage

Skill directory: 20260316/scientific-skills/Academic Writing/paper-2-web
No packaged executable script was detected.
Use the documented workflow in SKILL.md together with the references/assets in this folder.

Example run plan:

1. Read the skill instructions and collect the required inputs.
2. Follow the documented workflow exactly.
3. Use packaged references/assets from this folder when the task needs templates or rules.
4. Return a structured result tied to the requested deliverable.

Implementation Details

See ## Overview above for related details.

• Execution model: validate the request, choose the packaged workflow, and produce a bounded deliverable.
• Input controls: confirm the source files, scope limits, output format, and acceptance criteria before running any script.
• Primary implementation surface: instruction-only workflow in SKILL.md.
• Reference guidance: references/ contains supporting rules, prompts, or checklists.
• Parameters to clarify first: input path, output path, scope filters, thresholds, and any domain-specific constraints.
• Output discipline: keep results reproducible, identify assumptions explicitly, and avoid undocumented side effects.

Overview

This skill enables conversion of academic papers into multiple promotional and presentation formats using the Paper2All autonomous pipeline. The system transforms research papers (LaTeX or PDF) into three main outputs:

1. Paper2Web: Interactive, explorable academic homepages with layout-aware design.
2. Paper2Video: Professional presentation videos with narration, slides, and optional talking-head.
3. Paper2Poster: Print-ready conference posters with professional layouts.

The pipeline leverages LLM-driven content extraction, design generation, and iterative optimization to create high-quality outputs suitable for conferences, journals, preprint repositories, and academic promotion.

When to Use This Skill

Use this skill in the following scenarios:

• Creating conference materials: Prepare posters, presentation videos, and companion websites for academic conferences.
• Promoting research outcomes: Convert published papers or preprints into accessible, engaging web formats.
• Preparing presentation reports: Generate video abstracts or full presentation videos from paper content.
• Disseminating research findings: Create promotional materials for social media, lab websites, or institutional displays.
• Enhancing preprint impact: Add interactive homepages to bioRxiv, arXiv, or other preprint submissions.
• Batch processing: Generate promotional materials for multiple papers simultaneously.

Trigger Phrases:

• "Convert this paper to a website"
• "Generate a conference poster from my LaTeX paper"
• "Create a video presentation for this research"
• "Make an interactive homepage for my paper"
• "Transform my paper into promotional materials"
• "Generate poster and video for my conference talk"

Visual Enhancement with Scientific Schematics

When creating documents with this skill, please consider adding scientific diagrams and schematics to enhance visual communication.

If your document does not yet include schematics or diagrams:

• Use the scientific-schematics skill to generate AI-driven publication-grade figures.
• Simply describe the diagram you want in natural language.
• Nano Banana Pro will automatically generate, review, and optimize the schematics.

For new documents: Scientific schematics should be generated by default to intuitively depict key concepts, workflows, architectures, or relationships described in the text.

How to generate schematics:

python scripts/generate_schematic.py "your diagram description" -o figures/output.png

The AI will automatically:

• Create properly formatted publication-grade images.
• Review and optimize through multiple iterations.
• Ensure accessibility (colorblind-friendly, high-contrast).
• Save output to the figures/ directory.

When to add schematics:

• Paper conversion pipeline diagrams.
• Website layout architecture illustrations.
• Video production workflow.
• Poster design process flowcharts.
• Content extraction diagrams.
• System architecture visualizations.
• Any complex concept that benefits from visualization.

Refer to the scientific-schematics skill documentation for detailed guidance on creating schematics.

Core Capabilities

1. Paper2Web: Interactive Website Generation

Transforms papers into layout-aware interactive academic homepages, going beyond simple HTML conversion.

Core Features:

• Responsive, multi-section layouts adapted to paper content.
• Interactive figures, tables, and citations.
• Mobile-friendly design with navigation features.
• Automatic logo search (via Google Search API).
• Aesthetic optimization and quality assessment.

Best For: Post-publication promotion, preprint enhancement, lab websites, permanent research displays.

→ See references/paper2web.md for detailed documentation

2. Paper2Video: Presentation Video Generation

Generates professional presentation videos with slides, narration, cursor movements, and optional talking-head videos.

Core Features:

• Automatic slide generation from paper structure.
• Natural speech synthesis.
• Synchronized cursor movements and highlights.
• Optional talking-head video using Hallo2 (requires GPU).
• Multi-language support.

Best For: Video abstracts, conference presentations, online talks, course materials, YouTube promotion.

→ See references/paper2video.md for detailed documentation

3. Paper2Poster: Conference Poster Generation

Creates print-ready academic posters with professional layouts and visual design.

Core Features:

• Customizable poster sizes (any dimension).
• Professional design templates.
• Institutional branding support.
• QR code generation for links.
• High-resolution output (300+ DPI).

Best For: Conference poster sessions, symposia, academic exhibitions, virtual conferences.

→ See references/paper2poster.md for detailed documentation

Quick Start

Prerequisites

1. Install Paper2All:

   git clone https://github.com/YuhangChen1/Paper2All.git
   cd Paper2All
   conda create -n paper2all python=3.11
   conda activate paper2all
   pip install -r requirements.txt

2. Configure API Keys (create .env file):

   OPENAI_API_KEY=your_openai_api_key_here
   Optional: GOOGLE_API_KEY and GOOGLE_CSE_ID for logo search

3. Install System Dependencies:

   • LibreOffice (document conversion)
   • Poppler utilities (PDF processing)
   • NVIDIA GPU with 48GB VRAM (optional, for talking-head video)

→ See references/installation.md for complete installation guide

Basic Usage

Generate All Components (website + poster + video):

python pipeline_all.py \
  --input-dir "path/to/paper" \
  --output-dir "path/to/output" \
  --model-choice 1

Generate Website Only:

python pipeline_all.py \
  --input-dir "path/to/paper" \
  --output-dir "path/to/output" \
  --model-choice 1 \
  --generate-website

Generate Poster with Custom Dimensions:

python pipeline_all.py \
  --input-dir "path/to/paper" \
  --output-dir "path/to/output" \
  --model-choice 1 \
  --generate-poster \
  --poster-width-inches 60 \
  --poster-height-inches 40

Generate Video (lightweight pipeline):

python pipeline_light.py \
  --model_name_t gpt-4.1 \
  --model_name_v gpt-4.1 \
  --result_dir "path/to/output" \
  --paper_latex_root "path/to/paper"

→ See references/usage_examples.md for comprehensive workflow examples

Workflow Decision Tree

Use this decision tree to determine which components to generate:

Does the user need paper promotional materials?
│
├─ Need permanent online presence?
│  └─→ Generate Paper2Web (interactive website)
│
├─ Need physical conference materials?
│  ├─→ Poster session? → Generate Paper2Poster
│  └─→ Oral presentation? → Generate Paper2Video
│
├─ Need video content?
│  ├─→ Journal video abstract? → Generate Paper2Video (5-10 minutes)
│  ├─→ Conference talk? → Generate Paper2Video (15-20 minutes)
│  └─→ Social media? → Generate Paper2Video (1-3 minutes)
│
└─ Need complete package?
   └─→ Generate all three components simultaneously

Input Requirements

Supported Input Formats

1. LaTeX Source (Recommended):

paper_directory/
├── main.tex              # Main paper file
├── sections/             # Optional: split sections
├── figures/              # All image files
├── tables/               # Table files
└── bibliography.bib      # References

2. PDF:

• High-quality PDF with embedded fonts.
• Selectable text (not scanned images).
• High-resolution images (300+ DPI preferred).

Input Organization

Single Paper:

input/
└── paper_name/
    ├── main.tex (or paper.pdf)
    ├── figures/
    └── bibliography.bib

Multiple Papers (batch processing):

input/
├── paper1/
│   └── main.tex
├── paper2/
│   └── main.tex
└── paper3/
    └── main.tex

Common Parameters

Model Selection

• --model-choice 1: GPT-4 (best balance of quality and cost).
• --model-choice 2: GPT-4.1 (latest features, higher cost).
• --model_name_t gpt-3.5-turbo: Faster, lower cost (acceptable quality).

Component Selection

• --generate-website: Enable website generation.
• --generate-poster: Enable poster generation.
• --generate-video: Enable video generation.
• --enable-talking-head: Add talking-head to video (requires GPU).

Customization

• --poster-width-inches [width]: Custom poster width.
• --poster-height-inches [height]: Custom poster height.
• --video-duration [seconds]: Target video length.
• --enable-logo-search: Automatically search for institution logos.

Output Structure

Generated output is organized by paper and component:

output/
└── paper_name/
    ├── website/
    │   ├── index.html
    │   ├── styles.css
    │   └── assets/
    ├── poster/
    │   ├── poster_final.pdf
    │   ├── poster_final.png
    │   └── poster_source/
    └── video/
        ├── final_video.mp4
        ├── slides/
        ├── audio/
        └── subtitles/

Best Practices

Input Preparation

1. Use LaTeX when possible: Provides best content extraction and structure.
2. Organize files properly: Keep all resources (images, tables, references) in the paper directory.
3. High-quality images: Use vector formats (PDF, SVG) or high-resolution bitmaps (300+ DPI).
4. Keep LaTeX clean: Remove compiled artifacts, ensure source compiles successfully.

Model Selection Strategy

• GPT-4: Most suitable for production-quality output, conferences, and publishing.
• GPT-4.1: Use when latest features or highest quality is needed.
• GPT-3.5-turbo: For quick drafts, testing, or simple papers.

Component Priority

For urgent deadlines, generate in this order:

1. Website (fastest, most versatile, ~15-30 minutes).
2. Poster (moderate speed, limited by print deadline, ~10-20 minutes).
3. Video (slowest, can be generated later, ~20-60 minutes).

Quality Assurance

Before finalizing output:

1. Website: Test on multiple devices, verify all links work, check image quality.
2. Poster: Print test page, verify text readability from 3-6 feet, check colors.
3. Video: Watch entire video, verify audio-video sync, test on different devices.

Resource Requirements

Processing Time

• Website: 15-30 minutes per paper.
• Poster: 10-20 minutes per paper.
• Video (without talking-head): 20-60 minutes per paper.
• Video (with talking-head): 60-120 minutes per paper.

Computational Requirements

• CPU: Multi-core processor for parallel processing support.
• RAM: Minimum 16GB, 32GB recommended for large papers.
• GPU: Optional for standard output, required for talking-head video (NVIDIA A6000 48GB recommended).
• Storage: 1-5GB per paper depending on components and quality settings.

API Costs (Estimated)

• Website: $0.50-2.00 per paper (GPT-4).
• Poster: $0.30-1.00 per paper (GPT-4).
• Video: $1.00-3.00 per paper (GPT-4).
• Complete package: $2.00-6.00 per paper (GPT-4).

Troubleshooting