skills.rest
proyecto26
proyecto26OFFICIAL
Explore all skills by this author →
Website𝕏@proyecto_26GitHub

paper-analyzer

Convert academic papers into Markdown and HTML articles via MinerU API.

35|2|Updated Feb 2, 2026
Search Tags:#markdown#HTML#PDF#analyze#papers#MinerU#writing-styles
One-click install
npx skills add https://github.com/proyecto26/sherlock-ai-plugin --skill paper-analyzer
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: paper-analyzer
Source: https://github.com/proyecto26/sherlock-ai-plugin/tree/main/skills/paper-analyzer
Command: npx skills add https://github.com/proyecto26/sherlock-ai-plugin --skill paper-analyzer

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, PyMuPDF, and includes scripts (resource) components.

What problem does it solve?

This Skill transforms academic papers into structured, publication-ready articles by extracting text, figures, tables, and LaTeX formulas, and reformatting them into Markdown and HTML with selectable writing styles.

Core Features & Use Cases

  • MinerU Cloud API for high-precision PDF parsing (text, images, tables, formulas)
  • Multiple writing styles: storytelling, academic, concise
  • Optional formula explanations and GitHub code analysis
  • Output Markdown + HTML with base64-embedded images

Quick Start

Run the conversion using the MinerU-enabled workflow: python scripts/convert_pdf.py <path-to-pdf> <output-dir> To use MinerU Cloud API, set MINERU_TOKEN in your environment: export MINERU_TOKEN=your_token

Frequently Asked Questions about paper-analyzer

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

FAQPage Schema
How do I convert academic PDF papers into Markdown and HTML articles?▼

To convert academic PDF papers into Markdown and HTML articles, use the MinerU Cloud API for high-precision parsing to extract text, images, tables, and LaTeX, then reformat them into structured, publication-ready outputs.

Can I extract LaTeX formulas and tables from research papers automatically?▼

You can extract LaTeX formulas and tables from research papers automatically by utilizing the MinerU API to parse the PDF, ensuring accurate extraction of complex mathematical content and structured data.

Does converting PDF papers to HTML require a MinerU API token?▼

Converting PDF papers to HTML requires a MinerU API token. You must set the MINERU_TOKEN environment variable with your token to access the cloud API for parsing the document.

What writing styles are available when transforming research papers into articles?▼

When transforming research papers into articles, the available writing styles are storytelling, academic, and concise, allowing you to select the tone that best fits your publication requirements.

How to analyze GitHub code and explain formulas from academic papers?▼

To analyze GitHub code and explain formulas from academic papers, the conversion workflow includes optional features for formula explanations and code analysis alongside the primary text and image extraction.

What is the best way to publish academic reports with embedded images from PDF?▼

The best way to publish academic reports with embedded images from PDF is to output Markdown and HTML files with base64-embedded images, ensuring all visual assets remain intact and self-contained.

Related Skills

Explore More Education & Research Skills→
digital-stoic-orgdigital-stoic-org
19

install-dependency

Automate monorepo-aware dependency installation across Python, JavaScript, and system packages.

Official
Intermediate
JackweiStudJackweiStud

x-article-publisher

Publish Markdown articles to X Articles with cover images and rich text.

Community
Advanced
AincFhAincFh

markdown-render

Convert Markdown documents into HTML with syntax highlighting and math support.

Community
Intermediate
jdnichollscjdnichollsc
5

paper-analyzer

Parse academic paper PDFs into structured Markdown and HTML formats.

Community
Advanced