glmv-pdf-to-web

Convert PDFs into self-contained academic webpages with outline.json and cropped figures.

Updated Apr 2, 2026
One-click install
npx skills add https://github.com/ViewWay/openclaw-skills --skill glmv-pdf-to-web-viewway
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: glmv-pdf-to-web
Source: https://github.com/ViewWay/openclaw-skills/tree/main/glmv-pdf-to-web
Command: npx skills add https://github.com/ViewWay/openclaw-skills --skill glmv-pdf-to-web-viewway

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pymupdf, Pillow, and includes scripts (resource) components.

What problem does it solve?

This workflow converts a PDF document into a self-contained, shareable academic web page. It generates a structured outline.json and crops figures locally, enabling an immediately publishable project page.

Core Features & Use Cases

  • Single-page academic website from a PDF: Creates a browsable page with title, authors, venue, and links.
  • Local processing: Renders images at DPI 120, saves crops, and builds a complete HTML site without remote services.
  • Use Case: Researchers can convert papers or reports into polished online pages for GitHub Pages or project portfolios.

Quick Start

Provide a PDF file and the skill will generate a self-contained academic webpage with outline.json and a local index.html.

Frequently Asked Questions about glmv-pdf-to-web

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert a research paper PDF into a single-page academic website?

To convert a research paper PDF into a single-page academic website, this skill processes local files or URLs to generate a structured outline.json and locally crop figures using PyMuPDF and Pillow. It outputs a self-contained HTML site for offline viewing or deployment.

Can I build a project portfolio page from a technical report PDF without remote services?

You can build a project portfolio page from a technical report PDF entirely through local processing. The workflow renders images at DPI 120, saves local crops, and builds a complete HTML site without relying on remote services.

Does this PDF to HTML conversion tool support Chinese and English documents?

This PDF to HTML conversion tool supports both English and Chinese documents. It parses research papers, technical reports, and project documents to generate a polished webpage with titles, authors, and venue links.

What is the best way to crop figures from a PDF for an academic webpage locally?

The best way to crop figures from a PDF locally is using a workflow that coordinates PyMuPDF for rendering and Pillow for image processing. This skill crops figures and saves them so the generated HTML site references local crops via relative paths.

How do I deploy an offline academic webpage generated from a PDF?

To deploy an offline academic webpage generated from a PDF, you use the self-contained output produced by this skill. The resulting single-page site includes local image crops and an index.html file, making it suitable for immediate deployment to GitHub Pages.

Do I need Python dependencies installed to generate an academic webpage from a PDF?

You need the PyMuPDF and Pillow Python dependencies installed to generate an academic webpage from a PDF. These libraries handle document rendering and image cropping to produce the self-contained HTML site and outline.json.